NeurIPS2026 论文笔记 TODO¶
总计: 2271 篇 | 已完成: 2271 | 待更新: 0
- \(R^3\): 3D Reconstruction via Relative Regression | arXiv: 2605.26519
- 2d spatial reasoning with adaptive neural cellular automata | arXiv: 2610.08518 | 📄 ../paper_cache/NeurIPS2026/2610.08518.txt
- 3d point splatting for mmwave radar novel view synthesis | arXiv: 2609.11894
- 3d-vital visibility-aware identity training from artificial liftings of 3d recon | arXiv: 2610.16692
- 3dcodebench benchmarking agentic procedural 3d modeling via code | arXiv: 2606.01057 | 📄 ../paper_cache/NeurIPS2026/2606.01057.txt
- a benchmark for omni-modal reasoning in long videos | arXiv: 2512.16978
- a biconvex formulation for stable transport of mixture models with a unique solu | arXiv: 2606.02515 | 📄 ../paper_cache/NeurIPS2026/2606.02515.txt
- a bitter lesson for data filtering | arXiv: 2605.19407 | 📄 ../paper_cache/NeurIPS2026/2605.19407.txt
- a closer look at dynamic scene graph generation in the era of multimodal large l | arXiv: 2503.15846
- a comprehensive view of fairness through distributional stability | arXiv: 2609.37061 | 📄 ../paper_cache/NeurIPS2026/2609.37061.txt
- a distribution mapping approach to counterfactually fair reinforcement learning | arXiv: 2608.08743 | 📄 ../paper_cache/NeurIPS2026/2608.08743.txt
- a few teacher steps go a long way cost-efficient on-policy data augmentation for | arXiv: 2607.04574 | 📄 ../paper_cache/NeurIPS2026/2607.04574.txt
- a free lunch in llm compression revisiting retraining after pruning | arXiv: 2510.14444
- a geometric perspective on reward function updates in inverse reinforcement lear | arXiv: 2610.14041 | 📄 ../paper_cache/NeurIPS2026/2610.14041.txt
- a kernel nonconformity score for multivariate conformal prediction | arXiv: 2604.21595 | 📄 ../paper_cache/NeurIPS2026/2604.21595.txt
- a latent control model for realistic rodent motion | arXiv: 2610.27279
- a matched-budget audit framework for recaptioned image-text supervision distribu | arXiv: 2610.00952 | 📄 ../paper_cache/NeurIPS2026/2610.00952.txt
- a memory efficient unified algorithm for online learning of linear dynamical sys | arXiv: 2607.02050 | 📄 ../paper_cache/NeurIPS2026/2607.02050.txt
- a minimal interpretable architecture for zero-shot reconstruction of dynamical s | arXiv: 2607.14937 | 📄 ../paper_cache/NeurIPS2026/2607.14937.txt
- a multi-scale information geometry reveals the structure of mutual information i | arXiv: 2605.06304 | 📄 ../paper_cache/NeurIPS2026/2605.06304.txt
- a near-optimal sq lower bound for smoothed agnostic learning of boolean halfspac | arXiv: 2605.02350 | 📄 ../paper_cache/NeurIPS2026/2605.02350.txt
- a novel schur-decomposition-based weight projection method for stable state-spac | arXiv: 2605.14489 | 📄 ../paper_cache/NeurIPS2026/2605.14489.txt
- a principled optimal transport framework for frame selection in long video under | arXiv: 2610.27692
- a provably convergent and practical algorithm for gromovwasserstein optimal tran | arXiv: 2605.04175 | 📄 ../paper_cache/NeurIPS2026/2605.04175.txt
- a reduction from delayed to immediate feedback for online convex optimization wi | arXiv: 2602.02634 | 📄 ../paper_cache/NeurIPS2026/2602.02634.txt
- a scalable measure of loss landscape curvature for analyzing the training dynami | arXiv: 2601.16979 | 📄 ../paper_cache/NeurIPS2026/2601.16979.txt
- a scalable nonparametric continuous-time survival model through numerical quadra | arXiv: 2605.16208 | 📄 ../paper_cache/NeurIPS2026/2605.16208.txt
- a self-evolving framework for efficient terminal agents via observational contex | arXiv: 2604.19572 | 📄 ../paper_cache/NeurIPS2026/2604.19572.txt
- a semantic-sampling framework for evaluating calibration in open-ended question | arXiv: 2605.08432 | 📄 ../paper_cache/NeurIPS2026/2605.08432.txt
- a simple model of co-emergence of grid and place fields | arXiv: 2605.21356 | 📄 ../paper_cache/NeurIPS2026/2605.21356.txt
- a single-sample polylogarithmic regret bound for nonstationary online linear pro | arXiv: 2603.14673 | 📄 ../paper_cache/NeurIPS2026/2603.14673.txt
- a statistical framework for algorithmic collective action with multiple collecti | arXiv: 2605.06749 | 📄 ../paper_cache/NeurIPS2026/2605.06749.txt
- a statistical theory of gated attention through the lens of hierarchical mixture | arXiv: 2602.01468 | 📄 ../paper_cache/NeurIPS2026/2602.01468.txt
- a steerable deep network for model-free diffusion mri registration | arXiv: 2501.04794
- a stratified multi-rater evaluation of llm-based virtual standardized patients w | arXiv: 2610.29312
- a systematic analysis of out-of-distribution detection under representation and | arXiv: 2511.11934
- a systematic evaluation of co-folding model representations for small-molecule l | arXiv: 2602.13249 | 📄 ../paper_cache/NeurIPS2026/2602.13249.txt
- a systematic evaluation of vision-language models for observational astronomical | arXiv: 2604.24589 | 📄 ../paper_cache/NeurIPS2026/2604.24589.txt
- A Theoretical Analysis of Test-Driven Code Generation | arXiv: 2602.06098
- a theoretical analysis of why masked diffusion models mitigate the reversal curs | arXiv: 2602.02133
- A Theory of Time-Sensitive Language Generation: Sparse Hallucination Beats Mode Collapse | arXiv: 2605.11302
- a unified approach for computing wasserstein barycenters of discrete and continu | arXiv: 2605.11270 | 📄 ../paper_cache/NeurIPS2026/2605.11270.txt
- a unified framework for adversary-aware differential privacy bounds | arXiv: 2507.08158
- a unified framework for image-to-3d part generation via variable granularity | arXiv: 2610.31671
- a unified perturbation framework for analyzing leaderboard stability and manipul | arXiv: 2605.15761 | 📄 ../paper_cache/NeurIPS2026/2605.15761.txt
- a unified uncertainty representation for graph neural networks via doubly-spectr | arXiv: 2609.35703
- a2eval agentic and automated evaluation for embodied brain | arXiv: 2602.01640 | 📄 ../paper_cache/NeurIPS2026/2602.01640.txt
- abc any-subset autoregression via non-markovian diffusion bridges in continuous | arXiv: 2604.27443 | 📄 ../paper_cache/NeurIPS2026/2604.27443.txt
- absolute state-wise constrained policy optimization high-probability state-wise | arXiv: 2410.01212
- accelerating llm pre-training through flat-direction dynamics enhancement | arXiv: 2602.22681 | 📄 ../paper_cache/NeurIPS2026/2602.22681.txt
- Accelerating Rectified Flow Models via Trajectory-Aware Caching | arXiv: 2605.16789
- accuracy vs accuracy computational tradeoffs between classification rates and ut | arXiv: 2505.16494
- acdc on a budget - alternating sparse phases | arXiv: 2610.27758
- achieving optimal static and dynamic regret simultaneously in bandits with deter | arXiv: 2602.07418 | 📄 ../paper_cache/NeurIPS2026/2602.07418.txt
- action chunking proximal policy optimization with feedback correction | arXiv: 机器人
- Actionable Hallucination Detection: Translating Latent Uncertainty into Agentic Critique | arXiv: 2608.10430
- actionunet improving robustness of vla models with efficient multi-scale fine-tu | arXiv: 2609.34982 | 📄 ../paper_cache/NeurIPS2026/2609.34982.txt
- active context selection improves simple regret in contextual bandits | arXiv: 2605.20040 | 📄 ../paper_cache/NeurIPS2026/2605.20040.txt
- active learning for conditional generative compressed sensing | arXiv: 2605.05435 | 📄 ../paper_cache/NeurIPS2026/2605.05435.txt
- active learning for gaussian process regression under self-induced boltzmann wei | arXiv: 2605.10654 | 📄 ../paper_cache/NeurIPS2026/2605.10654.txt
- active learning from positive and unlabeled examples | arXiv: 2602.02081 | 📄 ../paper_cache/NeurIPS2026/2602.02081.txt
- active learning of conditional generative models via the transport neural tangen | arXiv: 2610.35652 | 📄 ../paper_cache/NeurIPS2026/2610.35652.txt
- actor-accelerated policy dual averaging for reinforcement learning in continuous | arXiv: 2603.10199 | 📄 ../paper_cache/NeurIPS2026/2603.10199.txt
- adacodec a predictive visual code for video mllms | arXiv: 2606.02569 | 📄 ../paper_cache/NeurIPS2026/2606.02569.txt
- adam under generalized smoothness with second-moment-type stochastic gradients | arXiv: 2609.37787
- adam-rec adaptive modality routing for multimodal recommendation | arXiv: 2609.38455 | 📄 ../paper_cache/NeurIPS2026/2609.38455.txt
- adaocc adaptive 3d occupancy prediction for embodied tasks | arXiv: 2609.38864 | 📄 ../paper_cache/NeurIPS2026/2609.38864.txt
- adapting actively on the fly relevance-guided online meta-learning with latent c | arXiv: 2602.17605 | 📄 ../paper_cache/NeurIPS2026/2602.17605.txt
- adapting in the dark efficient and stable test-time adaptation for black-box mod | arXiv: 2604.15609 | 📄 ../paper_cache/NeurIPS2026/2604.15609.txt
- Adaptive Compression and Targeted Perturbation: A Unified Framework for Generalized Audio Deepfake Detection | arXiv: 2610.16049
- adaptive conditional gradient sliding projection-free and line-search-free accel | arXiv: 2601.20443 | 📄 ../paper_cache/NeurIPS2026/2601.20443.txt
- adaptive inference for functionals of m-estimands | arXiv: 2609.39274
- adaptive mass-segmented kv compression for long-context reasoning | arXiv: 2605.23200
- adaptnc adaptive nonconformity scores for conformal prediction under distributio | arXiv: 2602.01629 | 📄 ../paper_cache/NeurIPS2026/2602.01629.txt
- adastate self-evolving anchors for streaming video generation | arXiv: 2605.30349 | 📄 ../paper_cache/NeurIPS2026/2605.30349.txt
- addressable memory for video world models | arXiv: 2608.07408 | 📄 ../paper_cache/NeurIPS2026/2608.07408.txt
- advancing entropy-level credit assignment in rlvr via proximal entropy policy op | arXiv: 2609.39402
- advancing narrative long video generation via training-free identity-aware memor | arXiv: 2605.18733 | 📄 ../paper_cache/NeurIPS2026/2605.18733.txt
- advectra asymmetric latent transport for non-stationary physics | arXiv: 2610.05098 | 📄 ../paper_cache/NeurIPS2026/2610.05098.txt
- adversary-robust learning from fully asynchronous directional derivative estimat | arXiv: 2605.09337 | 📄 ../paper_cache/NeurIPS2026/2605.09337.txt
- advjudge-zero binary decision flips in llm-as-a-judge via adversarial control to | arXiv: 2512.17375
- aegis generative gradient masking for privacy-preserving medical federated learn | arXiv: 2609.38339
- aeon unifying video and 3d world models | arXiv: 2610.28631
- aetdice unified framework and offline optimization for nonlinear multi-objective | arXiv: 2606.31178 | 📄 ../paper_cache/NeurIPS2026/2606.31178.txt
- affectgpt-rl revealing roles of reinforcement learning in open-vocabulary emotio | arXiv: 2605.06126 | 📄 ../paper_cache/NeurIPS2026/2605.06126.txt
- agent2world learning to generate symbolic world models via adaptive multi-agent | arXiv: 2512.22336 | 📄 ../paper_cache/NeurIPS2026/2512.22336.txt
- agentabstain do llm agents know when not to act | arXiv: 2607.10059 | 📄 ../paper_cache/NeurIPS2026/2607.10059.txt
- agentforesight online auditing for early failure prediction in multi-agent syste | arXiv: 2605.08715 | 📄 ../paper_cache/NeurIPS2026/2605.08715.txt
- agenthop a diagnostic benchmark for agentic multi-hop scientific question answer | arXiv: 2609.34428
- agentic abstention do agents know when to stop instead of act | arXiv: 2606.28733 | 📄 ../paper_cache/NeurIPS2026/2606.28733.txt
- agentic ai scientists are not built for autonomous scientific discovery | arXiv: 2605.08956 | 📄 ../paper_cache/NeurIPS2026/2605.08956.txt
- agentic-imodels evolving agentic interpretability tools via autoresearch | arXiv: 2605.03808 | 📄 ../paper_cache/NeurIPS2026/2605.03808.txt
- agentkvshift efficient kv cache reuse for agentic memory systems | arXiv: 2607.21604 | 📄 ../paper_cache/NeurIPS2026/2607.21604.txt
- agentodyssey open-ended long-horizon text game generation for test-time continua | arXiv: 2606.24893 | 📄 ../paper_cache/NeurIPS2026/2606.24893.txt
- agroomni a large-scale multi-view agricultural dataset for cross-scale multimoda | arXiv: 2603.14342 | 📄 ../paper_cache/NeurIPS2026/2603.14342.txt
- ai agents may always fall for prompt injections | arXiv: 2605.17634 | 📄 ../paper_cache/NeurIPS2026/2605.17634.txt
- ai gamestore scalable open-ended evaluation of machine general intelligence with | arXiv: 2602.17594 | 📄 ../paper_cache/NeurIPS2026/2602.17594.txt
- align invert solving inverse problems with diffusion and flow-based models via r | arXiv: 2511.16870
- align3d-ad cross-modal feature alignment and dual-prompt learning for zero-shot | arXiv: 2605.05850 | 📄 ../paper_cache/NeurIPS2026/2605.05850.txt
- aligning flow map policies with optimal q-guidance | arXiv: 2605.12416 | 📄 ../paper_cache/NeurIPS2026/2605.12416.txt
- aligning forest and trees in images long captions for visually grounded understa | arXiv: 2602.02977 | 📄 ../paper_cache/NeurIPS2026/2602.02977.txt
- aligning language model benchmarks with pairwise preferences | arXiv: 2602.02898 | 📄 ../paper_cache/NeurIPS2026/2602.02898.txt
- aligning llms with biomedical knowledge using balanced fine-tuning | arXiv: 2511.21075
- alignment collapse under kv cache quantization diagnosis and mitigation | arXiv: 2606.09864 | 📄 ../paper_cache/NeurIPS2026/2606.09864.txt
- all roads lead to rome flow-driven multi-anchor exploration for open-environment | arXiv: 2609.36889
- allocate marginal reviews to borderline papers using llm comparative ranking | arXiv: 2602.06078 | 📄 ../paper_cache/NeurIPS2026/2602.06078.txt
- allocentric perceiver disentangling allocentric reasoning from egocentric visual | arXiv: 2602.05789 | 📄 ../paper_cache/NeurIPS2026/2602.05789.txt
- allospatial agentic harness framework for spatial reasoning in foundation models | arXiv: 2606.08952 | 📄 ../paper_cache/NeurIPS2026/2606.08952.txt
- almost sure convergence rates of stochastic approximation and reinforcement lear | arXiv: 2605.07104 | 📄 ../paper_cache/NeurIPS2026/2605.07104.txt
- alphapareto formulaic alpha discovery with llm-guided multi-objective reinforcem | arXiv: 2609.34188
- ambientfm a foundation model for ambient sensing | arXiv: 2602.11200 | 📄 ../paper_cache/NeurIPS2026/2602.11200.txt
- amortized linear-time exact shapley value for product-kernel methods | arXiv: 2505.16516
- amortized optimal transport from sliced potentials | arXiv: 2604.15114
- amortized structured stochastic variational inference for gaussian process laten | arXiv: 2610.03647 | 📄 ../paper_cache/NeurIPS2026/2610.03647.txt
- an embarrassingly simple graph heuristic reveals shortcut-solvable benchmarks fo | arXiv: 2605.07125 | 📄 ../paper_cache/NeurIPS2026/2605.07125.txt
- an empirical study on noisy data and llm pretraining loss divergence | arXiv: 2602.02400 | 📄 ../paper_cache/NeurIPS2026/2602.02400.txt
- an enigma of artificial reason investigating the production-evaluation gap in la | arXiv: 2606.01462 | 📄 ../paper_cache/NeurIPS2026/2606.01462.txt
- An exact information theory of generalization phase transitions in Bayesian diffusion models | arXiv: 2607.08041
- an open-source training dataset for foundation models for black-box optimization | arXiv: 2605.23417 | 📄 ../paper_cache/NeurIPS2026/2605.23417.txt
- Analyzing and Guiding Zero-Shot Posterior Sampling in Diffusion Models | arXiv: 2602.07715
- anatomy of off-policy policy gradient importance sampling kl regularization and | arXiv: 2610.25725 | 📄 ../paper_cache/NeurIPS2026/2610.25725.txt
- anchor audio-visually grounded chain-of-thought reasoning benchmark | arXiv: 2610.22964 | 📄 ../paper_cache/NeurIPS2026/2610.22964.txt
- anchor3dgs feed-forward 3d gaussian splatting with compact anchor-based represen | arXiv: 2610.21634
- anchoring adversarial trajectories to data manifolds a bilevel transfer optimiza | arXiv: 2609.38991
- anchorrep defending llms against cross-model adversarial transfer via representa | arXiv: 2609.32602 | 📄 ../paper_cache/NeurIPS2026/2609.32602.txt
- anchorworld embodied egocentric world simulation with view-based evolution custo | arXiv: 2606.07326 | 📄 ../paper_cache/NeurIPS2026/2606.07326.txt
- animation2code evaluating temporal visual reasoning in video-to-code generation | arXiv: 2606.28593 | 📄 ../paper_cache/NeurIPS2026/2606.28593.txt
- annealing in variational inference mitigates mode collapse a theoretical study o | arXiv: 2602.12923 | 📄 ../paper_cache/NeurIPS2026/2602.12923.txt
- AnyEdit: A Unified Framework for Speech and Singing Voice Editing with Real-World Environmental Consistency | arXiv: 2610.15665
- AnyHand: A Large-Scale Synthetic Dataset for RGB(-D) Hand Pose Estimation | arXiv: 2603.25726
- AnyMo: Geometry-Aware Setup-Agnostic Modeling of Human Motion in the Wild | arXiv: 2605.22715
- approaching io-optimality for approximate attention | arXiv: 2605.23751 | 📄 ../paper_cache/NeurIPS2026/2605.23751.txt
- approximation in contrastive representation learning | arXiv: 2610.15388 | 📄 ../paper_cache/NeurIPS2026/2610.15388.txt
- appsolver adaptive patch partitioning for point-wise ship flow prediction on uns | arXiv: 2608.29355
- ar1-zo topology-aware rank-1 zeroth-order queries for high-rank lora fine-tuning | arXiv: 2605.19767 | 📄 ../paper_cache/NeurIPS2026/2605.19767.txt
- arcmark distortion-free multi-byte llm watermark via optimal transport | arXiv: 2602.07235 | 📄 ../paper_cache/NeurIPS2026/2602.07235.txt
- are agents ready to teach a multi-stage benchmark for real-world teaching workfl | arXiv: 2605.14322 | 📄 ../paper_cache/NeurIPS2026/2605.14322.txt
- are multimodal benchmarks really useful item-level multimodal benchmark diagnosi | arXiv: 2610.14542 | 📄 ../paper_cache/NeurIPS2026/2610.14542.txt
- Are Text-to-Image Models Inductivist Turkeys? A Counterfactual Benchmark for Causal Reasoning | arXiv: 2606.24548
- are we making progress in multimodal domain generalization a comprehensive bench | arXiv: 2605.06643 | 📄 ../paper_cache/NeurIPS2026/2605.06643.txt
- Are we really tilting? The mechanics of reward guidance in flow and diffusion models | arXiv: 2606.02884
- are your reasoning models reasoning or guessing a mechanistic analysis of hierar | arXiv: 2601.10679 | 📄 ../paper_cache/NeurIPS2026/2601.10679.txt
- ark a dual-axis multimodal retrieval benchmark along reasoning and knowledge | arXiv: 2602.09839 | 📄 ../paper_cache/NeurIPS2026/2602.09839.txt
- asap attention sink anchored pruning | arXiv: 2605.22372 | 📄 ../paper_cache/NeurIPS2026/2605.22372.txt
- asirf an agentic framework for context-dependent sensitive information redaction | arXiv: 安全
- ask answer and detect role-playing llms for personality detection with question- | arXiv: 2512.08814
- ask answer and detect role-playing llms for personality detection with question- | arXiv: 2512.08814
- aspi seeking ambiguity clarification amplifies prompt injection vulnerability in | arXiv: 2605.17324 | 📄 ../paper_cache/NeurIPS2026/2605.17324.txt
- assaybench an assay-level virtual cell benchmark for llms and agents | arXiv: 2605.10876 | 📄 ../paper_cache/NeurIPS2026/2605.10876.txt
- assessing the robustness of heterogeneous treatment effects in survival analysis | arXiv: 2510.13397
- Asymmetric Hierarchical Anchoring for Robust Audio–Visual Cross-Modal Generalization | arXiv: 2602.03570
- Asymmetric Invertible Threat: Learning Reversible Privacy Defense for Face Recognition | arXiv: 2605.01217
- asymmetric phase coding audio watermarking | arXiv: 2605.07241 | 📄 ../paper_cache/NeurIPS2026/2605.07241.txt
- asymptotically exact negative guidance of diffusion models via positive-unlabele | arXiv: 2610.19802
- asymptotically optimal best arm identification with fixed-budget under different | arXiv: 2610.04600 | 📄 ../paper_cache/NeurIPS2026/2610.04600.txt
- asyncopd how stale can on-policy distillation be | arXiv: 2606.24143 | 📄 ../paper_cache/NeurIPS2026/2606.24143.txt
- at fulltilt real-time open-set 3d macromolecule detection directly from tilted 2 | arXiv: 2604.10766
- at-skm-net an accelerated trainable sampling kaczmarz-motzkin framework for line | arXiv: 2609.30088 | 📄 ../paper_cache/NeurIPS2026/2609.30088.txt
- ati-vla action-centric predictive visionlanguageaction models via actionable ali | arXiv: 2610.01741 | 📄 ../paper_cache/NeurIPS2026/2610.01741.txt
- atlas agentic or latent visual reasoning one word is enough for both | arXiv: 2605.15198 | 📄 ../paper_cache/NeurIPS2026/2605.15198.txt
- atlasvid efficient ultra-high-resolution long video generation via decoupled glo | arXiv: 2605.16649 | 📄 ../paper_cache/NeurIPS2026/2605.16649.txt
- Atom-level Protein Representation Learning Improves Protein Structure Prediction | arXiv: 2605.22133
- Atomic Trajectory Modeling with State Space Models for Biomolecular Dynamics | arXiv: 2603.17633
- AtomMOF: All-Atom Flow Matching for MOF-Adsorbate Structure Prediction | arXiv: 2602.07351
- attack selection in agentic ai control evaluations meaningfully decreases safety | arXiv: 2606.06529 | 📄 ../paper_cache/NeurIPS2026/2606.06529.txt
- attention alignment between humans and vision-language models | arXiv: 2606.17410 | 📄 ../paper_cache/NeurIPS2026/2606.17410.txt
- attention sinks induce gradient sinks massive activations as gradient regulators | arXiv: 2603.17771 | 📄 ../paper_cache/NeurIPS2026/2603.17771.txt
- attention-discounted adaptive sampler for masked diffusion language models | arXiv: 2606.10829
- audible world models spatially aware sound generation for 3d worlds | arXiv: 2609.38444
- Audio-Visual Flamingo: Open Audio-Visual Intelligence for Long and Complex Videos | arXiv: 2607.16107
- AudioCALM: Continuous Autoregressive Language Modeling for Universal Audio Generation | arXiv: 2606.23080
- auditing conformal prediction for language models under inference-time model shi | arXiv: 2610.28937
- auditing cross-lingual fairness in language model watermarking | arXiv: 2608.20047 | 📄 ../paper_cache/NeurIPS2026/2608.20047.txt
- auteur language-driven cinematographic framing for human-centric video generatio | arXiv: 2606.01900 | 📄 ../paper_cache/NeurIPS2026/2606.01900.txt
- authority bias in language models source deference and user agreement are not in | arXiv: LLM对齐
- autoexpert automating 3d lidar annotation from expert-crafted guidelines | arXiv: 2506.02914
- automated kernel discovery towards understanding high-dimensional bayesian optim | arXiv: 2605.20249 | 📄 ../paper_cache/NeurIPS2026/2605.20249.txt
- automated reformulation of robust optimization via memory-augmented large langua | arXiv: 2605.11813 | 📄 ../paper_cache/NeurIPS2026/2605.11813.txt
- automotive-env benchmarking multimodal models in automotive cockpit environments | arXiv: 2509.21143 | 📄 ../paper_cache/NeurIPS2026/2509.21143.txt
- autoregressive appearance prediction for 3d gaussian avatars | arXiv: 2604.00928
- avenue audio-video editing understanding and evaluation | arXiv: 2609.04253 | 📄 ../paper_cache/NeurIPS2026/2609.04253.txt
- avis adaptive test-time scaling for visionlanguage models | arXiv: 2606.11576 | 📄 ../paper_cache/NeurIPS2026/2606.11576.txt
- avo agentic variation operators for autonomous evolutionary search | arXiv: 2603.24517 | 📄 ../paper_cache/NeurIPS2026/2603.24517.txt
- avoiding obfuscation with prover-estimator debate | arXiv: 2506.13609
- avsd adaptive-view self-distillation by balancing consensus and teacher-specific | arXiv: 2605.20643 | 📄 ../paper_cache/NeurIPS2026/2605.20643.txt
- B-CALM: Bias-Limited Bayesian Borrowing for RCT-Anchored Treatment Effects under Covariate Mismatch | arXiv: 2607.04036
- b3-pwl gpu-batched branch-and-bound for piecewise-linear optimization with sos2 | arXiv: 2608.28988 | 📄 ../paper_cache/NeurIPS2026/2608.28988.txt
- B[FM]\(^2\): Brain Foundation Model via Flow Matching with SplitUNet | arXiv: 2606.20812
- ba-t an iterative transformer for two-view bundle adjustment | arXiv: 2606.03287
- baba in wonderland online self-supervised dynamics discovery for executable worl | arXiv: 2605.16725 | 📄 ../paper_cache/NeurIPS2026/2605.16725.txt
- back to blackwell closing the loop on intransitivity in multi-objective preferen | arXiv: 2602.19041 | 📄 ../paper_cache/NeurIPS2026/2602.19041.txt
- backdoor purification for lora-tuned llms via null-space projection | arXiv: 2610.00685 | 📄 ../paper_cache/NeurIPS2026/2610.00685.txt
- Balancing Frequencies and Pixels in Flow Matching | arXiv: 2609.02748
- balancing image compression and generation with bootstrapped tokenization | arXiv: 2606.05552 | 📄 ../paper_cache/NeurIPS2026/2606.05552.txt
- balcaprl a balanced framework for rl-based mllm image captioning | arXiv: 2605.07394 | 📄 ../paper_cache/NeurIPS2026/2605.07394.txt
- barycentric guidance turning foundation image editors into continuous affective | arXiv: 2610.16892 | 📄 ../paper_cache/NeurIPS2026/2610.16892.txt
- Baton: Explicit Semantic Blueprints for Joint Video-Audio Generation | arXiv: 2605.25195
- bayesian decision making around experts | arXiv: 2510.08113 | 📄 ../paper_cache/NeurIPS2026/2510.08113.txt
- bayesian decision making observing an expert | arXiv: 2510.08113
- bayesian optimization on function spaces via sparse rkhs manifolds | arXiv: 2610.07417 | 📄 ../paper_cache/NeurIPS2026/2610.07417.txt
- bayesian optimization with fisher information geometry gradient bounds and trust | arXiv: 2609.31107
- bayesian preference learning for test-time steerable reward models | arXiv: 2602.08819 | 📄 ../paper_cache/NeurIPS2026/2602.08819.txt
- bayesian test-time inference of task-aligned similarity from weak interactive fe | arXiv: 2610.18656 | 📄 ../paper_cache/NeurIPS2026/2610.18656.txt
- bayesjudge uncertainty-aware bayesian meta-evaluation of human and llm judgments | arXiv: 2610.11116 | 📄 ../paper_cache/NeurIPS2026/2610.11116.txt
- bayesrag probabilistic mutual evidence corroboration for multimodal retrieval-au | arXiv: 2601.07329 | 📄 ../paper_cache/NeurIPS2026/2601.07329.txt
- bbowp-bench evaluating llms on black-box optimization word problems | arXiv: 2608.02612 | 📄 ../paper_cache/NeurIPS2026/2608.02612.txt
- beacon cross-domain co-training of generative robot policies via best-effort ada | arXiv: 2605.08571 | 📄 ../paper_cache/NeurIPS2026/2605.08571.txt
- behavior pack optimization for video mllm post-training | arXiv: 2610.03141 | 📄 ../paper_cache/NeurIPS2026/2610.03141.txt
- behavioral foundation models for quality diversity | arXiv: 2609.35615
- behavioral geometric supervision aligns video foundation models with human socia | arXiv: 2510.01502
- bench-mfg a benchmark suite for learning in stationary mean field games | arXiv: 2602.12517 | 📄 ../paper_cache/NeurIPS2026/2602.12517.txt
- benchmark for assessing olfactory perception of large language models | arXiv: 2604.00002 | 📄 ../paper_cache/NeurIPS2026/2604.00002.txt
- benchmark health index a systematic framework for benchmarking the benchmarks of | arXiv: 2602.11674 | 📄 ../paper_cache/NeurIPS2026/2602.11674.txt
- benchmarking and improving monitors for out-of-distribution alignment failure in | arXiv: 2605.21602 | 📄 ../paper_cache/NeurIPS2026/2605.21602.txt
- benchmarking attention for tabular foundation models | arXiv: 2609.31306 | 📄 ../paper_cache/NeurIPS2026/2609.31306.txt
- benchmarking compositional generalisation for machine learning interatomic poten | arXiv: 2605.08988
- benchmarking multimodal mathematical reasoning with explicit visual dependency
- benchmarking optimizers for large language model pretraining | arXiv: 2509.01440
- benchmarking sensor-fault robustness in forecasting | arXiv: 2605.10822 | 📄 ../paper_cache/NeurIPS2026/2605.10822.txt
- benchmarks are not atomic composition-aware llm evaluation using benchhub | arXiv: 2506.00482
- bernini latent semantic planning for video diffusion | arXiv: 2605.22344 | 📄 ../paper_cache/NeurIPS2026/2605.22344.txt
- Bernoulli Flow Models: Self-Consistent Generative Modeling for Binary Data | arXiv: 2610.11362
- beyond chamfer distance granular order-aware evaluation metric for online mappin | arXiv: 2605.22578 | 📄 ../paper_cache/NeurIPS2026/2605.22578.txt
- beyond distribution matching self-supervised representation forcing for few-step | arXiv: 2610.35594 | 📄 ../paper_cache/NeurIPS2026/2610.35594.txt
- beyond drug discovery the nanotechnology molecular optimization nmo benchmark | arXiv: 计算生物
- beyond empirical support structured outlier generation via sinkhorn optimal tran | arXiv: 2609.31470
- beyond fixed benchmarks and worst-case attacks dynamic boundary evaluation for l | arXiv: 2605.06213 | 📄 ../paper_cache/NeurIPS2026/2605.06213.txt
- beyond iid how general are tabular foundation models really | arXiv: 2606.30410 | 📄 ../paper_cache/NeurIPS2026/2606.30410.txt
- beyond interpretability when why and how sparse autoencoders enable label-free v | arXiv: 2506.01247
- beyond linear activation steering invertible latent transformations for controll | arXiv: 2606.08454 | 📄 ../paper_cache/NeurIPS2026/2606.08454.txt
- beyond maximum likelihood variational inequality estimation for generalized line | arXiv: 2511.03087
- beyond missing rates rethinking incomplete multi-view clustering with protocol d | arXiv: 2606.04857
- beyond modality fusion deep ensembles for multimodal classification | arXiv: 2607.05019 | 📄 ../paper_cache/NeurIPS2026/2607.05019.txt
- beyond normal references discriminative few-shot anomaly detection | arXiv: 2605.23231
- beyond prediction steering vlm agents with retrospective world modeling | arXiv: 2609.39101
- beyond raw context transfer representation-based federated retrieval-augmented g | arXiv: 2609.22162 | 📄 ../paper_cache/NeurIPS2026/2609.22162.txt
- beyond scalar distances semantic attribute gradients from frozen mllms for visua | arXiv: 2606.15134 | 📄 ../paper_cache/NeurIPS2026/2606.15134.txt
- beyond selection token parameterization for extreme visual token compression | arXiv: VLM Efficiency
- Beyond Self-Play and Scale: A Behavior Benchmark for Generalization in Autonomous Driving | arXiv: 2605.10034
- beyond sft-to-rl pre-alignment via black-box on-policy distillation for multimod | arXiv: 2604.28123 | 📄 ../paper_cache/NeurIPS2026/2604.28123.txt
- beyond single expert harmonizing diverse visual priors in mllms for spatial unde | arXiv: 2607.15054 | 📄 ../paper_cache/NeurIPS2026/2607.15054.txt
- beyond spatial-domain supervision a relation constrained space for multi-modal i | arXiv: 2609.38968
- beyond steering vector flow-based activation steering for inference-time interve | arXiv: 2605.05892 | 📄 ../paper_cache/NeurIPS2026/2605.05892.txt
- beyond the training distribution evaluating predictions under distribution shift | arXiv: 2606.14506 | 📄 ../paper_cache/NeurIPS2026/2606.14506.txt
- beyond thinking imagining in 360circ for humanoid visual search | arXiv: 2605.09146 | 📄 ../paper_cache/NeurIPS2026/2605.09146.txt
- beyond vit tokens masked-diffusion pretrained convolutional pathology foundation | arXiv: 2605.08276 | 📄 ../paper_cache/NeurIPS2026/2605.08276.txt
- beyond what seems necessary hidden gains from scaling training-time reasoning le | arXiv: 2602.00927 | 📄 ../paper_cache/NeurIPS2026/2602.00927.txt
- beyond worst-case coreset bounds for k-clustering via determinantal sampling | arXiv: 2609.06394 | 📄 ../paper_cache/NeurIPS2026/2609.06394.txt
- bias-id a framework for analyzing transformation biases in ai-generated image de | arXiv: 2605.31153 | 📄 ../paper_cache/NeurIPS2026/2605.31153.txt
- bidirectional information flow bif - a sample efficient hierarchical gaussian pr | arXiv: 2505.11294
- bidirectional sparse attention for faster video diffusion training | arXiv: 2509.01085
- bimogen bidirectional motion-text generation via unified masked discrete diffusi | arXiv: 2609.35407
- binding multiple modalities via multimodal wasserstein barycenter | arXiv: 多模态VLM
- bioblobs unsupervised discovery of functional substructures for protein function | arXiv: 2510.01632
- bird-rl scaling agentic reinforcement learning over stateful data-centric enviro | arXiv: 2610.29426
- bishield-tee on the in-security of unilateral weight obfuscation in on-device te | arXiv: 2610.21565 | 📄 ../paper_cache/NeurIPS2026/2610.21565.txt
- BitDance: Scaling Autoregressive Generative Models with Binary Tokens | arXiv: 2602.14041
- bitmtp when multi-token prediction meets low-bit large language models | arXiv: 2610.28500
- blarm animating 3d objects from video via blending latent rigid motion primitive | arXiv: 2608.31113
- blend balancing personalization vs generalization in federated visionlanguage mo | arXiv: 2610.12907 | 📄 ../paper_cache/NeurIPS2026/2610.12907.txt
- block sparse flash attention | arXiv: 2512.07011
- block sphere vector quantization | arXiv: 2605.19972 | 📄 ../paper_cache/NeurIPS2026/2605.19972.txt
- block-r1 rethinking the role of block size in multi-domain reinforcement learnin | arXiv: 2605.11726 | 📄 ../paper_cache/NeurIPS2026/2605.11726.txt
- boldsymbolf-opd stabilizing long-horizon on-policy distillation with freshness-a | arXiv: 2605.17862 | 📄 ../paper_cache/NeurIPS2026/2605.17862.txt
- bonsai bayesian optimization with natural simplicity and interpretability | arXiv: 2602.07144 | 📄 ../paper_cache/NeurIPS2026/2602.07144.txt
- boosting inference with guided reasoning stochastic exploration for recursive mo | arXiv: 2605.25230 | 📄 ../paper_cache/NeurIPS2026/2605.25230.txt
- Boosting Text-to-Image Diffusion Models via Core Token Attention-Based Seed Selection | arXiv: 2605.19532
- born-preconditioned learning for iterative neural pde solvers | arXiv: 2603.18527
- bound-conditioned latent inference for progressive image compression | arXiv: 2610.30966
- bounding global and local compression error of signal parameterizations | arXiv: 2606.00126 | 📄 ../paper_cache/NeurIPS2026/2606.00126.txt
- brainpro process-conditioned pretraining with topographic retrieval for large ee | arXiv: 2509.22050
- branching flows discrete continuous and manifold flow matching with splits and d | arXiv: 2511.09465
- breakeven complexity a new perspective on neural partial differential equation s | arXiv: 2605.15399 | 📄 ../paper_cache/NeurIPS2026/2605.15399.txt
- Breaking Adversarial Transferability in Fine-Tuned Speech Recognition | arXiv: 2610.09109
- breaking the group size barrier parameter-efficient group dance generation with | arXiv: 2610.11237 | 📄 ../paper_cache/NeurIPS2026/2610.11237.txt
- breaking the qualityprivacy tradeoff in tabular data generation via in-context l | arXiv: 2605.04911 | 📄 ../paper_cache/NeurIPS2026/2605.04911.txt
- breaking the uniformity trap scaling video diffusion model via splitmoe | arXiv: 2609.38140
- brenier meets adversarial training optimal transport geometry for robust learnin | arXiv: 2609.31363 | 📄 ../paper_cache/NeurIPS2026/2609.31363.txt
- bricker to brace a bracket exposure raw dataset and restoration model for flicke | arXiv: 2606.29845 | 📄 ../paper_cache/NeurIPS2026/2606.29845.txt
- Bridge Graphical Models: Coupling, Projection, and Current-Preserving Dynamics for Generative Modeling | arXiv: 2608.19144
- bridging academia and industry a comprehensive benchmark for attributed graph cl | arXiv: 2602.08519 | 📄 ../paper_cache/NeurIPS2026/2602.08519.txt
- bridging scene generation and planning driving with world model via unifying vis | arXiv: 2603.14948 | 📄 ../paper_cache/NeurIPS2026/2603.14948.txt
- bridging the modality bottleneck in pathology mil through virtual molecular stai | arXiv: 2605.16392 | 📄 ../paper_cache/NeurIPS2026/2605.16392.txt
- brittlebench quantifying llm robustness via prompt sensitivity | arXiv: 2603.13285 | 📄 ../paper_cache/NeurIPS2026/2603.13285.txt
- bso safety alignment is density ratio matching | arXiv: 2605.12339 | 📄 ../paper_cache/NeurIPS2026/2605.12339.txt
- Budgeted Multi-Source Counterfactual Annotation for Off-Policy Evaluation | arXiv: 2610.10974
- building transformation layers for riemannian neural networks | arXiv: 2609.35436
- busterx mllm-powered ai-generated video forgery detection and explanation | arXiv: 2505.12620
- c-lora continual low-rank adaptation for pre-trained visual models | arXiv: 2502.17920
- C3P: Contrastive promoter-protein pretraining yields representations capturing bacterial gene regulation | arXiv: 2605.25242
- cab accelerating flow and diffusion sampling via rectification and corrected ada | arXiv: 2605.16736 | 📄 ../paper_cache/NeurIPS2026/2605.16736.txt
- cairn cross-room 3d scene understanding with topology-aware large multimodal mod | arXiv: 2607.06534
- Calibrating Generative Models to Feature Distributions with MMD Finetuning | arXiv: 2606.19496
- can 4d foundation models remember | arXiv: 2609.20819 | 📄 ../paper_cache/NeurIPS2026/2609.20819.txt
- can circuit alignment predict ood generalization | arXiv: 2609.31996
- can large language models develop gambling addiction | arXiv: 2509.22818
- can linguistic reasoning vectors enhance multimodal reasoning ability | arXiv: 2609.31140
- can llm agents respond to disasters benchmarking heterogeneous geospatial reason | arXiv: 2605.11633 | 📄 ../paper_cache/NeurIPS2026/2605.11633.txt
- can model merging improve aggregation in diloco | arXiv: 2607.03011 | 📄 ../paper_cache/NeurIPS2026/2607.03011.txt
- can pixels alone reveal image origin minimax limits and learnable interfaces for | arXiv: 2609.30997
- can we model the artifacts explicitly disentangle artifacts via pairwise edit re | arXiv: 2610.07916 | 📄 ../paper_cache/NeurIPS2026/2610.07916.txt
- cando cooperative agentic network for layout design optimization | arXiv: 2610.10044 | 📄 ../paper_cache/NeurIPS2026/2610.10044.txt
- canvasmar improving masked autoregressive video prediction with canvas | arXiv: 2510.13669
- carebench evaluating llms emotion understanding by assessing cognitive appraisal | arXiv: 2605.17176 | 📄 ../paper_cache/NeurIPS2026/2605.17176.txt
- casl-vae learning structured latent variables from unpaired data for semi-superv | arXiv: 2607.08254 | 📄 ../paper_cache/NeurIPS2026/2607.08254.txt
- caspian online detection and attribution of cascade attacks in llm multi-agent s | arXiv: 2605.19240 | 📄 ../paper_cache/NeurIPS2026/2605.19240.txt
- cass contribution-aware structured sparsity for model merging | arXiv: 2609.34184
- catch your breath adaptive computation for self-paced sequence production | arXiv: 2510.13879
- causal abstractions categorically unified | arXiv: 2510.05033
- Causal Discovery Under Hard Selection Bias: A New Robust Score-Matching Approach | arXiv: 2610.18075
- causal discovery via transformed low-rank quantile surfaces | arXiv: 2609.16931
- Causal Inference for Sequential Settings under Interference and Latent Confounding | arXiv: 2607.14940
- causal pieces analysing and improving spiking neural networks piece by piece | arXiv: 2504.14015
- Causal Representation Learning for Generalisable Recommendation | arXiv: 2605.27043
- CausalBind: Causal Modeling and Learning for Protein-Molecule Virtual Screening | arXiv: 2610.07340
- CausalDriveBench: Evaluating Causal Reasoning in Vision-Language-Action Models for Autonomous Driving | arXiv: 2609.32157
- CausalMix: Data Mixture as Causal Inference for Language Model Training | arXiv: 2607.01104
- cd-rcm generalizable continuous-depth novel view synthesis for reflectance confo | arXiv: 2606.12635
- cellmsa context modeling for single-cell representation learning | arXiv: 2609.38908
- cephalonauts one a deep fmri dataset for decoding naturalistic speech in the hum | arXiv: 2610.03558 | 📄 ../paper_cache/NeurIPS2026/2610.03558.txt
- chaining 2-fwl gnns for combinatorial graph alignment | arXiv: 2510.03086
- character mixing for video generation | arXiv: 2510.05093
- characterizing the generalization error of random feature regression with arbitr | arXiv: 2605.10290 | 📄 ../paper_cache/NeurIPS2026/2605.10290.txt
- Chasing Label Shifters: A Change-Aware Framework for Dynamic Graph Node Classification | arXiv: 2610.17582
- cheap and powerful tests for supervised subspaces per-component inference for pl | arXiv: 2609.36307
- Chem-PerturBridge: a harmonized compendium of small molecule perturbation transcriptomic effects | arXiv: 2605.31522
- chi-bench can ai agents automate end-to-end long-horizon policy-rich healthcare | arXiv: 2605.16679
- circuitseer mining high-quality data by probing mathematical reasoning circuits | arXiv: 2510.18470
- clarification as supervision reinforcement learning for vision-language interfac | arXiv: 2509.26594
- classification fields arbitrarily fine recursive hierarchical clustering from fe | arXiv: 2605.07119 | 📄 ../paper_cache/NeurIPS2026/2605.07119.txt
- closing the reflection gap a free calibration bonus for agentic rl | arXiv: 2606.14211 | 📄 ../paper_cache/NeurIPS2026/2606.14211.txt
- cmespectrumbench can llms analyze condensed matter spectral data | arXiv: 2610.24304 | 📄 ../paper_cache/NeurIPS2026/2610.24304.txt
- Code2World: A GUI World Model via Renderable Code Generation | arXiv: 2602.09856
- codecsplat ultra-compact latent coding for feed-forward 3d gaussian splatting | arXiv: 2605.25563
- CodeMimicry: Exploiting Safety Generalization Lag in Large Language Models via Structured Code Completion | arXiv: 2609.39902
- codescaler scaling code llm training and test-time inference via reward models | arXiv: 2602.17684
- cofactvla deconfounding vision-language-action models via counterfactual interve | arXiv: 2608.04396 | 📄 ../paper_cache/NeurIPS2026/2608.04396.txt
- cogarena benchmarking multimodal agents on interactive behavioral experiments | arXiv: 2610.36484 | 📄 ../paper_cache/NeurIPS2026/2610.36484.txt
- coherence mechanisms for provable self-improvement | arXiv: 2511.08440
- ColorConceptBench: A Benchmark for Probabilistic Color-Concept Understanding in Text-to-Image Models | arXiv: 2601.16836
- colvr enhancing exploratory latent visual reasoning via contrastive optimization | arXiv: 2605.08802
- combating catastrophic forgetting in continual domain adaptation via knowledge r | arXiv: 2610.28892 | 📄 ../paper_cache/NeurIPS2026/2610.28892.txt
- comet context and multiplicity decomposition for multimodal uncertainty estimati | arXiv: 2606.32012 | 📄 ../paper_cache/NeurIPS2026/2606.32012.txt
- communication-efficient llm adaptation over decentralized gpu meshes | arXiv: 2609.14339
- commutator memory sparse path-local reading and steering in language models | arXiv: 2609.34348
- compact so3 equivariant atomistic foundation models via structural pruning | arXiv: 2605.08885 | 📄 ../paper_cache/NeurIPS2026/2605.08885.txt
- compactsplat spatially adaptive gaussian distribution for feedforward scene reco | arXiv: 2610.13177
- comparing explanations is not enoughexplain the change new standards are needed | arXiv: 2602.02304 | 📄 ../paper_cache/NeurIPS2026/2602.02304.txt
- Compatible Likelihoods for Flow Matching on Manifolds | arXiv: 2610.31981
- complete or sparse a tale of two identifiabilities | arXiv: 2610.20851
- complllm fine-tuning llms to discover complementary signals for decision-making | arXiv: 2602.19458 | 📄 ../paper_cache/NeurIPS2026/2602.19458.txt
- computer science conferences should require nonrepudiable experimental results | arXiv: 2605.08586 | 📄 ../paper_cache/NeurIPS2026/2605.08586.txt
- computing all optimal partial p-wasserstein matchings on the line | arXiv: 2608.18875 | 📄 ../paper_cache/NeurIPS2026/2608.18875.txt
- computing thiele rules on interval elections and their generalizations | arXiv: 2605.03067 | 📄 ../paper_cache/NeurIPS2026/2605.03067.txt
- concept modulation models a unified framework for identifiability and extrapolat | arXiv: 2606.18509 | 📄 ../paper_cache/NeurIPS2026/2606.18509.txt
- concepts in motion temporal concept bottleneck model for interpretable video cla | arXiv: 2509.20899
- concise and logically consistent conformal sets for neuro-symbolic concept-based | arXiv: 2605.18202
- concorde geometry-aware link prediction via decoupled energy minimization | arXiv: 2610.36204 | 📄 ../paper_cache/NeurIPS2026/2610.36204.txt
- Concurrence of Symmetry Breaking and Nonlocality Phase Transitions in Diffusion Models | arXiv: 2605.04830
- condensevla learnable history condensation for efficient multi-frame vla | arXiv: 2610.25927
- Conditional Counterfactual Mean Embeddings: Doubly Robust Estimation and Learning Rates | arXiv: 2602.04736
- conditional misalignment common interventions can hide emergent misalignment beh | arXiv: 2604.25891 | 📄 ../paper_cache/NeurIPS2026/2604.25891.txt
- conformal language modeling via posterior sampling | arXiv: 2606.03731 | 📄 ../paper_cache/NeurIPS2026/2606.03731.txt
- conformal selective acting anytime-valid risk control for rlvr-trained llms | arXiv: 2605.20270
- conqur corner aligned activation quantization via optimized rotations for llms | arXiv: 2605.10793 | 📄 ../paper_cache/NeurIPS2026/2605.10793.txt
- Conservation Laws for Diffusion Models | arXiv: 2607.10067
- consistent geometric deep learning via hilbert bundles and cellular sheaves | arXiv: 2605.06395 | 📄 ../paper_cache/NeurIPS2026/2605.06395.txt
- Constrained Code Generation with Discrete Diffusion | arXiv: 2605.16829
- constrained stochastic spectral preconditioning converges for nonconvex objectiv | arXiv: 2605.11850 | 📄 ../paper_cache/NeurIPS2026/2605.11850.txt
- context value informed in-context reinforcement learning | arXiv: 2509.23209
- Contextual Flow Matching: Adaptive Step Selection in Flow Models for Efficient Visual Generation | arXiv: 2610.03202
- Continual Learning in Modern Hopfield Networks with an Application to Diffusion Models | arXiv: 2605.27975
- continually evolving skill knowledge in vision language action model | arXiv: 2511.18085
- continuous expert assembly instance-conditioned low-rank residuals for all-in-on | arXiv: 2605.06127 | 📄 ../paper_cache/NeurIPS2026/2605.06127.txt
- continuous latent diffusion language model | arXiv: 2605.06548 | 📄 ../paper_cache/NeurIPS2026/2605.06548.txt
- contractbench can llm agents preserve observation contracts | arXiv: 2605.17281
- contrast encodes inductive bias separating slow noise from dynamics in predictiv | arXiv: 2606.07770 | 📄 ../paper_cache/NeurIPS2026/2606.07770.txt
- contrastive adversarial training for robust graph neural networks under label po | arXiv: 2610.24685 | 📄 ../paper_cache/NeurIPS2026/2610.24685.txt
- contrastive distribution matching for amortized sequential monte carlo in discre | arXiv: 2605.23346 | 📄 ../paper_cache/NeurIPS2026/2605.23346.txt
- contrastive representation shaping for llm unlearning | arXiv: 2601.22028
- control-augmented autoregressive diffusion for data assimilation | arXiv: 2510.06637
- controlflow3d distilling multi-view knowledge into latent flow matching for poin | arXiv: 2610.21190
- controllable and content based recommendations | arXiv: 2607.20938 | 📄 ../paper_cache/NeurIPS2026/2607.20938.txt
- controllable dynamic 3d shape generation via 3d trajectories and text | arXiv: 2606.05162
- Controllable Generative Sandbox for Causal Inference | arXiv: 2603.03587
- convergence analysis of newtons method for neural networks in the overparameteri | arXiv: 2605.08352 | 📄 ../paper_cache/NeurIPS2026/2605.08352.txt
- convergence guarantees for federated sarsa with local training and heterogeneous | arXiv: 2512.17688
- convex compositional reasoning models | arXiv: 2605.23395 | 📄 ../paper_cache/NeurIPS2026/2605.23395.txt
- coop2 defining observing and repairing cooperation in llm multi-agent systems | arXiv: 2603.00349 | 📄 ../paper_cache/NeurIPS2026/2603.00349.txt
- copra conditional parameter adaptation with reinforcement learning for video ano | arXiv: 2605.15325 | 📄 ../paper_cache/NeurIPS2026/2605.15325.txt
- Coreset-Induced Conditional Velocity Flow Matching | arXiv: 2605.12951
- corrected integrated laplace approximation for bayesian inference in latent gaus | arXiv: 2605.20345 | 📄 ../paper_cache/NeurIPS2026/2605.20345.txt
- corrective diffusion language models | arXiv: 2512.15596
- correlating cross-iteration noise for dp-sgd using model curvature | arXiv: 2510.05416
- CORVUS: Context Optimization and Reduction Via Underlying Synchronization for LLM Coding Agents | arXiv: 2607.22711
- cost efficient fairness audit under partial feedback | arXiv: 2510.03734
- cost-aware best-llm identification using dueling feedback | arXiv: 2609.30360
- Counterfactual Maps: What They Are and How to Find Them | arXiv: 2602.09128
- counterfactual online conformal prediction under adaptive logging | arXiv: 2609.30811 | 📄 ../paper_cache/NeurIPS2026/2609.30811.txt
- counterfactual rollout replay forkable environments as free process rewards for | arXiv: 2609.33875
- coupled integral pinn for discontinuity | arXiv: 2411.11276
- covariate-adjusted deep causal learning for heterogeneous panel data models | arXiv: 2505.20536
- CoWorld-VLA: Thinking in a Multi-Expert World Model for Autonomous Driving | arXiv: 2605.10426
- CRAFT: Counterfactual-to-Interactive Reinforcement Fine-Tuning for Driving Policies | arXiv: 2605.04470
- crafterdojo a suite of foundation models for building open-ended embodied agents | arXiv: 2508.13530
- crisp fixing flying pixels in latent lidar generation via diffusion decoding | arXiv: 2610.11376
- crumb efficient prior fitted network inference via distributionally matched cont | arXiv: 2606.11473 | 📄 ../paper_cache/NeurIPS2026/2606.11473.txt
- cs-dialogue 基于104小时中英自发对话的语码转换语音识别数据集 | arXiv: 2502.18913
- CS-Dialogue: A 104-Hour Dataset of Spontaneous Mandarin-English Code-Switching Dialogues for Speech Recognition | arXiv: 2502.18913
- CSFlow: Aligning Flow Matching with Human Contrast Sensitivity | arXiv: 2606.08833
- cte-bench counterfactual trace evaluation for stateful software simulators | arXiv: 代码智能
- cumulative-goodness free-riding in forward-forward networks real repairable but | arXiv: 2605.06240
- curriculum multiple shooting for robust training of neural and universal differe | arXiv: 2608.05777 | 📄 ../paper_cache/NeurIPS2026/2608.05777.txt
- curvature beyond positivity greedy guarantees for arbitrary submodular functions | arXiv: 2605.07902 | 📄 ../paper_cache/NeurIPS2026/2605.07902.txt
- curvebench a benchmark for exact topological reasoning over nested jordan curves | arXiv: 2605.14068 | 📄 ../paper_cache/NeurIPS2026/2605.14068.txt
- cybiasbench benchmarking bias in llm agents for cyber-attack scenarios | arXiv: 2605.07830 | 📄 ../paper_cache/NeurIPS2026/2605.07830.txt
- Cyclic Denoising Reveals Ultrastable Memories in Diffusion Models | arXiv: 2606.24000
- d-gap improving out-of-domain robustness via dataset-agnostic and gradient-guide | arXiv: 2511.11286
- D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models | arXiv: 2605.05204
- d2d detector-to-differentiable critic for improved numeracy in text-to-image gen | arXiv: 2510.19278
- d2quant accurate low-bit post-training weight quantization for llms | arXiv: 2602.02546 | 📄 ../paper_cache/NeurIPS2026/2602.02546.txt
- daca-grpo denoising-aware credit assignment for reinforcement learning in diffus | arXiv: 2605.16342 | 📄 ../paper_cache/NeurIPS2026/2605.16342.txt
- data auctions for retrieval augmented generation | arXiv: 2508.16007
- Data-Driven Covariate Selection for Nonparametric and Cycle-Agnostic Causal Effect Estimation | arXiv: 2605.06385
- data-driven soft labeling scales dna read classification to whole-body cell-type | arXiv: 2607.04987
- dd-ranking rethinking the evaluation of dataset distillation | arXiv: 2505.13300
- debate a large-scale benchmark for evaluating opinion dynamics in role-playing l | arXiv: 2510.25110
- decentralized ranking aggregation via gossip convergence and robustness | arXiv: 2602.22847 | 📄 ../paper_cache/NeurIPS2026/2602.22847.txt
- deceptive grounding entity attribution failure in clinical retrieval-augmented g | arXiv: 2607.09349
- decoding the critique mechanism in large reasoning models | arXiv: 2603.16331 | 📄 ../paper_cache/NeurIPS2026/2603.16331.txt
- Decoupled Descent: Exact Test Error Tracking Via Approximate Message Passing | arXiv: 2604.27883
- decoupling action from egocentric observation for world simulation | arXiv: 2610.27946
- Decoupling Conversational Dynamics in Full-Duplex Spoken Models through Reinforcement Learning | arXiv: 2607.07148
- deep double q-learning | arXiv: 2507.00275
- deep ensembles for epistemic uncertainty a frequentist perspective | arXiv: 2510.22063
- deep minds and shallow probes | arXiv: 2605.11448
- deeparrhythmia segment-contextualized ecg arrhythmia classification via selectiv | arXiv: 医学图像
- DegradeQuery: Counterfactual Tuple Pretraining for Context-Aware PROTAC Degradation Prediction | arXiv: 2608.10595
- delayed homomorphic reinforcement learning for environments with delayed feedbac | arXiv: 2604.03641 | 📄 ../paper_cache/NeurIPS2026/2604.03641.txt
- delightful distributed policy gradient | arXiv: 2603.20521 | 📄 ../paper_cache/NeurIPS2026/2603.20521.txt
- Delta-Adapter: Scalable Exemplar-Based Image Editing with Single-Pair Supervision | arXiv: 2605.07940
- depth exploration for llm decoding | arXiv: 2606.29223 | 📄 ../paper_cache/NeurIPS2026/2606.29223.txt
- depth2pose a pose-based benchmark for monocular depth estimation without ground- | arXiv: 2605.19797
- depthmaster unified monocular depth estimation for perspective and panoramic ima | arXiv: 2606.12368
- Designing Reinforcement Learning for Diffusion Models: A Unified Path-Space View | arXiv: 2608.14430
- detecting rlvr training data via structural convergence of reasoning | arXiv: 2602.11792 | 📄 ../paper_cache/NeurIPS2026/2602.11792.txt
- diagnosing and mitigating modality interference in multimodal large language mod | arXiv: 2505.19616
- diagonalizing the softmax hadamard initialization for tractable cross-entropy dy | arXiv: 2512.04006
- didedirect injection with color-texture decoupling for 3d stylization | arXiv: 2610.02044
- Diff-CA: Separating Common and Salient Factors with Diffusion Models | arXiv: 2606.06120
- difference of convex programming in the wasserstein space with applications to m | arXiv: 2606.27767 | 📄 ../paper_cache/NeurIPS2026/2606.27767.txt
- differentiable nonlinear model predictive control | arXiv: 2505.01353
- differentiable retrieval-augmented generation for predicting cellular responses | arXiv: 2603.07233 | 📄 ../paper_cache/NeurIPS2026/2603.07233.txt
- differentiable systematic resampling for variational sequential monte carlo | arXiv: 2610.12094 | 📄 ../paper_cache/NeurIPS2026/2610.12094.txt
- differentially private model merging | arXiv: 2604.20985 | 📄 ../paper_cache/NeurIPS2026/2604.20985.txt
- diffpts rethinking diffusion elbo for probabilistic time series forecasting | arXiv: 2609.32363
- diffract diffusion feature reconstruction and attribution for circuit tracing | arXiv: 2606.15796 | 📄 ../paper_cache/NeurIPS2026/2606.15796.txt
- diffratio training one-step diffusion models without teacher supervision | arXiv: 2502.08005
- diffusion guidance is a controllable policy improvement operator | arXiv: 2505.23458
- diffusion llms are natural adversaries for any llm | arXiv: 2511.00203
- diffusion masked pretraining for dynamic point cloud | arXiv: 2605.03639
- Diffusion Models Observe Only Gradients: A Geometric Perspective on Score Matching Errors | arXiv: 2606.06179
- diffusion models without classifier-free guidance | arXiv: 2502.12154
- digs distribution-informed gaussian splatting for training-free open-vocabulary | arXiv: 2610.16177
- dinocomplete 3d shape completion with distilled semantic priors and state space | arXiv: 2605.26949
- DiPhon: Diffusion on Graphons for Scalable Graph Generation | arXiv: 2607.07232
- direct product flow matching decoupling radial and angular dynamics for few-shot | arXiv: 2605.05054 | 📄 ../paper_cache/NeurIPS2026/2605.05054.txt
- direction-aware offline-to-online learning in linear contextual bandits | arXiv: 2604.24016 | 📄 ../paper_cache/NeurIPS2026/2604.24016.txt
- directuv image-conditioned uv texture generation with surface-aware positional e | arXiv: 2609.34651
- dirotq rotation-aware quantization for 4-bit diffusion transformers | arXiv: 2605.16732 | 📄 ../paper_cache/NeurIPS2026/2605.16732.txt
- disambiguating 2d-3d correspondences in gaussian splatting-based feature fields | arXiv: 2605.07351
- discovering mechanistic models of neural activity system identification in an in | arXiv: 2602.04492 | 📄 ../paper_cache/NeurIPS2026/2602.04492.txt
- discovering phase space structure in learned hamiltonian systems | arXiv: 2509.23003
- discovering what you can control interventional boundary discovery for reinforce | arXiv: 2603.18257 | 📄 ../paper_cache/NeurIPS2026/2603.18257.txt
- discrete diffusion models exploit asymmetry to solve lookahead planning tasks | arXiv: 2602.19980 | 📄 ../paper_cache/NeurIPS2026/2602.19980.txt
- discrete flow matching convergence guarantees under minimal assumptions | arXiv: 2605.08882 | 📄 ../paper_cache/NeurIPS2026/2605.08882.txt
- discretizing continuous time series for imputation with masked diffusion trainin | arXiv: 2608.19119 | 📄 ../paper_cache/NeurIPS2026/2608.19119.txt
- disentangled representation learning via flow matching | arXiv: 2602.05214 | 📄 ../paper_cache/NeurIPS2026/2602.05214.txt
- disentangled sparse representations for concept-separated diffusion unlearning | arXiv: 2605.12122
- disentanglement as identifiable pushforward factorisation | arXiv: 2410.22559
- disentangling dual image references in frequency aware diffusion models for pers | arXiv: 2610.07684 | 📄 ../paper_cache/NeurIPS2026/2610.07684.txt
- disrfm polar riemannian flow matching for structure-preserving graph domain adap | arXiv: 2602.00656 | 📄 ../paper_cache/NeurIPS2026/2602.00656.txt
- distilling graph geometry knowledge gap from gnns to mlps | arXiv: 2610.10520 | 📄 ../paper_cache/NeurIPS2026/2610.10520.txt
- distilling llm feedback for lean theorem proving | arXiv: 2605.30861 | 📄 ../paper_cache/NeurIPS2026/2605.30861.txt
- distilling multi-teacher scoring principles for unsupervised time series anomaly | arXiv: 2610.29063
- distilling what matters confidence-aware selective distillation for large langua | arXiv: 模型压缩
- distinguishing performance from competence in evaluations of humanlike abstract | arXiv: 2510.02125
- distributed online convex optimization with compressed communication optimal reg | arXiv: 2604.09276 | 📄 ../paper_cache/NeurIPS2026/2604.09276.txt
- distribution matching distillation without fake score network | arXiv: 2605.19256 | 📄 ../paper_cache/NeurIPS2026/2605.19256.txt
- distribution shift in missing data imputation a risk-based perspective and impor | arXiv: 2602.06713 | 📄 ../paper_cache/NeurIPS2026/2602.06713.txt
- distributionally robust token optimization in rlhf | arXiv: 2604.08577 | 📄 ../paper_cache/NeurIPS2026/2604.08577.txt
- dit4dit jointly modeling video dynamics and actions for generalizable robot cont | arXiv: 2603.10448 | 📄 ../paper_cache/NeurIPS2026/2603.10448.txt
- diversity curves for graph representation learning | arXiv: 2605.06466 | 📄 ../paper_cache/NeurIPS2026/2605.06466.txt
- Do Coding Agents Deceive Us? Detecting and Preventing Cheating via Capped Evaluation with Randomized Tests | arXiv: 2606.07379
- do composed image retrieval benchmarks require multimodal composition | arXiv: 2605.14787 | 📄 ../paper_cache/NeurIPS2026/2605.14787.txt
- do enterprise systems need learned world models the importance of context to inf | arXiv: 2605.12178 | 📄 ../paper_cache/NeurIPS2026/2605.12178.txt
- do image editing models understand lighting | arXiv: 2606.26738 | 📄 ../paper_cache/NeurIPS2026/2606.26738.txt
- do latent-cot models think step-by-step a mechanistic study on sequential reason | arXiv: 2602.00449 | 📄 ../paper_cache/NeurIPS2026/2602.00449.txt
- do multimodal models imagine electric sheep | arXiv: 2605.09693 | 📄 ../paper_cache/NeurIPS2026/2605.09693.txt
- do sparse autoencoders learn meaningful concept hierarchies | arXiv: 2606.22994 | 📄 ../paper_cache/NeurIPS2026/2606.22994.txt
- docptbench benchmarking end-to-end photographed document parsing and translation | arXiv: 2511.18434
- does synthetic data help empirical evidence from deep learning time series forec | arXiv: 2605.06032 | 📄 ../paper_cache/NeurIPS2026/2605.06032.txt
- does your neural network extrapolate feature engineering as identifiability bias | arXiv: 2605.07483 | 📄 ../paper_cache/NeurIPS2026/2605.07483.txt
- dont let gains fade breaking down policy gradient weights in rl | arXiv: 2607.01490 | 📄 ../paper_cache/NeurIPS2026/2607.01490.txt
- dont pause every prediction matters in a streaming video | arXiv: 2604.24317 | 📄 ../paper_cache/NeurIPS2026/2604.24317.txt
- dont pay attention plant it pretraining attention via learning-to-rank | arXiv: 2410.23066
- doob-based generative policy optimization | arXiv: 2610.28990
- dpiagent divide protocol isolate for agentic reproduction test generation | arXiv: 2608.23341 | 📄 ../paper_cache/NeurIPS2026/2608.23341.txt
- dprivbench benchmarking llms reasoning for differential privacy | arXiv: 2604.15851 | 📄 ../paper_cache/NeurIPS2026/2604.15851.txt
- dream-cubed controllable generative modeling in minecraft by training on billion | arXiv: 2604.22847 | 📄 ../paper_cache/NeurIPS2026/2604.22847.txt
- drift flow matching | arXiv: 2605.17244 | 📄 ../paper_cache/NeurIPS2026/2605.17244.txt
- drill training world models to improve policies not predict pixels | arXiv: 2610.30814 | 📄 ../paper_cache/NeurIPS2026/2610.30814.txt
- DriveFuture: Future-Aware Latent World Models for Autonomous Driving | arXiv: 2605.09701
- drivehierarchy a benchmark for diagnosing vlm driving capabilities from open-loo | arXiv: 2609.31814
- DriveMind: Mind-Evolving Belief Tracking for Closed-Loop Autonomous Driving | arXiv: 2610.32069
- DriveSpatial: A Benchmark for Spatiotemporal Intelligence in VLMs for Autonomous Driving | arXiv: 2605.23176
- driving video retrieval for complex queries with structured grounding | arXiv: 2606.09109
- drogo default representation objective via graph optimization in reinforcement l | arXiv: 2602.00403 | 📄 ../paper_cache/NeurIPS2026/2602.00403.txt
- dt-pbo an interpretable tree-based surrogate model for preferential bayesian opt | arXiv: 2512.14263
- Dual-Pathway Circuits of Object Hallucination in Vision-Language Models | arXiv: 2605.13156
- DUET: Unified Dual-Space Emotion Control for Diffusion and Flow-Matching Driven Text-to-Speech | arXiv: 2606.00066
- dycorm dynamic criterion-aware reward modeling for text-to-image generation | arXiv: 2605.25876 | 📄 ../paper_cache/NeurIPS2026/2605.25876.txt
- dynamic model merging made slim | arXiv: 2605.18904
- dynamic query as budgeting for tiny object detection | arXiv: 2610.33430 | 📄 ../paper_cache/NeurIPS2026/2610.33430.txt
- dynamic regret in online convex optimization with indicator switching costs | arXiv: 优化/理论
- dynamic video generation shaping video generation across time and space | arXiv: 2605.21042 | 📄 ../paper_cache/NeurIPS2026/2605.21042.txt
- dynamics of the transformer residual stream coupling spectral geometry to networ | arXiv: 2605.14258
- dynedit dynamic entropy-guided sequential editing for large language models | arXiv: 2610.34768 | 📄 ../paper_cache/NeurIPS2026/2610.34768.txt
- dynt2i-eval a dynamic evaluation framework for text-to-image models | arXiv: 2605.06170 | 📄 ../paper_cache/NeurIPS2026/2605.06170.txt
- dysurface consistent 4d surface reconstruction via bridging explicit gaussians a | arXiv: 2605.10360
- déjà view looping transformers for multi-view 3d reconstruction | arXiv: 2605.30215
- e-geo a testbed for generative engine optimization in e-commerce | arXiv: 2511.20867
- edge of stochastic stability revisiting the edge of stability for sgd | arXiv: 2412.20553
- edisco equivariant discrete diffusion for euclidean combinatorial optimization | arXiv: 2610.04953 | 📄 ../paper_cache/NeurIPS2026/2610.04953.txt
- edit the bits diff the codes bitwise residual editing for visual autoregressive | arXiv: 2606.13558 | 📄 ../paper_cache/NeurIPS2026/2606.13558.txt
- edit-r2 context-aware reinforcement learning for multi-turn image editing | arXiv: 2606.05950 | 📄 ../paper_cache/NeurIPS2026/2606.05950.txt
- editdistill is it possible to guide video editing with image editing | arXiv: 2610.34303 | 📄 ../paper_cache/NeurIPS2026/2610.34303.txt
- effective biological representation learning by masking gene expression | arXiv: 2605.31562 | 📄 ../paper_cache/NeurIPS2026/2605.31562.txt
- effective context in transformers an analysis of fragmentation and tokenization | arXiv: 2605.13485 | 📄 ../paper_cache/NeurIPS2026/2605.13485.txt
- effectiveness of curriculum learning depends on reward sparsity and competing op | arXiv: 2610.31884
- efficient accurate and stable gradients for neural odes | arXiv: 2410.11648
- efficient adjoint matching for fine-tuning diffusion models | arXiv: 2605.11480
- efficient bias mitigation in t2i diffusion models using concept graphs | arXiv: 2607.03397 | 📄 ../paper_cache/NeurIPS2026/2607.03397.txt
- efficient dataset distillation for pre-trained self-supervised models via statis | arXiv: 自监督学习
- efficient dynamic algorithms for graph neural networks with non-linear propagati | arXiv: 2609.32929
- efficient image synthesis with sphere latent encoder | arXiv: 2605.15592 | 📄 ../paper_cache/NeurIPS2026/2605.15592.txt
- efficient sam3 adaptation for multi-class semantic segmentation via dense compet | arXiv: 2610.27960
- efficient scaling of llm training with flexible context parallelism | arXiv: 2602.21788 | 📄 ../paper_cache/NeurIPS2026/2602.21788.txt
- Efficient Streaming Audio-Visual Target Speaker Extraction for Real-World Acoustic Scenes | arXiv: 2610.32749
- efficient transferable optimal transport via min-sliced transport plans | arXiv: 2511.19741
- egostream a diagnostic benchmark for streaming episodic memory in egocentric vis | arXiv: 2605.31557 | 📄 ../paper_cache/NeurIPS2026/2605.31557.txt
- ehrnote-chatqa a benchmark for evidence-grounded multi-turn clinical question an | arXiv: 2606.15735
- eliciting secret knowledge from language models | arXiv: 2510.01070
- ELMA: Benchmarking Anaphoric Compositions for Long-Term Text-to-Motion Generation | arXiv: 2610.13549
- embodied neurocomputation a framework for interfacing biological neural cultures | arXiv: 2605.13315 | 📄 ../paper_cache/NeurIPS2026/2605.13315.txt
- emerge a benchmark for updating knowledge graphs with emerging textual knowledge | arXiv: 2507.03617
- emergence of distortions in high-dimensional guided diffusion models | arXiv: 2602.00716 | 📄 ../paper_cache/NeurIPS2026/2602.00716.txt
- emergent semantic role understanding in language models | arXiv: 2605.09187 | 📄 ../paper_cache/NeurIPS2026/2605.09187.txt
- emo pretraining mixture of experts for emergent modularity | arXiv: 2605.06663 | 📄 ../paper_cache/NeurIPS2026/2605.06663.txt
- enhancing gaze reasoning in vision foundation models for gaze following | arXiv: 2605.22607 | 📄 ../paper_cache/NeurIPS2026/2605.22607.txt
- enhancing novel view synthesis via geometry grounded set diffusion | arXiv: 2601.07540
- enhancing speech large language models through reinforced behavior alignment | arXiv: 2509.03526
- ensemble modeling for time series forecasting an adaptive robust optimization ap | arXiv: 2304.04308
- ensembling language models with sequential monte carlo | arXiv: 2603.05432 | 📄 ../paper_cache/NeurIPS2026/2603.05432.txt
- Entropy Distribution as a Fingerprint for Hallucinations in Generative Models | arXiv: 2605.28264
- epic efficient predicate-guided inference-time control for compositional text-to | arXiv: 2605.11722 | 📄 ../paper_cache/NeurIPS2026/2605.11722.txt
- equilibrium forcing adaptive video generation without noise conditioning | arXiv: 2608.14706 | 📄 ../paper_cache/NeurIPS2026/2608.14706.txt
- equilibrium matching generative modeling with implicit energy-based models | arXiv: 2510.02300
- equivariant reinforcement learning for clifford quantum circuit synthesis | arXiv: 2605.10910 | 📄 ../paper_cache/NeurIPS2026/2605.10910.txt
- equivariant spherical transformer for efficient molecular modeling | arXiv: 2505.23086
- ergodic risk measures towards a risk-aware foundation for continual reinforcemen | arXiv: 2510.02945
- ergodic trajectory design by learned pushforward maps provable coverage via cond | arXiv: 2605.13063 | 📄 ../paper_cache/NeurIPS2026/2605.13063.txt
- essam a novel competitive evolution strategies approach to reinforcement learnin | arXiv: 2602.01003 | 📄 ../paper_cache/NeurIPS2026/2602.01003.txt
- estimating and orthogonalizing unknown pre-training gradients for continual fine | arXiv: 2609.30935
- estimating model-level membership inference vulnerability without reference mode | arXiv: 2510.19773
- estimating the expected output of wide random mlps more efficiently than samplin | arXiv: 2605.05179 | 📄 ../paper_cache/NeurIPS2026/2605.05179.txt
- estimation of the label-noise transition matrix with performance guarantees via | arXiv: 2609.39829
- evaluating epistemic uncertainty beyond ood detection and active learning | arXiv: 2607.14817 | 📄 ../paper_cache/NeurIPS2026/2607.14817.txt
- evaluating whether llms can reliably connect the dots | arXiv: 2609.38406 | 📄 ../paper_cache/NeurIPS2026/2609.38406.txt
- even sharper bounds for transductive learning and its applications | arXiv: 2609.28459
- eventprune cascaded event-assisted token pruning for efficient first-person dyna | arXiv: 2605.19506 | 📄 ../paper_cache/NeurIPS2026/2605.19506.txt
- every sample counts supervised fine-tuning of language models with pointwise con | arXiv: 2607.08968 | 📄 ../paper_cache/NeurIPS2026/2607.08968.txt
- evochamber test-time co-evolution of multi-agent system at individual team and p | arXiv: 2605.11136 | 📄 ../paper_cache/NeurIPS2026/2605.11136.txt
- evocua evolving computer use agents via learning from scalable synthetic experie | arXiv: 2601.15876 | 📄 ../paper_cache/NeurIPS2026/2601.15876.txt
- evolutionary feature engineering for structured data | arXiv: 2607.01548 | 📄 ../paper_cache/NeurIPS2026/2607.01548.txt
- evolutionary foraging in grids intermittent search dynamics emerge in finite dep | arXiv: 2609.39239
- evolutionary system prompt learning for reinforcement learning in llms | arXiv: 2602.14697 | 📄 ../paper_cache/NeurIPS2026/2602.14697.txt
- evooptigraph weakness-driven coevolution via graph-based structural generation f | arXiv: 2606.26578 | 📄 ../paper_cache/NeurIPS2026/2606.26578.txt
- exact flow linear attention exact solution from continuous-time dynamics | arXiv: 2512.12602
- exact instance compression for convex empirical risk minimization via color refi | arXiv: 2602.00437 | 📄 ../paper_cache/NeurIPS2026/2602.00437.txt
- exact unlearning via quantized sufficient statistics | arXiv: 2610.07197 | 📄 ../paper_cache/NeurIPS2026/2610.07197.txt
- excomm exploration-stage communication for error-resilient agentic test-time sca | arXiv: 2605.22102 | 📄 ../paper_cache/NeurIPS2026/2605.22102.txt
- execution guided line-by-line code generation | arXiv: 2506.10948
- exemplar2vqa a scalable exemplar-driven visual question answering generation fra | arXiv: 2609.37655
- existence precedes value joint modeling of observational existence and evolving | arXiv: 2606.13571 | 📄 ../paper_cache/NeurIPS2026/2606.13571.txt
- expanding the role of diffusion models for robust classifier training | arXiv: 2602.19931 | 📄 ../paper_cache/NeurIPS2026/2602.19931.txt
- expected harm rethinking safety evaluation of misaligned llms | arXiv: 2602.01600 | 📄 ../paper_cache/NeurIPS2026/2602.01600.txt
- explainability matters the effect of liability rules on the healthcare sector | arXiv: 2509.17334
- explaining and preventing alignment collapse in iterative rlhf | arXiv: 2605.04266 | 📄 ../paper_cache/NeurIPS2026/2605.04266.txt
- explanation of dynamic physical field predictions using wassersteingrad applicat | arXiv: 2604.22580 | 📄 ../paper_cache/NeurIPS2026/2604.22580.txt
- exploring mllm-diffusion information transfer with metacanvas | arXiv: 2512.11464
- exposing the illusion of erasure in knowledge editing for llms | arXiv: 2606.23276 | 📄 ../paper_cache/NeurIPS2026/2606.23276.txt
- extended wasserstein-gan approach to causal distribution learning density-free e | arXiv: 2605.10206 | 📄 ../paper_cache/NeurIPS2026/2605.10206.txt
- extending myersons optimal auctions to correlated bidders via neural network int | arXiv: 2610.24240 | 📄 ../paper_cache/NeurIPS2026/2610.24240.txt
- extending roc analysis to uncertainty-aware risk prediction with an interval-bas | arXiv: 2602.04775
- externalized cpdag summaries improve llm causal deduction | arXiv: 2609.31071
- extracting search trees from llm reasoning traces reveals myopic planning | arXiv: 2605.06840
- extracting training data from diffusion language models via infilling | arXiv: 2605.24173 | 📄 ../paper_cache/NeurIPS2026/2605.24173.txt
- f2g-pose geometry-aware foundation feature lifting for direct rgb-d category-lev | arXiv: 2610.31623
- FA-LAM: Focus-Aware Large Avatar Model for One-Shot 4D Animatable Gaussian Head | arXiv: 2607.20922
- facephys state of the heart learning | arXiv: 2512.06275
- factorized spectral representations for reinforcement learning | arXiv: 2607.13498 | 📄 ../paper_cache/NeurIPS2026/2607.13498.txt
- factorizedhmr a hybrid framework for video human mesh recovery | arXiv: 2605.14854
- factual recall in linear associative memories sharp asymptotics and mechanistic | arXiv: 2605.10795 | 📄 ../paper_cache/NeurIPS2026/2605.10795.txt
- FashionChameleon: Towards Real-Time and Interactive Human-Garment Video Customization | arXiv: 2605.15824
- fast 4d mesh generation by spatio-temporal attention chains | arXiv: 2605.19786
- fast and stable gradient approximation for bilinear forms of hermitian matrix fu | arXiv: 2605.12801 | 📄 ../paper_cache/NeurIPS2026/2605.12801.txt
- Fast Organic Crystal Structure Prediction with Unit Cell Flow Matching | arXiv: 2606.03199
- fast rates for offline contextual bandits with forward-kl regularization under s | arXiv: 2605.09214 | 📄 ../paper_cache/NeurIPS2026/2605.09214.txt
- federate the router learning language model routers with sparse and decentralize | arXiv: 2601.22318 | 📄 ../paper_cache/NeurIPS2026/2601.22318.txt
- federated learning by utility-constrained stochastic aggregation for improving r | arXiv: 2605.18020 | 📄 ../paper_cache/NeurIPS2026/2605.18020.txt
- feedback forensics a toolkit to measure ai personality | arXiv: 2509.26305
- feedback world model enables precise guidance of diffusion policy | arXiv: 2605.15705
- feedforward novel view synthesis for heterogeneous cameras | arXiv: 2610.03522
- fill the gap a granular alignment paradigm for visual reasoning in multimodal la | arXiv: 2605.12374 | 📄 ../paper_cache/NeurIPS2026/2605.12374.txt
- film-cam keyed feature modulation for conditional-access watermarking | arXiv: 2610.30347
- finding interpretable prompt-specific circuits in language models | arXiv: 2602.13483 | 📄 ../paper_cache/NeurIPS2026/2602.13483.txt
- findstatbench evaluating large language models on combinatorial code synthesis | arXiv: 2607.18260 | 📄 ../paper_cache/NeurIPS2026/2607.18260.txt
- finevision open data is all you need | arXiv: 2510.17269
- finevla fine-grained instruction alignment for steerable vision-language-action | arXiv: 2605.27284 | 📄 ../paper_cache/NeurIPS2026/2605.27284.txt
- finite-sample performance of gradient descent in logistic regression with gaussi | arXiv: 2606.21683
- fire fine-grained multimodal reasoning for enhanced image generation | arXiv: 2604.13491
- fits interpretable spiking neurons via frequency selectivity and temporal shapin | arXiv: 2605.13071 | 📄 ../paper_cache/NeurIPS2026/2605.13071.txt
- fixed-point masked generative modeling | arXiv: 2605.31215 | 📄 ../paper_cache/NeurIPS2026/2605.31215.txt
- fixed-size active statistical inference | arXiv: 2610.27389
- flame flow enhanced legendre memory models for general time series forecasting | arXiv: 2512.14253
- FLARE: Full-Modality Long-Video Audiovisual Retrieval Benchmark with User-Simulated Queries | arXiv: 2605.10228
- flashbob io-efficient exact backward-over-backward for softmax attention | arXiv: 2609.24089
- flashevolve accelerating agent self-evolution with asynchronous stage orchestrat | arXiv: 2605.08520 | 📄 ../paper_cache/NeurIPS2026/2605.08520.txt
- FlashMol: High-Quality Molecule Generation in as Few as Four Steps | arXiv: 2605.07020
- flatclip reusing image foundation models for fmri representation learning via co | arXiv: 2609.31204 | 📄 ../paper_cache/NeurIPS2026/2609.31204.txt
- flow map denoisers traversing the distortion-perception plane for inverse proble | arXiv: 2606.19802 | 📄 ../paper_cache/NeurIPS2026/2606.19802.txt
- flow matching for count data | arXiv: 2605.07746 | 📄 ../paper_cache/NeurIPS2026/2605.07746.txt
- flow mismatching unsupervised anomaly detection via velocity discrepancies in fl | arXiv: 2605.23070 | 📄 ../paper_cache/NeurIPS2026/2605.23070.txt
- flow-dppo divergence proximal policy optimization for flow matching models | arXiv: 2606.11025 | 📄 ../paper_cache/NeurIPS2026/2606.11025.txt
- flowsteer prompt-only workflow steering exposes planning-time vulnerabilities in | arXiv: 2605.11514 | 📄 ../paper_cache/NeurIPS2026/2605.11514.txt
- flux geometry-aware longitudinal flow matching with mixture of experts | arXiv: 2605.08648 | 📄 ../paper_cache/NeurIPS2026/2605.08648.txt
- fluxlite inference-time proposal control for discrete diffusion models | arXiv: 2609.35947
- flyaoc evaluating agentic ontology curation of drosophila scientific knowledge b | arXiv: 2602.09163
- fmmi flow matching mutual information estimation | arXiv: 2511.08552
- focus align and diffuse time-series-aware keyframe diffusion for cardiac dynamic | arXiv: 2610.19050 | 📄 ../paper_cache/NeurIPS2026/2610.19050.txt
- focus benchmarking retinal model generalization from foundation vision encoders | arXiv: 2609.33158
- focusable monocular depth estimation | arXiv: 2605.11756
- focusing influence mechanism for multi-agent reinforcement learning | arXiv: 2506.19417
- follow the mean reference-guided flow matching | arXiv: 2605.10302 | 📄 ../paper_cache/NeurIPS2026/2605.10302.txt
- fomemo towards foundation models for expensive multi-objective optimization | arXiv: 2509.03244
- forgetting has neighbors localized collateral forgetting in machine unlearning | arXiv: 2605.31317 | 📄 ../paper_cache/NeurIPS2026/2605.31317.txt
- forgetting is not always bad a neuro-inspired memory repair mechanism for poison | arXiv: 2610.13267 | 📄 ../paper_cache/NeurIPS2026/2610.13267.txt
- formal conjectures an open and evolving benchmark for verified discovery in math | arXiv: 2605.13171 | 📄 ../paper_cache/NeurIPS2026/2605.13171.txt
- fractional state space transition for long sequence modeling | arXiv: 2609.36314
- FrED: External Data Influence Estimation via Domain Knowledge Graph Grounding | arXiv: 2607.21615
- free draft-and-verification toward lossless parallel decoding for diffusion larg | arXiv: 2510.00294
- freeing the law with locus a local ordinance corpus for the united states | arXiv: 2606.19334
- frequencyaware flow matching for continuous and consistent robotic action genera | arXiv: 2606.20135 | 📄 ../paper_cache/NeurIPS2026/2606.20135.txt
- from baselines to transport geodesics axiomatic attribution via optimal generati | arXiv: 2603.05093 | 📄 ../paper_cache/NeurIPS2026/2603.05093.txt
- from collapse to improvement statistical perspectives on the evolutionary dynami | arXiv: 2602.10531 | 📄 ../paper_cache/NeurIPS2026/2602.10531.txt
- from cursed to competitive closing the zofo gap via input-to-state stability | arXiv: 2604.25372 | 📄 ../paper_cache/NeurIPS2026/2604.25372.txt
- from density matrices to phase transitions in deep learning spectral early warni | arXiv: 2603.29805 | 📄 ../paper_cache/NeurIPS2026/2603.29805.txt
- from inexact gradients to byzantine robustness acceleration and optimization und | arXiv: 2602.03329 | 📄 ../paper_cache/NeurIPS2026/2602.03329.txt
- from intent to evidence a categorical approach for structural evaluation of deep | arXiv: 2603.25342 | 📄 ../paper_cache/NeurIPS2026/2603.25342.txt
- From Isolated feature to Orbits: Discovering Music Concepts via Multi-SAE Alignment | arXiv: 2610.01864
- from matrix inversion to constraints provably tighter confidence regions for imp | arXiv: 2609.14802 | 📄 ../paper_cache/NeurIPS2026/2609.14802.txt
- from next-token to next-block a principled adaptation path for diffusion llms | arXiv: 2512.06776
- from noise to diversity random embedding injection in llm reasoning | arXiv: 2605.11936 | 📄 ../paper_cache/NeurIPS2026/2605.11936.txt
- from persistence to survival hypothesis testing effect sizes and vectorisation f | arXiv: 2606.11911 | 📄 ../paper_cache/NeurIPS2026/2606.11911.txt
- from pixels to concepts do segmentation models understand what they segment | arXiv: 2605.09591 | 📄 ../paper_cache/NeurIPS2026/2605.09591.txt
- from representational complementarity to dual systems synergizing vlm and vision | arXiv: 2602.10719 | 📄 ../paper_cache/NeurIPS2026/2602.10719.txt
- from retrieval to reasoning agentic mechanism prediction from cell painting prof | arXiv: 2609.36406 | 📄 ../paper_cache/NeurIPS2026/2609.36406.txt
- from topology to retrieval decoding embedding spaces with unified signatures | arXiv: 2511.22150
- from uncertain judgments to calibrated rankings conformal elo estimation for llm | arXiv: 2606.13221 | 📄 ../paper_cache/NeurIPS2026/2606.13221.txt
- from weak data to strong policy q-targets enable provable in-context reinforceme | arXiv: 2609.30391
- from weak signals to strong models preference delta aggregation with lora mergin | arXiv: 2606.00357 | 📄 ../paper_cache/NeurIPS2026/2606.00357.txt
- Frontier Coding Agents Use Metaprogramming to Adapt to Unfamiliar Programming Languages | arXiv: 2606.10933
- frontier language models struggle to copy text can be better viewed in 2d | arXiv: 2607.16072 | 📄 ../paper_cache/NeurIPS2026/2607.16072.txt
- fruc feedforward dynamic scene reconstruction from uncalibrated collaborative dr | arXiv: 2605.29997
- Function graph transformers universally approximate operators between function spaces | arXiv: 2605.17968
- fusion or confusion multimodal complexity is not all you need | arXiv: 2512.22991 | 📄 ../paper_cache/NeurIPS2026/2512.22991.txt
- futon fourier tensor network for implicit neural representations | arXiv: 2602.13414 | 📄 ../paper_cache/NeurIPS2026/2602.13414.txt
- g2tr generation-guided visual token reduction for separate-encoder unified multi | arXiv: 2605.12309
- gate-based feature importance in simulation-based inference for eeg a cautionary | arXiv: 2610.30364
- gaussian splatting-based volumetric video compression with sparse 4d anchors | arXiv: 2609.33969
- gazeflow from human gaze behavior to generative egocentric gaze prediction | arXiv: 人体理解
- gdsd reinforcement learning as guided denoiser self-distillation for diffusion l | arXiv: 2605.29398 | 📄 ../paper_cache/NeurIPS2026/2605.29398.txt
- gen-searcher reinforcing agentic search for image generation | arXiv: 2603.28767 | 📄 ../paper_cache/NeurIPS2026/2603.28767.txt
- GenCOPE: Syn2Real Generalized Category-Level Object Pose Estimation for Robotic Picking | arXiv: 2610.01758
- genenv difficulty-aligned co-evolution between llm agents and environment simula | arXiv: 2512.19682
- generalization analysis of biased stochastic gradient methods for minimax proble | arXiv: 2610.19322 | 📄 ../paper_cache/NeurIPS2026/2610.19322.txt
- Generalized Bayes for Causal Inference | arXiv: 2603.03035
- generalized wasserstein flow matching transport plans everywhere all at once | arXiv: 2605.08424 | 📄 ../paper_cache/NeurIPS2026/2605.08424.txt
- generating from discrete distributions using diffusions insights from random con | arXiv: 2603.20589 | 📄 ../paper_cache/NeurIPS2026/2603.20589.txt
- Generating in the Limit with Infinitely Many Hallucinations | arXiv: 2606.28354
- generation navigator a state-aware agentic framework for image generation | arXiv: 2605.17969 | 📄 ../paper_cache/NeurIPS2026/2605.17969.txt
- generative conformal prediction with optimized coverage allocation | arXiv: 2410.13735
- generative control as optimization time unconditional flow matching for adaptive | arXiv: 2603.17834 | 📄 ../paper_cache/NeurIPS2026/2603.17834.txt
- generative modeling via drifting | arXiv: 2602.04770 | 📄 ../paper_cache/NeurIPS2026/2602.04770.txt
- Generative Scenario Rollouts for End-to-End Autonomous Driving | arXiv: 2601.11475
- genevolve self-evolving image generation agents via tool-orchestrated visual exp | arXiv: 2605.21605 | 📄 ../paper_cache/NeurIPS2026/2605.21605.txt
- genrecon bridging generative priors for multi-view 3d scene reconstruction | arXiv: 2605.23888
- genscale a benchmark for relative object scale in image generation and editing | arXiv: 2609.00525 | 📄 ../paper_cache/NeurIPS2026/2609.00525.txt
- geofidelity-bench evaluating block-conditioned geographic fidelity in text-to-im | arXiv: 2606.23669 | 📄 ../paper_cache/NeurIPS2026/2606.23669.txt
- geometric analysis of neural regression collapse via intrinsic dimension | arXiv: 2510.01105
- geometric inductive biases for semi-supervised equalization the constellation-aw | arXiv: 信号/通信
- geometry of relaxed fair regression a unified framework for aware and unaware se | arXiv: 2605.28233 | 📄 ../paper_cache/NeurIPS2026/2605.28233.txt
- geometry-adaptive explainer for faithful dictionary-based interpretability under | arXiv: 2605.21849 | 📄 ../paper_cache/NeurIPS2026/2605.21849.txt
- geometry-aware similarity metrics for neural representations on riemannian and s | arXiv: 2603.28764 | 📄 ../paper_cache/NeurIPS2026/2603.28764.txt
- geometry-centered 3d latent world models for growing surfaces | arXiv: 2506.03173
- geotransolver learning physics on irregular domains using multi-scale geometry a | arXiv: 2512.20399
- geowind2plan mission-time 3d urban wind prediction for energy-efficient uav plan | arXiv: 机器人
- gfnx fast and scalable library for generative flow networks in jax | arXiv: 2511.16592
- ghost geometry-hierarchical online streaming token eviction for efficient 3d rec | arXiv: 2605.15852
- glare generating listening heads with appropriate reactions | arXiv: 2609.40317
- glint sparsely gated vision-language alignment for fine-grained radiology repres | arXiv: 2606.03180 | 📄 ../paper_cache/NeurIPS2026/2606.03180.txt
- global convergence of four-layer matrix factorization under random initializatio | arXiv: 2511.09925
- global linear convergence of entropy-regularized softmax policy gradient beyond | arXiv: 2605.24939 | 📄 ../paper_cache/NeurIPS2026/2605.24939.txt
- glucofm-bench benchmarking time-series foundation models for blood glucose forec | arXiv: 2606.06881 | 📄 ../paper_cache/NeurIPS2026/2606.06881.txt
- gluing local contexts into global meaning a sheaf-theoretic decomposition of tra | arXiv: 2610.17117 | 📄 ../paper_cache/NeurIPS2026/2610.17117.txt
- glut 3d gaussian lookup table for continuous color transformation | arXiv: 2605.19889
- gmos grounding moving object segmentation in 3d space and time | arXiv: 2605.30352 | 📄 ../paper_cache/NeurIPS2026/2605.30352.txt
- goal-conditioned supervised learning for multi-objective recommendation | arXiv: 2412.08911
- going down memory lane scaling tokens for video stream understanding with dynami | arXiv: 2602.18434 | 📄 ../paper_cache/NeurIPS2026/2602.18434.txt
- gold panning strategic context shuffling for needle-in-haystack reasoning | arXiv: 2510.09770
- golden layers and where to find them improved knowledge editing for large langua | arXiv: 2602.20207 | 📄 ../paper_cache/NeurIPS2026/2602.20207.txt
- good token hunting a hitchhikers guide to token selection for visual geometry tr | arXiv: 2605.23892 | 📄 ../paper_cache/NeurIPS2026/2605.23892.txt
- grade a graph diffusion estimator for frequent subgraph discovery in neural arch | arXiv: 2602.03257 | 📄 ../paper_cache/NeurIPS2026/2602.03257.txt
- gradient routing localizes and removes unintended behaviors in rl | arXiv: 2610.17062
- graph distance based on cause-effect estimands with latents | arXiv: 2510.25037
- Graph Energy Matching: Transport-Aligned Energy-Based Modeling for Graph Generation | arXiv: 2603.23398
- graph learning should move beyond restrictive views of spectral and message-pass | arXiv: 2602.10031 | 📄 ../paper_cache/NeurIPS2026/2602.10031.txt
- graph-regularized sparse autoencoders for llm safety steering | arXiv: 2512.06655
- GraphIP–Bench: How Hard Is It to Steal a Graph Neural Network, and Can We Stop It? | arXiv: 2605.12827
- grasp guided residual adapters with sample-wise partitioning | arXiv: 2512.01675
- greedy alignment principle for optimizer selection | arXiv: 2512.06370
- grid games the power of multiple grids for quantizing large language models | arXiv: 2605.12327 | 📄 ../paper_cache/NeurIPS2026/2605.12327.txt
- group distributionally robust optimization with flexible sample queries | arXiv: 2505.15212
- group perspective matters regulating debate relationships can mitigate blind con | arXiv: 2608.03648 | 📄 ../paper_cache/NeurIPS2026/2608.03648.txt
- gt-harmbench benchmarking ai safety risks through the lens of game theory | arXiv: 2602.12316
- guaranteed noisy cp tensor recovery via riemannian optimization on the segre man | arXiv: 2510.00569
- guiding visual autoregressive models through spectrum weakening | arXiv: 2511.22991
- guitar structured failure diagnosis of gui agents via state transitions | arXiv: 2609.34113 | 📄 ../paper_cache/NeurIPS2026/2609.34113.txt
- gvcc zero-shot video compression via codebook-driven stochastic rectified flow | arXiv: 2603.26571 | 📄 ../paper_cache/NeurIPS2026/2603.26571.txt
- h2g hierarchy-aware hyperbolic grouping for 3d scenes | arXiv: 2605.11967
- hadamard representation scaffolding performance across model-free rl
- Hallucination in World Models is Predictable and Preventable | arXiv: 2606.27326
- HalluWorld: A Controlled Benchmark for Hallucination via Reference World Models | arXiv: 2605.19341
- ham-world soft-hamiltonian world models with selective memory for planning | arXiv: 强化学习
- handedit a unified benchmark for egocentric human-to-robot dexterous hand image | arXiv: 2608.12122 | 📄 ../paper_cache/NeurIPS2026/2608.12122.txt
- handwriting decoding as a challenging motor task for eeg foundation models | arXiv: 2605.15698 | 📄 ../paper_cache/NeurIPS2026/2605.15698.txt
- handwritten text recognition lives in the high-pixel variance subspace | arXiv: 2609.35473
- hardware-friendly token-group activation quantization for low-bit mamba super-re | arXiv: 2610.16261 | 📄 ../paper_cache/NeurIPS2026/2610.16261.txt
- harnessing agentic evolution | arXiv: 2605.13821 | 📄 ../paper_cache/NeurIPS2026/2605.13821.txt
- Hearing is Believing? Evaluating and Analyzing Audio Language Model Sycophancy with SYAUDIO | arXiv: 2601.23149
- heavy-tailed flow matching via random clocks | arXiv: 2607.13841 | 📄 ../paper_cache/NeurIPS2026/2607.13841.txt
- helpbench assessing the ability of llms to provide privacy safety and security a | arXiv: 2606.24819 | 📄 ../paper_cache/NeurIPS2026/2606.24819.txt
- hermes a multi-scale spatial-temporal hypergraph network for stock time series f | arXiv: 2509.23668
- hero a heterogeneity-aware benchmark library for federated continual learning | arXiv: 2607.08784
- hero improving the reliability and sensitivity of generative model evaluation us | arXiv: 2606.29784 | 📄 ../paper_cache/NeurIPS2026/2606.29784.txt
- heterogeneous agent collaborative reinforcement learning | arXiv: 2603.02604 | 📄 ../paper_cache/NeurIPS2026/2603.02604.txt
- hidden forgetting in continual multimodal learning when accuracy survives but gr | arXiv: 2607.02020 | 📄 ../paper_cache/NeurIPS2026/2607.02020.txt
- hidden measurement error in llm pipelines distorts annotation evaluation and ben | arXiv: 2604.11581 | 📄 ../paper_cache/NeurIPS2026/2604.11581.txt
- hierarchical semantic tree anchoring for clip-based class-incremental learning | arXiv: 2511.15633
- higraph a large-scale hierarchical graph dataset for malware analysis | arXiv: 2509.02113
- hilbertgen-3dhilbert--multifractal conditioning for topology-aware 3d generation | arXiv: 2610.22720
- hilora adaptive hierarchical lora routing for training-free domain generalizatio | arXiv: 2510.12266
- hopse scalable higher-order positional and structural encoder for combinatorial | arXiv: 2505.15405
- horizon-stream long-horizon attention for streaming 3d reconstruction | arXiv: 2605.23889
- hots homophily-aware temperature scaling for graph neural network calibration | arXiv: 2609.32426
- how are linear representations learned exact solutions to the dynamics of abstra | arXiv: 2607.08843 | 📄 ../paper_cache/NeurIPS2026/2607.08843.txt
- how data scales in agentic reinforcement learning laws and synthesis strategies | arXiv: 2610.23946
- how deep is your network deep vs shallow learning of transfer operators | arXiv: 2509.19930
- how diffusion models memorize | arXiv: 2509.25705
- how do language models compose functions | arXiv: 2510.01685
- how do language models understand tables a mechanistic analysis of cell location | arXiv: 2602.08548 | 📄 ../paper_cache/NeurIPS2026/2602.08548.txt
- how does personalized memory shape llm behavior benchmarking rational preference | arXiv: 2601.16621 | 📄 ../paper_cache/NeurIPS2026/2601.16621.txt
- how does rl post-training induce skill composition a case study on countdown | arXiv: 2512.01775
- how far are vlms from privacy awareness in the physical world an empirical study | arXiv: 2605.05340 | 📄 ../paper_cache/NeurIPS2026/2605.05340.txt
- How Fine-Tuning Objectives Shape Layer-Wise Information in LLM Hallucination Detection | arXiv: 2610.27711
- how hard is it to rig a benchmark a social choice analysis of leaderboard robust | arXiv: 2605.23628 | 📄 ../paper_cache/NeurIPS2026/2605.23628.txt
- how i learned to stop worrying and love stopgrads stationarity convergence and a | arXiv: 2609.16222 | 📄 ../paper_cache/NeurIPS2026/2609.16222.txt
- how much must a private mempool hide exact leakage thresholds for sandwich attac | arXiv: 2609.31379
- how much of a model do we need redundancy and slimmability in remote sensing fou | arXiv: 2601.22841 | 📄 ../paper_cache/NeurIPS2026/2601.22841.txt
- how neural reward models learn features for policy optimization a single-index a | arXiv: 2605.24749
- how to instruct your robot dense language annotations power robot policy learnin | arXiv: 2605.17077 | 📄 ../paper_cache/NeurIPS2026/2605.17077.txt
- How to make the most of your masked language model for protein engineering | arXiv: 2603.10302
- hsco-bench an agent-driven end-to-end hardware-software co-design benchmark for | arXiv: 2605.19399 | 📄 ../paper_cache/NeurIPS2026/2605.19399.txt
- human cognitive benchmarks reveal foundational visual gaps in mllms | arXiv: 2502.16435
- HumanScore: Benchmarking Human Motions in Generated Videos | arXiv: 2604.20157
- hybrid probabilistic zonotopes for identifiable and refinable predictive uncerta | arXiv: 2608.05454 | 📄 ../paper_cache/NeurIPS2026/2608.05454.txt
- hyco a hybrid neural solver for combinatorial optimization | arXiv: 2609.07990 | 📄 ../paper_cache/NeurIPS2026/2609.07990.txt
- hydra representation harmonized tokenization for multimodal generation and under | arXiv: 2603.15228 | 📄 ../paper_cache/NeurIPS2026/2603.15228.txt
- hyper input convex neural networks for shape constrained learning and optimal tr | arXiv: 2604.26942 | 📄 ../paper_cache/NeurIPS2026/2604.26942.txt
- hypernsde personalized neural sdes for joint staticlongitudinal clinical data ge | arXiv: 2610.07383 | 📄 ../paper_cache/NeurIPS2026/2610.07383.txt
- hypertransport amortized conditioning of t2i generative models | arXiv: 2605.08254 | 📄 ../paper_cache/NeurIPS2026/2605.08254.txt
- i have a stream making self-supervised learning work on continuous video | arXiv: 2609.40333v1
- i-deq a stable inertial deep equilibrium model for image restoration | arXiv: 2605.19705v2
- i2v-detach source grounding detachment for unauthorized image-to-video generatio | arXiv: 2610.23287 | 📄 ../paper_cache/NeurIPS2026/2610.23287.txt
- icat incident-casegrounded adaptive testing for physical-risk prediction in embo | arXiv: 2604.16405 | 📄 ../paper_cache/NeurIPS2026/2604.16405.txt
- icats fast video generation via interaction-aware sparse attention and timestep- | arXiv: 2610.11302
- identified-set geometry of distributional model extraction under top-k censored | arXiv: 2605.10407 | 📄 ../paper_cache/NeurIPS2026/2605.10407.txt
- image2sim scaling embodied navigation via generative neural simulator | arXiv: 2607.05765 | 📄 ../paper_cache/NeurIPS2026/2607.05765.txt
- implicit bias of mirror flow in homogeneous neural networks sparse and dense fea | arXiv: 2605.19458 | 📄 ../paper_cache/NeurIPS2026/2605.19458.txt
- importance-aware obs pruning for diffusion models | arXiv: 2607.20048v3
- Impossibility of Distribution-Free Predictive Inference for Individual Treatment Effects | arXiv: 2605.05051
- improved baselines with representation autoencoders | arXiv: 2605.18324
- improved techniques for fine-tuning flow models via adjoint matching a determini | arXiv: 2605.06583 | 📄 ../paper_cache/NeurIPS2026/2605.06583.txt
- improving flexible image tokenizers for autoregressive image generation | arXiv: 2601.01535 | 📄 ../paper_cache/NeurIPS2026/2601.01535.txt
- improving function space flow matching with kernel optimal transport | arXiv: 2609.38049 | 📄 ../paper_cache/NeurIPS2026/2609.38049.txt
- improving general role-playing agents via psychology-grounded reasoning and role | arXiv: 2606.27025 | 📄 ../paper_cache/NeurIPS2026/2606.27025.txt
- in-context multi-operator learning with deeposets | arXiv: 2512.16074
- information bottleneck-guided adaptive hypergraph transformer for brain disease | arXiv: 2609.37220v1
- information loss and disparate effects in network embeddings | arXiv: 2509.12396
- information templates a new paradigm for intelligent active feature acquisition | arXiv: 2508.18380
- inline critic steers image editing | arXiv: 2605.12724 | 📄 ../paper_cache/NeurIPS2026/2605.12724.txt
- inner product aware quantization provably fast accurate and adaptive algorithms | arXiv: 2606.00289 | 📄 ../paper_cache/NeurIPS2026/2606.00289.txt
- inside the loop a mechanistic study of weight-tied transformers on depth-bound a | arXiv: 2610.24135 | 📄 ../paper_cache/NeurIPS2026/2610.24135.txt
- inspo unlocking intrinsic self-reflection for llm preference optimization | arXiv: 2512.23126
- instruct-particulate scaling feed-forward 3d object articulation with kinematic | arXiv: 2606.14699
- instructing llms to negotiate using reinforcement learning with verifiable rewar | arXiv: 2604.09855 | 📄 ../paper_cache/NeurIPS2026/2604.09855.txt
- intact interval-based task activation consolidation for continual learning | arXiv: 2511.17439
- Integrating Background Knowledge for Scalable Causal Discovery | arXiv: 2607.10456
- Intend, Reflect, Refine: An Adaptive Multimodal Reflection Framework for Autonomous Driving | arXiv: 2606.22913
- interpretable but fragile robustness of concept bottlenecks under geometric-sema | arXiv: 2609.38625v1
- Interpreting Latent Protein Language Model Features with Geometric Annotations | arXiv: 2608.26419
- interpreting neural combinatorial optimization via evolving programmatic bottlen | arXiv: 2606.19741 | 📄 ../paper_cache/NeurIPS2026/2606.19741.txt
- intrinsic-dimension empirical bernstein inequalities for bounded self-adjoint op | arXiv: 2605.15278 | 📄 ../paper_cache/NeurIPS2026/2605.15278.txt
- intrinsically interpretable attention via sparse post-training | arXiv: 2512.05865
- Invaria: Learning Scale and Density Invariance in Point Clouds via Next-Resolution Prediction | arXiv: 2605.15923
- invariant features in language models geometric characterization and model attri | arXiv: 2605.06458 | 📄 ../paper_cache/NeurIPS2026/2605.06458.txt
- investigationworlds an agentic environment for legal investigation | arXiv: 2610.04129 | 📄 ../paper_cache/NeurIPS2026/2610.04129.txt
- ipibench evaluating interactive proactive intelligence of mllms under continuous | arXiv: 2605.27074 | 📄 ../paper_cache/NeurIPS2026/2605.27074.txt
- is agentic ai ready for real-world hardware engineering a deep dive with phoenix | arXiv: 2605.15226 | 📄 ../paper_cache/NeurIPS2026/2605.15226.txt
- is sqrtd separation necessary for gradient em to learn gaussian mixtures in high | arXiv: 2610.07551 | 📄 ../paper_cache/NeurIPS2026/2610.07551.txt
- isotropic activation functions enable deindividuated neurons and adaptive topolo | arXiv: 2602.23405 | 📄 ../paper_cache/NeurIPS2026/2602.23405.txt
- iterative critique-and-routing controller for multi-agent systems with heterogen | arXiv: 2605.08686 | 📄 ../paper_cache/NeurIPS2026/2605.08686.txt
- its all training a fully synthetic single-stage recipe for llms | arXiv: 2609.37891v1
- jacobian descent for multi-objective optimization | arXiv: 2406.16232
- jailbreak susceptibility prediction and mitigation via the behavioral geometry o | arXiv: 2605.26409 | 📄 ../paper_cache/NeurIPS2026/2605.26409.txt
- jointly reinforcing diversity and quality in language model generations | arXiv: 2509.02534
- just ramp-up debiasing regression-based estimator for ab tests under network int | arXiv: 2410.12740
- justitia fair and efficient scheduling of task-parallel llm agents with selectiv | arXiv: 2510.17015 | 📄 ../paper_cache/NeurIPS2026/2510.17015.txt
- justitia 任务并行大模型智能体的公平高效调度与选择性饱和服务 | arXiv: 2510.17015
- kalibench a fine-grained benchmark for cybersecurity tool use on kali linux with | arXiv: 2610.02206 | 📄 ../paper_cache/NeurIPS2026/2610.02206.txt
- kernel token contradiction a fast and principled approach for llm claim uncertai | arXiv: 2608.22506 | 📄 ../paper_cache/NeurIPS2026/2608.22506.txt
- KG-Guard: Graph-Based Hallucination Detection for Knowledge Base Question Answering | arXiv: 2606.00328
- Kinetic-Optimal Scheduling with Moment Correction for Metric-Induced Discrete Flow Matching in Zero-Shot Text-to-Speech | arXiv: 2605.09386
- knn implementation details can dramatically change performance an example from c | arXiv: 2610.16940 | 📄 ../paper_cache/NeurIPS2026/2610.16940.txt
- knowledge transfer scaling laws for 3d medical imaging | arXiv: 2605.06859 | 📄 ../paper_cache/NeurIPS2026/2605.06859.txt
- knowledge-level consistency reinforcement learning dual-fact alignment for long- | arXiv: 2509.23765
- koalags complexity-aware continuous level of detail for gaussian splatting | arXiv: 2610.28615
- kv-cobra kv cache compression via co-optimized bit-rank allocation | arXiv: 2609.24298 | 📄 ../paper_cache/NeurIPS2026/2609.24298.txt
- kv-prm efficient process reward modeling via kv-cache transfer for multi-agent t | arXiv: 2607.09153 | 📄 ../paper_cache/NeurIPS2026/2607.09153.txt
- lacache robust semantic caching for llm serving | arXiv: 2608.01718 | 📄 ../paper_cache/NeurIPS2026/2608.01718.txt
- lafp preserving latent action structure in latent policy learning via flow match | arXiv: 2606.10517 | 📄 ../paper_cache/NeurIPS2026/2606.10517.txt
- langflow continuous diffusion rivals discrete in language modeling | arXiv: 2604.11748 | 📄 ../paper_cache/NeurIPS2026/2604.11748.txt
- language model memory and memory models for language | arXiv: 2602.13466 | 📄 ../paper_cache/NeurIPS2026/2602.13466.txt
- language-conditioned world modeling for visual navigation | arXiv: 2603.26741v2
- laquant a simple overhead-free large reasoning model quantization by layer-wise | arXiv: 2605.08755 | 📄 ../paper_cache/NeurIPS2026/2605.08755.txt
- latent video prediction for world modeling an evaluation uncovering intriguing f | arXiv: 2605.15618v2
- leaf language-eeg aligned foundation model for brain-computer interfaces | arXiv: 2509.24302
- leaner transformers can easily learn to cluster | arXiv: 2610.09760
- learning agentic policy from action guidance | arXiv: 2605.12004 | 📄 ../paper_cache/NeurIPS2026/2605.12004.txt
- learning chance-constrained mdps with bellman distributional certificates | arXiv: 强化学习
- learning discrete riemannian metrics for physical fields with cochain-frame equi | arXiv: 2608.14556
- learning domain trajectories with flow matching for gradual domain adaptation | arXiv: 2610.30685
- learning dynamic evidence routes for vision transformer probing | arXiv: 2605.00915 | 📄 ../paper_cache/NeurIPS2026/2605.00915.txt
- Learning Implicit Bias in Generative Spaces for Accelerating Protein Dynamics Emulation | arXiv: 2606.01833
- learning large-scale competitive team behaviors with mean-field interactions | arXiv: 2504.21164
- learning robust reasoning through guided adversarial self-play | arXiv: 2602.00173 | 📄 ../paper_cache/NeurIPS2026/2602.00173.txt
- learning scenario reduction for two-stage robust optimization with discrete unce | arXiv: 2605.14494 | 📄 ../paper_cache/NeurIPS2026/2605.14494.txt
- learning survival models with right-censored reporting delays | arXiv: 2510.04421
- learning the context of errors black-box online adaptation of time series founda | arXiv: 2606.14222 | 📄 ../paper_cache/NeurIPS2026/2606.14222.txt
- learning theory of transformers local-to-global approximation via softmax partit | arXiv: 2605.08811 | 📄 ../paper_cache/NeurIPS2026/2605.08811.txt
- learning to sample from diffusion models via inverse reinforcement learning | arXiv: 2602.08689 | 📄 ../paper_cache/NeurIPS2026/2602.08689.txt
- learning to trigger reinforcement learning at the large hadron collider | arXiv: 2606.23993 | 📄 ../paper_cache/NeurIPS2026/2606.23993.txt
- learning unbiased permutations via flow matching | arXiv: 2605.16755 | 📄 ../paper_cache/NeurIPS2026/2605.16755.txt
- learning when to trust llm priors a validated framework for semantic prior integ | arXiv: 2601.21410 | 📄 ../paper_cache/NeurIPS2026/2601.21410.txt
- learning where and what to restore for composite image restoration | arXiv: 图像恢复
- learning where it matters geometric anchoring for robust preference alignment | arXiv: LLM对齐
- leech lattice vector quantization for efficient llm compression | arXiv: 2603.11021 | 📄 ../paper_cache/NeurIPS2026/2603.11021.txt
- lemon-zest evolution-informed tokenization for efficient protein language modeli | arXiv: 计算生物
- Less Decoder is More Encoder: Geometric Representation Learning from Novel View Synthesis | arXiv: 2610.03717
- less supervision better generalization weakly supervised fake region localizatio | arXiv: 安全
- lethe link inference attacks for evaluation of edge unlearning methods | arXiv: 2610.21869 | 📄 ../paper_cache/NeurIPS2026/2610.21869.txt
- leveraging error diversity in group rollouts for reinforcement learning | arXiv: 2605.17333 | 📄 ../paper_cache/NeurIPS2026/2605.17333.txt
- leveraging soft prompts for privacy attacks in federated prompt tuning | arXiv: 2601.06641 | 📄 ../paper_cache/NeurIPS2026/2601.06641.txt
- leveraging unlabelled data for generalizable neural population decoding | arXiv: 2607.14086 | 📄 ../paper_cache/NeurIPS2026/2607.14086.txt
- LibEvoBench: Probing Temporal Knowledge Stratification in Code Generation Models | arXiv: 2606.25402
- lie generator networks for nonlinear partial differential equations | arXiv: 2603.29264 | 📄 ../paper_cache/NeurIPS2026/2603.29264.txt
- LiFi: LiDAR Generation from Multi-View Images via Geometric and Semantic Collaborative Guidance | arXiv: 2610.19786
- lifting biomolecular data acquisition | arXiv: 2512.15984
- lime link-based user-item interaction modeling with decoupled xor attention for | arXiv: 2510.18239 | 📄 ../paper_cache/NeurIPS2026/2510.18239.txt
- lime 基于解耦xor注意力与全局链接嵌入的测试期高效扩展推荐模型 | arXiv: 2510.18239
- linguistic trajectory encoding for efficient long-horizon spatial memory in embo | arXiv: 机器人
- listening to the wise few query-key alignment unlocks latent correct answers in | arXiv: 可解释性
- listening to the wise few querykey alignment unlocks latent correct answers in l | arXiv: 2410.02343
- ll-bench rethinking low-level vision evaluation in the era of large-scale genera | arXiv: 2606.02535 | 📄 ../paper_cache/NeurIPS2026/2606.02535.txt
- llm alignment--utility asymmetry under semantic-preserving transformations | arXiv: 2609.32717
- llm judge validation under sparse overlap from inference to design | arXiv: 2609.31857v2
- llm-auction generative auction towards llm-native advertising | arXiv: 2512.10551
- llm-based multi-agent blackboard system for information discovery in data scienc | arXiv: 2510.01285
- load balancing mixture of experts with similarity preserving routers | arXiv: 2506.14038
- local linear convergence of gradient methods for overparameterized gaussian mixt | arXiv: 2605.30936 | 📄 ../paper_cache/NeurIPS2026/2605.30936.txt
- localagent collaborative agentic verification for fine-grained instance-level co | arXiv: 2610.29174 | 📄 ../paper_cache/NeurIPS2026/2610.29174.txt
- localizing input uncertainty quantification for large language models via shaple | arXiv: 2605.28170 | 📄 ../paper_cache/NeurIPS2026/2605.28170.txt
- log-averaged mirror prox for fast large-scale optimal transport in linear space | arXiv: 2511.11359
- Log-Likelihood, Simpson’s Paradox, and the Detection of Machine-Generated Text | arXiv: 2605.06294
- logictree-rag logic tree-guided retrieval-augmented generation for long-form pat | arXiv: 信息检索/RAG
- logit-gap steering a forward-pass diagnostic for alignment robustness | arXiv: 2506.24056
- logsig-ssm time-series modelling with multi-scale log-signature compression for | arXiv: 2610.05051 | 📄 ../paper_cache/NeurIPS2026/2610.05051.txt
- logstop temporal scores over prediction sequences for matching and retrieval | arXiv: 2510.06512
- longscape advancing long-horizon embodied world models with context-aware moe | arXiv: 2509.21790
- look before you reason implicit visual thinking for efficient multimodal reasoni | arXiv: 2610.27341
- loop-free inverse reinforcement learning via sequential value recovery with q-sc | arXiv: 强化学习
- looprpt reinforcement pre-training for looped language models | arXiv: 2603.19714 | 📄 ../paper_cache/NeurIPS2026/2603.19714.txt
- loraspace a pool-wide shared substrate for static and dynamic multi-lora composi | arXiv: 2610.27444
- loratorio an intrinsic approach to lora skill composition
- lost in translation found in embeddings sign language translation and alignment | arXiv: 2512.08040
- lotion smoothing the optimization landscape for quantized training | arXiv: 2510.08757
- low-dimensional adaptation of rectified flow a diffusion and stochastic localiza | arXiv: 2601.15500 | 📄 ../paper_cache/NeurIPS2026/2601.15500.txt
- lpg balancing efficiency and policy reasoning in latent policy guardrails | arXiv: 2605.17329 | 📄 ../paper_cache/NeurIPS2026/2605.17329.txt
- lr-v2x loss-resilient collaborative perception under low-bandwidth communication | arXiv: 2610.11264
- lucidnft lr-anchored multi-reward preference optimization for flow-based real-wo | arXiv: 2603.05947 | 📄 ../paper_cache/NeurIPS2026/2603.05947.txt
- m a modular extensible serving system for multimodal models | arXiv: 2606.12688 | 📄 ../paper_cache/NeurIPS2026/2606.12688.txt
- m-plicits neural implicit surfaces via nested multiscale residuals | arXiv: 2609.28684
- m2e-uav a benchmark and analysis for onboard motion-on-motion event-based tiny u | arXiv: 2605.10496 | 📄 ../paper_cache/NeurIPS2026/2605.10496.txt
- m3 reframing training measures for discretized physical simulations | arXiv: 2605.08843 | 📄 ../paper_cache/NeurIPS2026/2605.08843.txt
- machine unlearning in low-dimensional feature subspace | arXiv: 2601.22456
- MAEB: Massive Audio Embedding Benchmark | arXiv: 2602.16008
- magnifying what matters attention-guided adaptive rendering for visual text comp | arXiv: 2606.12898 | 📄 ../paper_cache/NeurIPS2026/2606.12898.txt
- majority bit-aware watermarking for large language models | arXiv: 2508.03829
- making lora identifiable orthogonal alignment for continual learning | arXiv: 2610.16664 | 📄 ../paper_cache/NeurIPS2026/2610.16664.txt
- mamba can learn low-dimensional targets in-context via test-time feature learnin | arXiv: 2510.12026
- managing self-learning experts under per-round budget constraints | arXiv: 2510.22654
- manifold prior guided deep unfolding for hyperspectral image reconstruction | arXiv: 2610.27874 | 📄 ../paper_cache/NeurIPS2026/2610.27874.txt
- manitaskgen a comprehensive task generator for benchmarking and improving vision | arXiv: 2505.20726
- MAPLE: Latent Multi-Agent Play for End-to-End Autonomous Driving | arXiv: 2605.14201
- mappo maximum a posteriori preference optimization with prior knowledge | arXiv: 2507.21183
- market regime council for dynamic credit assignment in multi-agent llm decision | arXiv: 2605.24490 | 📄 ../paper_cache/NeurIPS2026/2605.24490.txt
- markovian dynamics enforcer feasibility preserving correction on learned dynamic | arXiv: 2609.39888v1
- marktune improving the quality-detectability trade-off in model-embedded llm wat | arXiv: 2512.04044
- Marrying Optimal Transport and ODEs for Unified Continuous-Time 4D Reconstruction and Tracking | arXiv: 2608.09613
- mars harmonizing multimodal convergence via adaptive rank search | arXiv: 2603.00720 | 📄 ../paper_cache/NeurIPS2026/2603.00720.txt
- masksense confronting the visual exploration trap in masked image generation | arXiv: 2610.17009 | 📄 ../paper_cache/NeurIPS2026/2610.17009.txt
- MAST: Label-Efficient, Robust, and Generalizable Sound Detection for Biodiversity Monitoring via Masked Audio Pretraining and Self-Training | arXiv: 2609.15221
- matching-based few-shot semantic segmentation models are interpretable by design | arXiv: 2511.18163
- maxitive donsker-varadhan formulation for possibilistic variational inference | arXiv: 2511.21223
- mc2mark distortion-free multi-bit watermarking for long messages | arXiv: 2602.14030 | 📄 ../paper_cache/NeurIPS2026/2602.14030.txt
- mcphunt an evaluation framework for cross-boundary data propagation in multi-ser | arXiv: 2604.27819 | 📄 ../paper_cache/NeurIPS2026/2604.27819.txt
- MCSplat: Multi-View Photometric and Geometric Consistent Feed-Forward Gaussian Splatting for Driving Scenes | arXiv: 2610.25345
- measuring and decomposing mode separation via the canonical diffusion | arXiv: 2605.08777 | 📄 ../paper_cache/NeurIPS2026/2605.08777.txt
- measuring safety alignment effects in autonomous security agents | arXiv: 2605.19722 | 📄 ../paper_cache/NeurIPS2026/2605.19722.txt
- measuring what matterssynthetic benchmarks for concept bottleneck models | arXiv: 2606.04326
- mechanism-aware ensemble conditioning for data-limited emulation of extreme even | arXiv: 2609.30746v1
- mechanistic circuit identification for controllable data generation | arXiv: 2608.24065 | 📄 ../paper_cache/NeurIPS2026/2608.24065.txt
- mechanistic insights into lora layer sparsity for adaptive fine-tuning via path | arXiv: 2610.34756 | 📄 ../paper_cache/NeurIPS2026/2610.34756.txt
- mechanistic interpretability with sparse autoencoder neural operators | arXiv: 2509.03738
- medevoeval evaluating continual evolution of doctor agents through simulated cli | arXiv: 2606.28900
- medhorizon towards long-context medical video understanding in the wild | arXiv: 2605.06537 | 📄 ../paper_cache/NeurIPS2026/2605.06537.txt
- medkit evaluating knowledge integration and generalization in large language mod | arXiv: 2609.38543v1
- medmemorybench benchmarking agent memory in personalized healthcare | arXiv: 2605.11814
- medzero self-evolving agents for open-ended medical reasoning through controlled | arXiv: 2610.08327 | 📄 ../paper_cache/NeurIPS2026/2610.08327.txt
- megastyle constructing diverse and scalable style dataset via consistent text-to | arXiv: 2604.08364 | 📄 ../paper_cache/NeurIPS2026/2604.08364.txt
- memarena an ego-centric benchmark for on-device agentic personal memory assistan | arXiv: 2608.02613 | 📄 ../paper_cache/NeurIPS2026/2608.02613.txt
- memleak diagnosing information leaks in multimodal agent memory | arXiv: 2606.29788 | 📄 ../paper_cache/NeurIPS2026/2606.29788.txt
- memory determines learning direction a theory of gradient-based optimization in | arXiv: 2510.00563 | 📄 ../paper_cache/NeurIPS2026/2510.00563.txt
- Mesh BDF: Barycentric Dominance Field for 3D Native Mesh Generation | arXiv: 2606.31777
- MeshFIM: Local Low-Poly Mesh Editing via Fill-in-the-Middle Autoregressive Generation | arXiv: 2605.08744
- mess multi-exposure sequence synthesis for generalizable image enhancement | arXiv: 2610.24680 | 📄 ../paper_cache/NeurIPS2026/2610.24680.txt
- messenger memory-enhanced sequential scene flow estimation via autoregressive ne | arXiv: 2610.10759 | 📄 ../paper_cache/NeurIPS2026/2610.10759.txt
- metacluster enabling deep compression of kolmogorov-arnold network | arXiv: 2510.19105
- metake meta-learning for knowledge editing toward a better accuracy-editability | arXiv: 2603.12677 | 📄 ../paper_cache/NeurIPS2026/2603.12677.txt
- metis multi-source egocentric training for integrated dexterous vision-language- | arXiv: 2511.17366
- Metric Depth Estimation from Arbitrarily Degraded Low-Resolution Depth Prompts | arXiv: 2602.09510
- metropolis-adjusted diffusion models | arXiv: 2605.09654 | 📄 ../paper_cache/NeurIPS2026/2605.09654.txt
- midpoint generative models | arXiv: 2605.29920 | 📄 ../paper_cache/NeurIPS2026/2605.29920.txt
- mildly overparameterized relu networks on orthogonal data incremental learning a | arXiv: 2605.27097 | 📄 ../paper_cache/NeurIPS2026/2605.27097.txt
- miles modular instruction memory with learnable selection for self-improving llm | arXiv: 2607.06974 | 📄 ../paper_cache/NeurIPS2026/2607.06974.txt
- mind monge inception distance for generative models evaluation | arXiv: 2605.06797 | 📄 ../paper_cache/NeurIPS2026/2605.06797.txt
- mineevolve self-evolution with accumulated knowledge for long-horizon embodied m | arXiv: 2603.13131 | 📄 ../paper_cache/NeurIPS2026/2603.13131.txt
- mini amusement parks maps a testbed for modelling business decisions | arXiv: 2511.15830
- mini-batch kernel k-means | arXiv: 2410.05902
- minimally invasive steering of language models | arXiv: 2609.30218 | 📄 ../paper_cache/NeurIPS2026/2609.30218.txt
- minimax optimal estimation of transport-growth pairs in unbalanced optimal trans | arXiv: 2605.08705 | 📄 ../paper_cache/NeurIPS2026/2605.08705.txt
- minimax rates and spectral distillation for tree ensembles | arXiv: 2605.11841 | 📄 ../paper_cache/NeurIPS2026/2605.11841.txt
- Minimizing Modality Gap from the Input Side: Your Speech LLM Can Be a Prosody-Aware Text LLM | arXiv: 2605.05927
- minmax recurrent neural cascades | arXiv: 2605.06384 | 📄 ../paper_cache/NeurIPS2026/2605.06384.txt
- miroeval benchmarking multimodal deep research agents in process and outcome | arXiv: 2603.28407 | 📄 ../paper_cache/NeurIPS2026/2603.28407.txt
- mirror descent actor-critic methods for entropy regularised mdps in general spac | arXiv: 2602.10838 | 📄 ../paper_cache/NeurIPS2026/2602.10838.txt
- mirror descent beyond euclidean stability an exponential separation in initializ | arXiv: 2606.11431 | 📄 ../paper_cache/NeurIPS2026/2606.11431.txt
- mirror descent-ascent for mean-field min-max problems | arXiv: 2402.08106
- mirror mirror on the wall can vlm agents tell who they are at all | arXiv: 2605.08816 | 📄 ../paper_cache/NeurIPS2026/2605.08816.txt
- misgeneralization of helpful-only fine-tuning | arXiv: 2606.04413 | 📄 ../paper_cache/NeurIPS2026/2606.04413.txt
- missing data and cluster graphs cluster-level missingness vs variable-level miss | arXiv: 2605.20943 | 📄 ../paper_cache/NeurIPS2026/2605.20943.txt
- missing old logits in asynchronous agentic rl semantic mismatch and repair metho | arXiv: 2605.12070 | 📄 ../paper_cache/NeurIPS2026/2605.12070.txt
- misspath-fm flow matching with structured priors for partially observed time ser | arXiv: 2610.17715 | 📄 ../paper_cache/NeurIPS2026/2610.17715.txt
- Mitigating Factual Hallucination in Large Reasoning Models via Mixed-Mode Advantage Regularization | arXiv: 2607.05861
- mitigating label bias with interpretable rubric embeddings | arXiv: 2605.21455 | 📄 ../paper_cache/NeurIPS2026/2605.21455.txt
- Mitigating Object Hallucination in Large Vision-Language Models via False Discovery Controlled Visual Data Splitting | arXiv: 2609.38979
- mitigating over-squashing without rewiring a sheaf effective resistance perspect | arXiv: 2610.04157 | 📄 ../paper_cache/NeurIPS2026/2610.04157.txt
- mitigating saliency collapse robust saliency-aware long-text image-text alignmen | arXiv: 2610.31005 | 📄 ../paper_cache/NeurIPS2026/2610.31005.txt
- mito a millimeter-wave dataset and simulator for non-line-of-sight perception | arXiv: 2502.10259
- mllmeraser achieving test-time unlearning in multimodal large language models th | arXiv: 2510.04217
- mllms fail to refuse when using tools agentically | arXiv: 2610.03938 | 📄 ../paper_cache/NeurIPS2026/2610.03938.txt
- mm-issueloc a controlled benchmark for evaluating visual evidence in multimodal | arXiv: 2607.15205 | 📄 ../paper_cache/NeurIPS2026/2607.15205.txt
- mmlongcite a benchmark for evaluating faithfulness of long-context vision-langua | arXiv: 2510.13276
- mmou a massive multi-task omni understanding and reasoning benchmark for long an | arXiv: 2603.14145 | 📄 ../paper_cache/NeurIPS2026/2603.14145.txt
- mmskills towards multimodal skills for general visual agents | arXiv: 2605.13527 | 📄 ../paper_cache/NeurIPS2026/2605.13527.txt
- mobayes a modular bayesian framework for separating reasoning from language in c | arXiv: 2604.20022
- mobilewan closing the quality gap for mobile video diffusion | arXiv: 2607.06173
- mobility helps learning unsupervised model adaptation for object recognition via | arXiv: 2610.15846 | 📄 ../paper_cache/NeurIPS2026/2610.15846.txt
- mobiquant mixture-of-bits quantization for token-adaptive any-precision llm | arXiv: 2602.20191 | 📄 ../paper_cache/NeurIPS2026/2602.20191.txt
- moca mixture-of-components attention for scalable compositional 3d generation | arXiv: 2512.07628
- mocar motion-code coordinate-aware autoregression for continuous trajectory fore | arXiv: 2610.06210 | 📄 ../paper_cache/NeurIPS2026/2610.06210.txt
- model guides you how to draw adaptive visual gating for unified multimodal reaso | arXiv: 2607.10004 | 📄 ../paper_cache/NeurIPS2026/2607.10004.txt
- model-aware tokenizer transfer | arXiv: 2510.21954
- modeling quantum neural network gradient with reinforcement learning | arXiv: 2609.31066v1
- modeling whole-slide images as dynamic tumor microenvironment fields | arXiv: 医学图像
- modellens finding the best for your task from myriads of models | arXiv: 2605.07075 | 📄 ../paper_cache/NeurIPS2026/2605.07075.txt
- models designed to forget machine unlearning via key deletion | arXiv: 2603.15033 | 📄 ../paper_cache/NeurIPS2026/2603.15033.txt
- molhit advancing molecular-graph generation with hierarchical discrete diffusion | arXiv: 2602.17602 | 📄 ../paper_cache/NeurIPS2026/2602.17602.txt
- momha multi-objective optimization of llm harnesses over accuracy safety and tok | arXiv: LLM Agent
- monitoring violations of differential privacy over time | arXiv: 2509.20283
- more is not more what matters for diversity in llm opinions | arXiv: 2607.20429 | 📄 ../paper_cache/NeurIPS2026/2607.20429.txt
- more than meets the eye uncovering the reasoning-planning disconnect in training | arXiv: 2510.04532
- more value per key asymmetric sparse attention for faster llm decoding | arXiv: 2610.04753 | 📄 ../paper_cache/NeurIPS2026/2610.04753.txt
- morphohelm a comprehensive benchmark for evaluating representations for microsco | arXiv: 2605.15383 | 📄 ../paper_cache/NeurIPS2026/2605.15383.txt
- MOSAIC-Bench: Measuring Compositional Vulnerability Induction in Coding Agents | arXiv: 2605.03952
- mosaicmri a diverse dataset and benchmark for raw musculoskeletal mri | arXiv: 2604.11762 | 📄 ../paper_cache/NeurIPS2026/2604.11762.txt
- Motion Cues from Image-based Point Tracking for LiDAR Scene Flow Estimation | arXiv: 2605.16922
- motion forcing a decoupled framework for robust video generation in motion dynam | arXiv: 2603.10408v2
- motiongrounder grounded multi-object motion transfer via diffusion transformer | arXiv: 2604.00853 | 📄 ../paper_cache/NeurIPS2026/2604.00853.txt
- MotionHalluc: Diagnosing Kinematic Hallucinations in Fine-Grained Motion Reasoning | arXiv: 2606.23061
- mulclip a multi-level alignment framework for enhancing fine-grained long-contex | arXiv: 2512.07128
- multabench benchmarking multimodal tabular learning with text and image | arXiv: 2605.10616
- multi-objective reinforcement learning using routed ensembles and trajectory att | arXiv: 2610.35733 | 📄 ../paper_cache/NeurIPS2026/2610.35733.txt
- multi-part object representations via graph structures and co-part discovery | arXiv: 2512.18192
- multi-site ppg an in-the-wild physiological dataset from emerging multi-site wea | arXiv: 2605.17859 | 📄 ../paper_cache/NeurIPS2026/2605.17859.txt
- multidimensional observer model and perceptual dimensions of human image quality | arXiv: 2609.38487
- multimodal llms outperform pathology foundation models in cross-domain histologi | arXiv: 2609.32876
- multiscale supervised unbalanced optimal transport flow matching | arXiv: 2605.16529 | 📄 ../paper_cache/NeurIPS2026/2605.16529.txt
- multistage defer trees for hybrid interpretability if at first you cant succeed | arXiv: 2606.30995 | 📄 ../paper_cache/NeurIPS2026/2606.30995.txt
- multivariate time series forecasting needs cross variable loss | arXiv: 2608.05742
- murphy feedback-aware grpo with retrospective credit assignment for multi-turn c | arXiv: 2511.07833
- mutable transcripts mitigating context pollution through editable conversation s | arXiv: 2609.31354
- mvffn multi-view floor-plan feed-forward network for unposed wide-baseline panor | arXiv: 2610.14315 | 📄 ../paper_cache/NeurIPS2026/2610.14315.txt
- myochallenge 2025 a new benchmark for human athletic intelligence | arXiv: 2605.15650 | 📄 ../paper_cache/NeurIPS2026/2605.15650.txt
- nads navigator-guided data selection for mitigating catastrophic forgetting in f | arXiv: 2610.25751
- namvis next-scale autoregressive multi-view image synthesis | arXiv: 2610.04722 | 📄 ../paper_cache/NeurIPS2026/2610.04722.txt
- narrowing the collaboration gap probably | arXiv: 2610.19215 | 📄 ../paper_cache/NeurIPS2026/2610.19215.txt
- Native Audio-Visual Alignment for Generation | arXiv: 2605.30073
- native multi-dimensional subquadratic operators via input dependent long convolu | arXiv: 2607.19378 | 📄 ../paper_cache/NeurIPS2026/2607.19378.txt
- natural language actor-critic scalable off-policy learning in language space | arXiv: 2512.04601
- natural synthesis outperforming reactive synthesis tools with large reasoning mo | arXiv: 2605.15131 | 📄 ../paper_cache/NeurIPS2026/2605.15131.txt
- navigating by old maps the pitfalls of static mechanistic localization in llm po | arXiv: 2605.06076 | 📄 ../paper_cache/NeurIPS2026/2605.06076.txt
- ndpp-grasp non-differentiable physical plausibility constraint-guided task-orien | arXiv: 2606.02432 | 📄 ../paper_cache/NeurIPS2026/2606.02432.txt
- nearly optimal robust covariance and scatter matrix estimation beyond gaussians | arXiv: 2502.06564
- neat neighborhood-guided efficient autoregressive set transformer for 3d molecul | arXiv: 2512.05844
- negation neglect when models fail to learn negations in training | arXiv: 2605.13829 | 📄 ../paper_cache/NeurIPS2026/2605.13829.txt
- nemotron-cascade scaling cascaded reinforcement learning for general-purpose rea | arXiv: 2512.13607
- neoworld-pro programming interactive scenes from monocular images for embodied s | arXiv: 2608.24212
- nestedvla learning to consolidate and generate skills for vision-language-action | arXiv: 2610.23271
- network intervention by polling strategic agents | arXiv: 2610.08347 | 📄 ../paper_cache/NeurIPS2026/2610.08347.txt
- network of theseus like the ship | arXiv: 2512.04198
- neural backward filtering forward guiding | arXiv: 2601.23030 | 📄 ../paper_cache/NeurIPS2026/2601.23030.txt
- neural bayesian filtering | arXiv: 2510.03614
- neural chameleons language models can learn to hide their thoughts from unseen a | arXiv: 2512.11949
- neural field thermal tomography a differentiable physics framework for non-destr | arXiv: 2603.11045 | 📄 ../paper_cache/NeurIPS2026/2603.11045.txt
- neural galerkin normalizing flows for bayesian inference of diffusions with inac | arXiv: 2606.04324 | 📄 ../paper_cache/NeurIPS2026/2606.04324.txt
- neural harmonic measure operator | arXiv: 2609.35752
- neural networks are more modular than single neurons suggest | arXiv: 2610.12842 | 📄 ../paper_cache/NeurIPS2026/2610.12842.txt
- neural neural scaling laws | arXiv: 2601.19831 | 📄 ../paper_cache/NeurIPS2026/2601.19831.txt
- neural statistical functions | arXiv: 2605.11327 | 📄 ../paper_cache/NeurIPS2026/2605.11327.txt
- neural structural reasoner a brain-inspired architecture for reasoning over stru | arXiv: 2609.36620
- neuralvisual decoding via cognitiveguided adaptive blurring and informationconst | arXiv: 2605.16418 | 📄 ../paper_cache/NeurIPS2026/2605.16418.txt
- neuroatlas benchmarking foundation models for clinical eeg and brain-computer in | arXiv: 2605.14698 | 📄 ../paper_cache/NeurIPS2026/2605.14698.txt
- neuron populations exhibit divergent selectivity with scale | arXiv: 2606.03990 | 📄 ../paper_cache/NeurIPS2026/2606.03990.txt
- neuronal identity as an organizational basis for analyzing neural population dyn | arXiv: 2610.36745 | 📄 ../paper_cache/NeurIPS2026/2610.36745.txt
- neurosymbolic object-centric learning with distant supervision | arXiv: 2506.16129
- next-latent prediction transformers learn compact world models | arXiv: 2511.05963
- nexus same pretraining loss better downstream generalization via common minima | arXiv: 2604.09258 | 📄 ../paper_cache/NeurIPS2026/2604.09258.txt
- niv neural axis variations for variable font generation | arXiv: 2606.05261 | 📄 ../paper_cache/NeurIPS2026/2606.05261.txt
- njord a probabilistic graph neural network for ensemble ocean forecasting | arXiv: 2605.15470 | 📄 ../paper_cache/NeurIPS2026/2605.15470.txt
- no pose no problem in 4d feed-forward dynamic gaussians from unposed multi-view | arXiv: 2605.22190
- nofe neural operator function embedding | arXiv: 2605.11970 | 📄 ../paper_cache/NeurIPS2026/2605.11970.txt
- noisy data is destructive to reinforcement learning with verifiable rewards | arXiv: 2603.16140 | 📄 ../paper_cache/NeurIPS2026/2603.16140.txt
- non-linear pricing restores tractability for a data seller | arXiv: 2609.36589
- nonconvex decentralized stochastic bilevel optimization under heavy-tailed noise | arXiv: 2509.15543
- nonparametric in-context learning under growing geometric complexity minimax opt | arXiv: 2609.31458
- norm anchors make model edits last | arXiv: 2602.02543 | 📄 ../paper_cache/NeurIPS2026/2602.02543.txt
- normative networks for source separation via local plasticity and dendritic comp | arXiv: 2605.19965 | 📄 ../paper_cache/NeurIPS2026/2605.19965.txt
- normlift from lifted features to semantic reliability in 3d gaussian splatting | arXiv: 2609.18898
- not all proofs are equal evaluating llm proof quality beyond correctness | arXiv: 2605.10379 | 📄 ../paper_cache/NeurIPS2026/2605.10379.txt
- not all tasks quantize equally fisher-guided quantization for visual geometry tr | arXiv: 2605.15828
- not too generative not too discriminative the human alignment sweet spot | arXiv: 2605.23819 | 📄 ../paper_cache/NeurIPS2026/2605.23819.txt
- notvla semantics-preserving robot adaptation via narrative action interfaces | arXiv: 2510.03895
- np-lora null space projection for subject-style lora fusion | arXiv: 2511.11051
- nrf-gs neural residual fields for expressive and compact gaussian splatting | arXiv: 2609.37115
- numuon nuclear-norm-constrained muon for compressible llm training | arXiv: 2603.03597 | 📄 ../paper_cache/NeurIPS2026/2603.03597.txt
- nuReasoning: A Reasoning-Centric Dataset and Benchmark for Long-Tail Autonomous Driving | arXiv: 2605.31572
- OASIS: Observation-Action Space Alignment via SE(3) Trajectory Prediction for Robotic Manipulation | arXiv: 2605.25829
- oats online data augmentation for time series foundation models | arXiv: 2601.19040 | 📄 ../paper_cache/NeurIPS2026/2601.19040.txt
- observable neural odes for identifiable causal forecasting in continuous time | arXiv: 2604.26070 | 📄 ../paper_cache/NeurIPS2026/2604.26070.txt
- odyssim building foundation models for human behavior simulation | arXiv: 2606.14199 | 📄 ../paper_cache/NeurIPS2026/2606.14199.txt
- offline constrained reinforcement learning under partial data coverage | arXiv: 2505.17506
- offline materials optimization with cliqueflowmer | arXiv: 2603.06082 | 📄 ../paper_cache/NeurIPS2026/2603.06082.txt
- Offloading Score: Measuring AI Reliance through Counterfactual Workflows | arXiv: 2605.29392
- OgBench: A Framework for Evaluating Graph Neural Networks on Omics Data | arXiv: 2605.15511
- olio ode-based linear transition operator for self-supervised time series foreca | arXiv: 2610.23345 | 📄 ../paper_cache/NeurIPS2026/2610.23345.txt
- OmniCapBench: A Deep-Structured Evaluation Framework for Fine-Grained Audio-Visual Captioning | arXiv: 2610.12458
- omnidex scaling dexterous hand grasping to diverse cluttered scenes | arXiv: 2610.11194 | 📄 ../paper_cache/NeurIPS2026/2610.11194.txt
- omnimem scalable and adaptive memory retrieval for long video generation | arXiv: 2605.30519 | 📄 ../paper_cache/NeurIPS2026/2605.30519.txt
- omnisimulator aligning small language models for authentic heterogeneous behavio | arXiv: 2610.29472
- omnispace efficient geometry awareness for autonomous vehicles mllms | arXiv: 2606.22617 | 📄 ../paper_cache/NeurIPS2026/2606.22617.txt
- omnitom benchmarking theory of mind in llms via explicit belief modeling | arXiv: 2605.26322 | 📄 ../paper_cache/NeurIPS2026/2605.26322.txt
- OmniTraffic: A Controllable Generation Pipeline and Benchmark for Spatio-Temporal Traffic Reasoning | arXiv: 2606.15749
- on data engineering for scaling llm terminal capabilities | arXiv: 2602.21193 | 📄 ../paper_cache/NeurIPS2026/2602.21193.txt
- on neural scaling laws for weather emulation through continual training | arXiv: 2603.25687 | 📄 ../paper_cache/NeurIPS2026/2603.25687.txt
- on observation time for recovering latent hawkes networks | arXiv: 2605.08400 | 📄 ../paper_cache/NeurIPS2026/2605.08400.txt
- on the burden of achieving fairness in conformal prediction | arXiv: 2605.14260 | 📄 ../paper_cache/NeurIPS2026/2605.14260.txt
- on the complexity of discounted robust mdps with l p uncertainty sets | arXiv: 2605.07459 | 📄 ../paper_cache/NeurIPS2026/2605.07459.txt
- on the depth of monotone relu neural networks and icnns | arXiv: 2505.06169
- on the error correcting effects of stochasticity in discrete diffusion | arXiv: 2605.26582 | 📄 ../paper_cache/NeurIPS2026/2605.26582.txt
- on the faithfulness of visual thinking measurement and enhancement | arXiv: 2510.23482
- on the invariance and generality of neural scaling laws | arXiv: 2605.07546 | 📄 ../paper_cache/NeurIPS2026/2605.07546.txt
- on the last-iterate convergence ofclipped gradient methods | arXiv: 2610.21026
- on the limits of latent reuse in diffusion models | arXiv: 2605.13448 | 📄 ../paper_cache/NeurIPS2026/2605.13448.txt
- on the overscaling curse of parallel thinking system efficacy contradicts sample | arXiv: 2601.21619 | 📄 ../paper_cache/NeurIPS2026/2601.21619.txt
- on the price of privacy for language identification and generation | arXiv: 2604.07238 | 📄 ../paper_cache/NeurIPS2026/2604.07238.txt
- on the recall scaling laws in mamba a theoretical and mechanistic study via hash | arXiv: 2609.07681 | 📄 ../paper_cache/NeurIPS2026/2609.07681.txt
- on the recoverability of causal relations from bulk gene expression data | arXiv: 2606.00568 | 📄 ../paper_cache/NeurIPS2026/2606.00568.txt
- on the robustness of watermarking for autoregressive image generation | arXiv: 2604.11720 | 📄 ../paper_cache/NeurIPS2026/2604.11720.txt
- On the Selectivity of Generative Models in Structure-Based Drug Design | arXiv: 2610.24124
- on the sparsity-storage-accuracy tradeoff in parsimoniously activated dictionary | arXiv: 2606.22352 | 📄 ../paper_cache/NeurIPS2026/2606.22352.txt
- on the tightness and computational tractability of higher-dimensional confidence | arXiv: 2610.03727 | 📄 ../paper_cache/NeurIPS2026/2610.03727.txt
- on time within budget constraint-driven online resource allocation for agentic w | arXiv: 2605.06110 | 📄 ../paper_cache/NeurIPS2026/2605.06110.txt
- on-policy consistency training improves llm safety with minimal capability degra | arXiv: 2605.21834 | 📄 ../paper_cache/NeurIPS2026/2605.21834.txt
- one algorithm two goals dual scoring for parameter and data selection in llm fin | arXiv: 2605.06166
- one language-free foundation model is enough for universal vision anomaly detect | arXiv: 2601.05552 | 📄 ../paper_cache/NeurIPS2026/2601.05552.txt
- one loss to rule them all marked time-to-event for structured ehr foundation mod | arXiv: 2602.00541 | 📄 ../paper_cache/NeurIPS2026/2602.00541.txt
- one model two roles emergent specialization in a shared recurrent transformer | arXiv: 2605.17811 | 📄 ../paper_cache/NeurIPS2026/2605.17811.txt
- one more time revisiting neural quantum states from a reinforcement learning per | arXiv: 2607.02292 | 📄 ../paper_cache/NeurIPS2026/2607.02292.txt
- one step is enough multi-agent reinforcement learning based on one-step policy o | arXiv: 2507.15351
- one threshold does not fit all languages language-conditional deferral for relia | arXiv: 2609.37861
- one view is enough in-the-wild monocular pretraining for novel view generation | arXiv: 2603.23488
- one world dual timeline decoupled spatio-temporal gaussian scene graph for 4d co | arXiv: 2605.07910 | 📄 ../paper_cache/NeurIPS2026/2605.07910.txt
- one-layer transformers provably learn in-context k-nearest neighbor prediction w | arXiv: 2610.16798 | 📄 ../paper_cache/NeurIPS2026/2610.16798.txt
- one-shot compositional human-environment video synthesis via spatial-decoupled m | arXiv: 2604.01043 | 📄 ../paper_cache/NeurIPS2026/2604.01043.txt
- one-shot private confidence regions via resampling | arXiv: 2610.08460 | 📄 ../paper_cache/NeurIPS2026/2610.08460.txt
- onecanvas 3d scene understanding via panoramic reprojection | arXiv: 2606.19253
- onevision-encoder codec-aligned sparsity as a foundational principle for multimo | arXiv: 2602.08683 | 📄 ../paper_cache/NeurIPS2026/2602.08683.txt
- online allocation with unknown shared supply | arXiv: 2605.07080 | 📄 ../paper_cache/NeurIPS2026/2605.07080.txt
- online bayesian calibration under gradual and abrupt system changes | arXiv: 2605.06612 | 📄 ../paper_cache/NeurIPS2026/2605.06612.txt
- online budget allocation with censored semi-bandit feedback | arXiv: 2508.05844
- online data selection for instruction tuning via gaussian processes | arXiv: 2606.30077 | 📄 ../paper_cache/NeurIPS2026/2606.30077.txt
- online learning on hidden-convex losses via algorithmic equivalence optimal regr | arXiv: 2605.26373 | 📄 ../paper_cache/NeurIPS2026/2605.26373.txt
- online learning via learned latent bayesian tracking | arXiv: 2609.31559
- online localized conformal prediction | arXiv: 2605.05497 | 📄 ../paper_cache/NeurIPS2026/2605.05497.txt
- ontoplan an ontology-grounded scene representation and agentic framework for sca | arXiv: 2610.07649 | 📄 ../paper_cache/NeurIPS2026/2610.07649.txt
- open vocabulary domain unlearning | arXiv: 2609.31356
- opencof learning to reason through video generation | arXiv: 2607.08763 | 📄 ../paper_cache/NeurIPS2026/2607.08763.txt
- openmhc accelerating the science of wearable foundation models | arXiv: 2607.16235 | 📄 ../paper_cache/NeurIPS2026/2607.16235.txt
- opensearch-vl an open recipe for frontier multimodal search agents | arXiv: 2605.05185 | 📄 ../paper_cache/NeurIPS2026/2605.05185.txt
- openview empowering mllms with out-of-view vqa | arXiv: 2512.18563
- openvton-bench a large-scale high-resolution benchmark for controllable virtual | arXiv: 2601.22725 | 📄 ../paper_cache/NeurIPS2026/2601.22725.txt
- openwebrl demystifying online multi-turn reinforcement learning for visual web a | arXiv: 2606.02031 | 📄 ../paper_cache/NeurIPS2026/2606.02031.txt
- openwhistle a large-scale longitudinal dataset and benchmark of bottlenose dolph | arXiv: 2609.34839
- opera an agent for image restoration with end-to-end joint planningexecution opt | arXiv: 2605.22104 | 📄 ../paper_cache/NeurIPS2026/2605.22104.txt
- optimal algorithmic complexity of inference in quantum kernel methods | arXiv: 2604.15214 | 📄 ../paper_cache/NeurIPS2026/2604.15214.txt
- optimal and efficient contextual combinatorial semi-bandits with general functio | arXiv: 2607.13686 | 📄 ../paper_cache/NeurIPS2026/2607.13686.txt
- optimal ansatz-free hamiltonian learning in situ | arXiv: 2606.19486 | 📄 ../paper_cache/NeurIPS2026/2606.19486.txt
- optimal convergence analysis of ddpm for general distributions | arXiv: 2510.27562
- optimal hidden-target learning for online inventory optimization on general conv | arXiv: 2606.14679 | 📄 ../paper_cache/NeurIPS2026/2606.14679.txt
- optimal in-context adaptivity and distributional robustness of transformers | arXiv: 2510.23254
- optimal rates for pure varepsilon-differentially private stochastic convex optim | arXiv: 2604.06492 | 📄 ../paper_cache/NeurIPS2026/2604.06492.txt
- optimal scaling laws in learning hierarchical multi-index models | arXiv: 2602.05846 | 📄 ../paper_cache/NeurIPS2026/2602.05846.txt
- optimal sequential tests yield log-optimal e-processes | arXiv: 2605.12720 | 📄 ../paper_cache/NeurIPS2026/2605.12720.txt
- optimal transport reweighting for robust learning under spurious correlations an | arXiv: 2610.01028 | 📄 ../paper_cache/NeurIPS2026/2610.01028.txt
- optimize once execute fast latency-aware multi-agent workflow learning for recur | arXiv: 2610.14481 | 📄 ../paper_cache/NeurIPS2026/2610.14481.txt
- orca hunting compositional failures in text-to-image diffusion | arXiv: 2610.09841 | 📄 ../paper_cache/NeurIPS2026/2610.09841.txt
- ordinary least squares as an attention mechanism | arXiv: 2504.09663
- orliczsobolev with musielak an efficient regularization approach for graph-based | arXiv: 2510.25591 | 📄 ../paper_cache/NeurIPS2026/2510.25591.txt
- orthogonal uplift learning with permutation-invariant representations for combin | arXiv: 2602.19851 | 📄 ../paper_cache/NeurIPS2026/2602.19851.txt
- orthoreg orthogonal regularization for hybrid symbolic-neural dynamical systems | arXiv: 2606.19145 | 📄 ../paper_cache/NeurIPS2026/2606.19145.txt
- otrope optimal transport-based robust off-policy evaluation for large language m | arXiv: 2609.36264
- otter weather skillful and computationally-efficient medium-range weather foreca | arXiv: 2606.26421 | 📄 ../paper_cache/NeurIPS2026/2606.26421.txt
- out-of-distribution detection in continual learning | arXiv: 2610.25901 | 📄 ../paper_cache/NeurIPS2026/2610.25901.txt
- outbidding and outbluffing elite humans mastering liars poker via self-play and | arXiv: 2511.03724
- outcome-based rl provably leads transformers to reason but only with the right d | arXiv: 2601.15158 | 📄 ../paper_cache/NeurIPS2026/2601.15158.txt
- Overcoming State Inertia in Full-Duplex Spoken Language Models via Activation Steering | arXiv: 2606.11386
- overlay dense-overlap layout-to-image generation dataset | arXiv: 2610.09071 | 📄 ../paper_cache/NeurIPS2026/2610.09071.txt
- P\(^{3}\): Joint Program-and-Proof Planning for Verified Code Generation | arXiv: 2608.09277
- p3-vlm a point-based alternative for grounded 3d vision-language models | arXiv: 2610.28018
- pac learning with bandit feedback sharp sample complexity in the realizable sett | arXiv: 2605.25678 | 📄 ../paper_cache/NeurIPS2026/2605.25678.txt
- pac-bayesian bounds for learning partially observed stochastic linear time-invar | arXiv: 2609.08740 | 📄 ../paper_cache/NeurIPS2026/2609.08740.txt
- pace a proxy for agentic capability evaluation | arXiv: 2607.02032 | 📄 ../paper_cache/NeurIPS2026/2607.02032.txt
- pace phase-aware chunk execution for robot policies with action chunking | arXiv: 2606.00537 | 📄 ../paper_cache/NeurIPS2026/2606.00537.txt
- PACE: Geometry-Aware Bridge Transport for Single-Cell Trajectory Inference | arXiv: 2605.18587
- pair prefix-aware internal reward model for multi-turn agent optimization | arXiv: 2605.17877 | 📄 ../paper_cache/NeurIPS2026/2605.17877.txt
- PAIR-CI: Calibrated Conditional Independence Testing for Causal Discovery with Incomplete Data | arXiv: 2605.04838
- paleoinspired vision from exploring colour vision evolution to inspiring camera | arXiv: 2412.19439
- palora paced low-rank adaptation for continual learning | arXiv: 2610.04226 | 📄 ../paper_cache/NeurIPS2026/2610.04226.txt
- pamod modeling cyclical shifts via phase-amplitude modulation for non-stationary | arXiv: 2605.00466 | 📄 ../paper_cache/NeurIPS2026/2605.00466.txt
- pan-fm a pan-organ foundation model with saliency-guided masking for missing rob | arXiv: 2605.07055 | 📄 ../paper_cache/NeurIPS2026/2605.07055.txt
- panoptic scene program diffusion transformer | arXiv: 2609.31780
- panoworld geometry-consistent panoramic video world modeling | arXiv: 2605.15391 | 📄 ../paper_cache/NeurIPS2026/2605.15391.txt
- parabolic position encoding vision-centric principled extrapolatable general | arXiv: 2602.01418 | 📄 ../paper_cache/NeurIPS2026/2602.01418.txt
- paradoxes of game theoretic equilibria and price of anarchy | arXiv: 2607.11752 | 📄 ../paper_cache/NeurIPS2026/2607.11752.txt
- paralin accelerating parallel diffusion integrator via intrinsic partially linea | arXiv: 2610.30704 | 📄 ../paper_cache/NeurIPS2026/2610.30704.txt
- parallel rollout approximation for pixel-space autoregressive image generation | arXiv: 2606.27978 | 📄 ../paper_cache/NeurIPS2026/2606.27978.txt
- parallel-in-time training of recurrent neural networks for dynamical systems rec | arXiv: 2605.12683 | 📄 ../paper_cache/NeurIPS2026/2605.12683.txt
- parameter symmetries determine representational geometry in overparameterized no | arXiv: 2609.39078
- parameterized complexity of stationarity testing for piecewise-affine functions | arXiv: 2605.10219 | 📄 ../paper_cache/NeurIPS2026/2605.10219.txt
- parameterized stripe attention for efficient video generation | arXiv: 2609.37001
- paretoslider diffusion models post-training for continuous reward control | arXiv: 2604.20816 | 📄 ../paper_cache/NeurIPS2026/2604.20816.txt
- partition tree conditional density estimation over general outcome spaces | arXiv: 2602.04042 | 📄 ../paper_cache/NeurIPS2026/2602.04042.txt
- partition-aware unlearning for removing spurious correlations in large vision-la | arXiv: 2608.29996 | 📄 ../paper_cache/NeurIPS2026/2608.29996.txt
- passing an endless journey through reconstructed spacetime with ai-generated sou | arXiv: 2609.27489
- past as state present as attention persistent-state blockwise flow matching for | arXiv: 2610.32373 | 📄 ../paper_cache/NeurIPS2026/2610.32373.txt
- patch learnable tile-level hybrid sparsity for llms | arXiv: 2509.23410
- patch rebirth fast and transferable model inversion of vision transformers | arXiv: 2509.23235
- patchbench measuring collateral damage in activation patching | arXiv: 2610.10276 | 📄 ../paper_cache/NeurIPS2026/2610.10276.txt
- path dependence under adaptive ai delegation | arXiv: 2603.02950 | 📄 ../paper_cache/NeurIPS2026/2603.02950.txt
- path-independent flow matching for multi-parameter generative dynamics | arXiv: 2605.13487 | 📄 ../paper_cache/NeurIPS2026/2605.13487.txt
- pathview-bench can multimodal large language models achieve fine-grained multisc | arXiv: 2607.28318 | 📄 ../paper_cache/NeurIPS2026/2607.28318.txt
- pathways of visual information flow in vision-language models | arXiv: 2607.03358
- pcbschemagen reward-guided llm code synthesis for printed circuit boards pcb sch | arXiv: 2602.00510 | 📄 ../paper_cache/NeurIPS2026/2602.00510.txt
- pcdfusion proposal-context-detail bayesian rendering for infrared-visible image | arXiv: 2610.23663 | 📄 ../paper_cache/NeurIPS2026/2610.23663.txt
- pceval a benchmark for evaluating physical computing capabilities of large langu | arXiv: 2601.02404 | 📄 ../paper_cache/NeurIPS2026/2601.02404.txt
- pde-pfn prior-data fitted neural pde solver | arXiv: 2610.13334 | 📄 ../paper_cache/NeurIPS2026/2610.13334.txt
- pde-ssm a spectral state space approach to spatial mixing in diffusion transform | arXiv: 2603.13663 | 📄 ../paper_cache/NeurIPS2026/2603.13663.txt
- pdf-hr pose distance fields for humanoid robots | arXiv: 2602.04851 | 📄 ../paper_cache/NeurIPS2026/2602.04851.txt
- penalty-based first-order methods for bilevel optimization with minimax and cons | arXiv: 2605.08006 | 📄 ../paper_cache/NeurIPS2026/2605.08006.txt
- penex adaboost-inspired neural network regularization | arXiv: 2510.02107 | 📄 ../paper_cache/NeurIPS2026/2510.02107.txt
- penex 基于 adaboost 思想的神经网络正则化 penex adaboost-inspired neural network regularizati | arXiv: 2510.02107
- PepSpecBench: A Unified Evaluation Benchmark for Peptide Tandem Mass Spectrometry Prediction | arXiv: 2605.01945
- per-loss adapters for gradient conflict in physics-informed neural networks | arXiv: 2605.10136 | 📄 ../paper_cache/NeurIPS2026/2605.10136.txt
- perceive interact reason building tool-augmented visual agents for spatial reaso | arXiv: 2606.12830
- Perceive-then-Plan: Layout-as-Policy for Monocular 3D Scene Layout Estimation | arXiv: 2605.25326
- perfect parallelization in mini-batch sgd with classical momentum acceleration | arXiv: 2605.18609 | 📄 ../paper_cache/NeurIPS2026/2605.18609.txt
- performance-driven policy optimization for speculative decoding with adaptive wi | arXiv: 2605.14978
- permavid consistent video generation across edits via disentangled context memor | arXiv: 2606.16449 | 📄 ../paper_cache/NeurIPS2026/2606.16449.txt
- permit permission-aware representation intervention for controlled generation in | arXiv: 2605.09480 | 📄 ../paper_cache/NeurIPS2026/2605.09480.txt
- permuquant lowering per-group quantization error by reordering channels for diff | arXiv: 2605.09503 | 📄 ../paper_cache/NeurIPS2026/2605.09503.txt
- permutation-invariant spectral learning via dyson diffusion | arXiv: 2510.08535
- perq inverse generative modeling for neural image compression via quantization e | arXiv: 2610.27374 | 📄 ../paper_cache/NeurIPS2026/2610.27374.txt
- persistent planar memory for video world models | arXiv: 2610.23795 | 📄 ../paper_cache/NeurIPS2026/2610.23795.txt
- persistent-transient policy evaluation for markov chains via minimal peripheral | arXiv: 2602.00474 | 📄 ../paper_cache/NeurIPS2026/2602.00474.txt
- persona vectors monitoring and controlling character traits in language models | arXiv: 2507.21509
- personalize-then-store benchmarking and learning personalized memory for long-ho | arXiv: 2605.25535 | 📄 ../paper_cache/NeurIPS2026/2605.25535.txt
- personamanifold revealing and exploiting curved geometry in llm persona represen | arXiv: 2609.34571
- perturb and correct post-hoc ensembles using affine redundancy | arXiv: 2605.01632 | 📄 ../paper_cache/NeurIPS2026/2605.01632.txt
- pessimistic latent task-aware optimization for robust offline meta-reinforcement | arXiv: 2610.15428 | 📄 ../paper_cache/NeurIPS2026/2610.15428.txt
- pg-lrf physiology-guided latent rectified flow for electro-hemodynamic ppg-to-ec | arXiv: 2605.12541 | 📄 ../paper_cache/NeurIPS2026/2605.12541.txt
- phaedra learning high-fidelity discrete tokenization for the physical science | arXiv: 物理/科学计算
- phmforge evaluating llm agents on industrial prognostics through mcp-native algo | arXiv: 2604.01532 | 📄 ../paper_cache/NeurIPS2026/2604.01532.txt
- phoebi an open-world benchmark for bacterial identification in phase-contrast mi | arXiv: 2606.22890
- photoflow agentic 3d virtual photography missions | arXiv: 2605.23771 | 📄 ../paper_cache/NeurIPS2026/2605.23771.txt
- phymo learning physical dynamics with accurate and continuous motion from multi- | arXiv: 2610.29107
- phyprobe rethinking physical consistency evaluation in generated videos | arXiv: 2609.38377
- physguard fisher-guided gradient projection for sim-to-real neural pde surrogate | arXiv: 2606.16602 | 📄 ../paper_cache/NeurIPS2026/2606.16602.txt
- Physical AI Smart Spaces: A Large-Scale Benchmark for Multi-Camera 3D Perception in Smart Spaces | arXiv: 2610.02580
- physics-informed video generation via mixture-of-experts latent alignment | arXiv: 2606.04737 | 📄 ../paper_cache/NeurIPS2026/2606.04737.txt
- pica pivot-based credit assignment for search agentic reinforcement learning | arXiv: 2605.09287 | 📄 ../paper_cache/NeurIPS2026/2605.09287.txt
- pickmoment continuous-time single-image-to-video via learning deblurring and blu | arXiv: 2610.01279 | 📄 ../paper_cache/NeurIPS2026/2610.01279.txt
- piearena ranking and profiling language agents in realistic negotiation scenario | arXiv: 2602.05302 | 📄 ../paper_cache/NeurIPS2026/2602.05302.txt
- pinpoint grounded worldwide image geolocation via cross-source retrieval and rer | arXiv: 2606.04133 | 📄 ../paper_cache/NeurIPS2026/2606.04133.txt
- pisa piecewise sparse attention is wiser for efficient diffusion transformers | arXiv: 2602.01077
- pisco precise video instance insertion with sparse control | arXiv: 2602.08277
- PitchBench: Measuring Pitch Hearing in Audio-Language Models | arXiv: 2605.26176
- pithtrain a compact and agent-native moe training system | arXiv: 2605.31463 | 📄 ../paper_cache/NeurIPS2026/2605.31463.txt
- pixelart image-to-layer decomposition without latents or text-to-image pretraini | arXiv: 2609.22789 | 📄 ../paper_cache/NeurIPS2026/2609.22789.txt
- pixeldit2 representation-grounded pixel diffusion transformers | arXiv: 2609.24919
- pixels to tokens token space efficient active learning for low-budget semantic s | arXiv: 2610.20881 | 📄 ../paper_cache/NeurIPS2026/2610.20881.txt
- PLANING: A Loosely Coupled Triangle-Gaussian Framework for Streaming 3D Reconstruction | arXiv: 2601.22046
- planning as dynamics relaxation hippocampal recurrent network realizes optimal g | arXiv: 2609.13219 | 📄 ../paper_cache/NeurIPS2026/2609.13219.txt
- platonic representations in the human brain unsupervised recovery of universal g | arXiv: 2605.20496 | 📄 ../paper_cache/NeurIPS2026/2605.20496.txt
- platonic task arithmetic | arXiv: 2610.00929 | 📄 ../paper_cache/NeurIPS2026/2610.00929.txt
- plausibility is not prediction contrastive evidence for llm-based cellular pertu | arXiv: 2606.01042 | 📄 ../paper_cache/NeurIPS2026/2606.01042.txt
- playing markov games without observing payoffs | arXiv: 2509.00179
- playing zendoworld challenging ai agents on active visual concept induction | arXiv: 2607.08233 | 📄 ../paper_cache/NeurIPS2026/2607.08233.txt
- pmo-dock benchmarking docking specificity and generalization in molecular optimi | arXiv: 2610.19011 | 📄 ../paper_cache/NeurIPS2026/2610.19011.txt
- po-pddl learning symbolic pomdps from visual demonstrations for robot planning u | arXiv: 2606.15654 | 📄 ../paper_cache/NeurIPS2026/2606.15654.txt
- pocketve stable and property-guided structure-based drug design with variance-ex | arXiv: 计算生物
- point cloud sequence encoding for material-conditioned graph network simulators | arXiv: 2605.20978
- pointforward feedforward driving reconstruction through point-aligned representa | arXiv: 2605.11594 | 📄 ../paper_cache/NeurIPS2026/2605.11594.txt
- pointwise lipschitz continuous graph algorithms | arXiv: 2405.08938
- poisoning attacks on llms require a near-constant number of poison samples | arXiv: 2510.07192
- polar-bench a diagnostic benchmark for privacy-utility trade-offs in llm agents | arXiv: 2605.19127 | 📄 ../paper_cache/NeurIPS2026/2605.19127.txt
- polarscale a physics-grounded benchmark for radiometrically consistent rgb-to-st | arXiv: 2610.08346 | 📄 ../paper_cache/NeurIPS2026/2610.08346.txt
- polestar drift-aware cache calibration and token commitment for efficient infere | arXiv: 2607.14107 | 📄 ../paper_cache/NeurIPS2026/2607.14107.txt
- policy gradient algorithms in average-reward multichain mdps | arXiv: 2602.18003 | 📄 ../paper_cache/NeurIPS2026/2602.18003.txt
- policy optimization in hybrid discrete-continuous action spaces via mixed gradie | arXiv: 2605.14297 | 📄 ../paper_cache/NeurIPS2026/2605.14297.txt
- political neutrality as balanced approval a large-scale human evaluation of ai r | arXiv: 2605.28911 | 📄 ../paper_cache/NeurIPS2026/2605.28911.txt
- polynomial-time algorithm for thiele voting rules with voter interval preference | arXiv: 2604.05953 | 📄 ../paper_cache/NeurIPS2026/2604.05953.txt
- polytopobench a benchmark for complex vector polygon generation from remote sens | arXiv: 2609.32856
- pop online structural pruning enables efficient inference of large foundation mo | arXiv: 2602.06822 | 📄 ../paper_cache/NeurIPS2026/2602.06822.txt
- portool importance-aware policy optimization with rewarded tree for multi-tool-i | arXiv: 2510.26020
- pose-free feed-forward 3d inpainting via learnable mask attention and support to | arXiv: 2610.11857 | 📄 ../paper_cache/NeurIPS2026/2610.11857.txt
- pose6daug physically plausible multi-view object swapping for robot data augment | arXiv: 2606.20118 | 📄 ../paper_cache/NeurIPS2026/2606.20118.txt
- posebridge bridging the skeletonization gap for zero-shot skeleton-based action | arXiv: 人体理解
- poseplaner denoising any feedforward pose predictor from pairwise planar geometr | arXiv: 2610.34845 | 📄 ../paper_cache/NeurIPS2026/2610.34845.txt
- position adopt constraints over fixed penalties in deep learning | arXiv: 2505.20628
- position lets strengthen verifiability if we cant enforce reproducibility | arXiv: 2609.35854
- position watermarking without standards is not ai governance | arXiv: 2505.23814
- positional lsh binary block matrix approximation for attention with linear biase | arXiv: 2605.09472 | 📄 ../paper_cache/NeurIPS2026/2605.09472.txt
- positional versus symbolic attention heads learning dynamics rope geometry and l | arXiv: 2605.31558 | 📄 ../paper_cache/NeurIPS2026/2605.31558.txt
- positive-unlabeled preference optimization for chest x-ray report generation | arXiv: 2608.05341 | 📄 ../paper_cache/NeurIPS2026/2608.05341.txt
- post-selection distributional model evaluation | arXiv: 2603.23055 | 📄 ../paper_cache/NeurIPS2026/2603.23055.txt
- posterior inference in latent space for scalable constrained black-box optimizat | arXiv: 2507.00480
- posterior-first neural pde simulation inferring hidden problem state from a sing | arXiv: 2605.03247 | 📄 ../paper_cache/NeurIPS2026/2605.03247.txt
- posteriorbench from point estimates to posterior matching in evaluating generati | arXiv: 2609.20794 | 📄 ../paper_cache/NeurIPS2026/2609.20794.txt
- potarcin multi-dimensional evaluation of skill acquisition in abstract reasoning | arXiv: 2609.27288 | 📄 ../paper_cache/NeurIPS2026/2609.27288.txt
- ppo in the fisher-rao geometry | arXiv: 2506.03757
- pr-smoother simulator-preserving non-gaussian smoothing for data assimilation | arXiv: 2609.26890
- practical adversarial attacks on stochastic bandits via fake data injection | arXiv: 2505.21938
- precise sde-consistent stochastic sampling for rl post-training of flow-matching | arXiv: 2605.23522 | 📄 ../paper_cache/NeurIPS2026/2605.23522.txt
- precision as you need stochastic computing is a dense adaptive quantizer | arXiv: 2609.32922 | 📄 ../paper_cache/NeurIPS2026/2609.32922.txt
- precomem predictive cognitive memory for self-evolving long-term dialogue agents | arXiv: 2610.29467
- preconditioned flow matching | arXiv: 2603.02337 | 📄 ../paper_cache/NeurIPS2026/2603.02337.txt
- predict-project-renoise sampling diffusion models under hard constraints | arXiv: 2601.21033 | 📄 ../paper_cache/NeurIPS2026/2601.21033.txt
- predicting quantization price for selecting ptq configurations before deployment | arXiv: 2609.28270 | 📄 ../paper_cache/NeurIPS2026/2609.28270.txt
- prediction under imperfect compression a theory of approximate mdl | arXiv: 2606.04834 | 📄 ../paper_cache/NeurIPS2026/2606.04834.txt
- prediction-powered active testing | arXiv: 2607.08347 | 📄 ../paper_cache/NeurIPS2026/2607.08347.txt
- predictive geometry of hidden trajectories in transformers | arXiv: 2609.37717 | 📄 ../paper_cache/NeurIPS2026/2609.37717.txt
- Predictive–Generative Drift Decomposition for Speech Enhancement and Separation | arXiv: 2605.06189
- preference conditioned multi-objective reinforcement learning decomposed diversi | arXiv: 2602.07764 | 📄 ../paper_cache/NeurIPS2026/2602.07764.txt
- preference-guided adaptation for open-vocabulary semantic segmentation via promp | arXiv: 2609.34528
- prefix-tuning for arbitrary output sequences on pretrained transformers | arXiv: 2610.24123 | 📄 ../paper_cache/NeurIPS2026/2610.24123.txt
- preserving deg rankings for gene discovery in histology-based spatial gene expre | arXiv: 2609.33928
- pretraining curricula enable selective fine-tuning | arXiv: 2607.04846
- prim meta-learned bayesian root cause analysis | arXiv: 2605.08786 | 📄 ../paper_cache/NeurIPS2026/2605.08786.txt
- primal-dual flow matching for sample-wise constrained generation | arXiv: 2610.12699 | 📄 ../paper_cache/NeurIPS2026/2610.12699.txt
- primal-dual guided decoding for constrained discrete diffusion | arXiv: 2605.09749 | 📄 ../paper_cache/NeurIPS2026/2605.09749.txt
- primal-dual representation learning for low-rank constrained mdps | arXiv: 2610.30756
- principia relational physics tests for video models | arXiv: 2609.04200 | 📄 ../paper_cache/NeurIPS2026/2609.04200.txt
- priorvla prior-preserving adaptation for vision-language-action models | arXiv: 2605.10925 | 📄 ../paper_cache/NeurIPS2026/2605.10925.txt
- prism a benchmark for programmatic spatial-temporal reasoning | arXiv: 2605.19382 | 📄 ../paper_cache/NeurIPS2026/2605.19382.txt
- prism attention proposal-refined index sharing mechanism for efficient llms infe | arXiv: 2610.22985 | 📄 ../paper_cache/NeurIPS2026/2610.22985.txt
- prism prior rectification and uncertainty-aware structure modeling for diffusion | arXiv: 2605.13027 | 📄 ../paper_cache/NeurIPS2026/2605.13027.txt
- prism prior relational information for self-supervised modeling to enhance solub | arXiv: 2610.25605 | 📄 ../paper_cache/NeurIPS2026/2610.25605.txt
- PRISM: Rethinking Atmospheric Scattering Reconstruction as a Unified Understanding and Restoration Model for Real-world Dehazing | arXiv: 2604.07048
- privacysim evaluating llm simulation of user privacy behavior | arXiv: 2605.12147 | 📄 ../paper_cache/NeurIPS2026/2605.12147.txt
- private online prediction from experts with small losses | arXiv: 2610.29575 | 📄 ../paper_cache/NeurIPS2026/2610.29575.txt
- privately estimating monotone statistics in polynomial time | arXiv: 2605.27912 | 📄 ../paper_cache/NeurIPS2026/2605.27912.txt
- pro enabling precise and robust text watermark for open-source llms | arXiv: 2510.23891
- probing persona-dependent preferencesin language models | arXiv: 2605.13339
- probing visual planning in image editing models | arXiv: 2604.22868 | 📄 ../paper_cache/NeurIPS2026/2604.22868.txt
- procare real-world study automation via profile-grounded evidence contracts | arXiv: 2610.16175 | 📄 ../paper_cache/NeurIPS2026/2610.16175.txt
- procedural memory distillation online reflection for self-improving language mod | arXiv: 2607.01480 | 📄 ../paper_cache/NeurIPS2026/2607.01480.txt
- proclip progressive vision-language alignment via llm-based embedder | arXiv: 2510.18795
- procobject-10k benchmarking object-centric procedural understanding in instructi | arXiv: 2512.03479
- procompnav proactive instance navigation with comparative judgment for ambiguous | arXiv: 2605.06223
- profit maximization in bilateral trade against a smooth adversary | arXiv: 2605.12664 | 📄 ../paper_cache/NeurIPS2026/2605.12664.txt
- program-as-weights a programming paradigm for fuzzy functions | arXiv: 2607.02512 | 📄 ../paper_cache/NeurIPS2026/2607.02512.txt
- programbench can language models rebuild programs from scratch | arXiv: 2605.03546 | 📄 ../paper_cache/NeurIPS2026/2605.03546.txt
- progress-aware distillation for mitigating stagnation in small language model ag | arXiv: 2610.19439 | 📄 ../paper_cache/NeurIPS2026/2610.19439.txt
- progressive residual warmup for language model pretraining | arXiv: 2603.05369 | 📄 ../paper_cache/NeurIPS2026/2603.05369.txt
- progressive risk estimation for accident anticipation | arXiv: 2609.32811
- promptactivation duality improving activation steering via attention-level inter | arXiv: 2605.10664 | 📄 ../paper_cache/NeurIPS2026/2605.10664.txt
- prompting diffusion models for zero-shot instance segmentation | arXiv: 2606.22660 | 📄 ../paper_cache/NeurIPS2026/2606.22660.txt
- prompts to proxies emulating human preferences via a compact llm ensemble | arXiv: 2509.11311
- propagation of chaos in contextual flow maps | arXiv: 2605.16747 | 📄 ../paper_cache/NeurIPS2026/2605.16747.txt
- Property-Guided LLM Program Synthesis for Planning | arXiv: 2605.16142
- proprio latent self-scoring and inference-time refinement for physically plausib | arXiv: 2605.28230 | 📄 ../paper_cache/NeurIPS2026/2605.28230.txt
- prospective hindsight self-calibrating reinforcement learning via predictionreal | arXiv: 2610.02740 | 📄 ../paper_cache/NeurIPS2026/2610.02740.txt
- proteus incremental memory activation for long-context sequence modeling | arXiv: 2608.16844 | 📄 ../paper_cache/NeurIPS2026/2608.16844.txt
- provable joint decontamination for benchmarking multiple large language models | arXiv: 2605.21543 | 📄 ../paper_cache/NeurIPS2026/2605.21543.txt
- provable robustness against backdoor attacks via the primal-dual perspective on | arXiv: 2605.21780 | 📄 ../paper_cache/NeurIPS2026/2605.21780.txt
- provable speedups from dynamic population sizes in evolutionary algorithms for m | arXiv: 2607.23800 | 📄 ../paper_cache/NeurIPS2026/2607.23800.txt
- proxy-based approximation of shapley and banzhaf interactions | arXiv: 2605.22738 | 📄 ../paper_cache/NeurIPS2026/2605.22738.txt
- prpo perception-reinforced policy optimization via token-level dynamic advantage | arXiv: 2606.08708 | 📄 ../paper_cache/NeurIPS2026/2606.08708.txt
- prudent-banker no extra fees for baseline safety in adversarial bandits with and | arXiv: 2605.23351 | 📄 ../paper_cache/NeurIPS2026/2605.23351.txt
- pruning and distilling mixture-of-experts into dense language models | arXiv: 2605.28207 | 📄 ../paper_cache/NeurIPS2026/2605.28207.txt
- publishing below-threshold triangle counts under local weight differential priva | arXiv: 2601.01710 | 📄 ../paper_cache/NeurIPS2026/2601.01710.txt
- pulse identifying demonstration-utility features with sparse autoencoders | arXiv: 2609.32469
- pure exploration beyond reward feedback the role of post-action context | arXiv: 2502.03061
- Pushing Biomolecular Utility-Diversity Frontiers with Supergroup Relative Policy Optimization | arXiv: 2605.08659
- pygmalion effect in vision image-to-clay translation for reflective geometry rec | arXiv: 2511.21098
- q-arvd quantizing autoregressive video diffusion models | arXiv: 2605.21072 | 📄 ../paper_cache/NeurIPS2026/2605.21072.txt
- q-probe scaling image quality assessment to high resolution via context-aware ag | arXiv: 2601.15356 | 📄 ../paper_cache/NeurIPS2026/2601.15356.txt
- qmaxcal path-space regularization for open quantum control via girsanovs theorem | arXiv: 2606.19947 | 📄 ../paper_cache/NeurIPS2026/2606.19947.txt
- qrita high-performance top-k and top-p using pivot-based truncation and selectio | arXiv: 2602.01518 | 📄 ../paper_cache/NeurIPS2026/2602.01518.txt
- quantifying concentration phenomena of mean-field transformers in the low-temper | arXiv: 2605.10931 | 📄 ../paper_cache/NeurIPS2026/2605.10931.txt
- quantile geometry regularization for distributional reinforcement learning | arXiv: 2605.08182 | 📄 ../paper_cache/NeurIPS2026/2605.08182.txt
- quanvi score-based variational inference via quantum maximally mixed states | arXiv: 2609.39164
- Querying Counterfactuals on Tissue Graphs with Supervised Disentanglement | arXiv: 2606.08493
- quotient-categorical representations for bellman-compatible average-reward distr | arXiv: 2605.11289 | 📄 ../paper_cache/NeurIPS2026/2605.11289.txt
- qutcc quantile uncertainty training and conformal calibration for imaging invers | arXiv: 2507.14760
- ra-cfgcache from branch-level criteria to guided-risk control under classifier-f | arXiv: 2609.36433 | 📄 ../paper_cache/NeurIPS2026/2609.36433.txt
- ra-clipscore making generative model evaluation more interpretable | arXiv: 2608.12088 | 📄 ../paper_cache/NeurIPS2026/2608.12088.txt
- rabbit rapidly adaptive bold foundation model via brain-tuning for accurate zero | arXiv: 2607.05171 | 📄 ../paper_cache/NeurIPS2026/2607.05171.txt
- radar relative angular divergence across representations | arXiv: 2605.23028 | 📄 ../paper_cache/NeurIPS2026/2605.23028.txt
- RAIL: Rethinking Auditory Intelligence in Large Audio-Language Models with a CHC-Grounded Benchmark | arXiv: 2606.11260
- ram-h1200 a unified evaluation and dataset on hand radiographs for rheumatoid ar | arXiv: 2605.05616
- ramanbench a large-scale benchmark for machine learning on raman spectroscopy | arXiv: 2605.02003 | 📄 ../paper_cache/NeurIPS2026/2605.02003.txt
- random matrix theory of early-stopped gradient flow a transient bbp scenario | arXiv: 2604.18450 | 📄 ../paper_cache/NeurIPS2026/2604.18450.txt
- random neural network expressivity for non-linear partial differential equations | arXiv: 2605.25057 | 📄 ../paper_cache/NeurIPS2026/2605.25057.txt
- rank-constrained adaptation for reliable real-world performance | arXiv: 2602.06924
- rank-transformed dissimilarity profiles for high-dimensional classification | arXiv: 2306.15199
- rankalign vision-language representation alignment via rank transformation | arXiv: 2610.31145
- ranke end-to-end post-training for discrete text-to-image generation with decode | arXiv: 2605.21195 | 📄 ../paper_cache/NeurIPS2026/2605.21195.txt
- ransac scoring done right | arXiv: 2606.27385 | 📄 ../paper_cache/NeurIPS2026/2606.27385.txt
- rapd resolution-agnostic pixel diffusion via semantics-enriched implicit represe | arXiv: 2605.15908 | 📄 ../paper_cache/NeurIPS2026/2605.15908.txt
- rats patches talk through registers emergent parts in register attention transfo | arXiv: 2606.14701 | 📄 ../paper_cache/NeurIPS2026/2606.14701.txt
- raw-routed mixture of adapters a causal intervention for routing collapse in tim | arXiv: 2609.39445
- razer pushing the limits of nvfp4 quantization with redundant zero remapping | arXiv: 2501.04052
- re-evaluating confidence remasking in masked diffusion language models | arXiv: 2606.12232 | 📄 ../paper_cache/NeurIPS2026/2606.12232.txt
- re-evaluating continual learning with few-shot adaptation | arXiv: 2606.03843 | 📄 ../paper_cache/NeurIPS2026/2606.03843.txt
- re-examining low rank adaptation for private llm fine-tuning | arXiv: 2510.01137
- read parse describe unified document parsing with visual element description gen | arXiv: 2610.20335 | 📄 ../paper_cache/NeurIPS2026/2610.20335.txt
- real in real out what if we only use real data for scene text editing | arXiv: 2610.27592
- real2sim in hoi toward physically plausible hoi reconstruction from monocular vi | arXiv: 2605.14462 | 📄 ../paper_cache/NeurIPS2026/2605.14462.txt
- realism vs accuracy event sequence forecasting from a generative modeling perspe | arXiv: 2610.12586 | 📄 ../paper_cache/NeurIPS2026/2610.12586.txt
- realm a unified red-teaming benchmark for physical-world vlms | arXiv: 2606.23892 | 📄 ../paper_cache/NeurIPS2026/2606.23892.txt
- reason in the words you speak idiolectal paraphrasing off-policy traces for reas | arXiv: 2608.26684 | 📄 ../paper_cache/NeurIPS2026/2608.26684.txt
- reasoning as compression unifying budget forcing via the conditional information | arXiv: 2603.08462 | 📄 ../paper_cache/NeurIPS2026/2603.08462.txt
- reasoning-trace collapse evaluating the loss of explicit reasoning during fine-t | arXiv: Reasoning
- rebalancing reference frame dominance to improve motion in image-to-video models | arXiv: 2605.19398
- rebellious student reversing teacher signals for reasoning exploration with self | arXiv: 2605.10781 | 📄 ../paper_cache/NeurIPS2026/2605.10781.txt
- recap looking once is not enough for vision-language reasoning | arXiv: 2610.30834 | 📄 ../paper_cache/NeurIPS2026/2610.30834.txt
- recog relational concept graph for training-free personalization | arXiv: 2610.31282 | 📄 ../paper_cache/NeurIPS2026/2610.31282.txt
- recognize -- open-set comic character re-identification | arXiv: 2609.34032
- recon reconstruction-guided reasoning synthesis for user modeling | arXiv: 2605.26969 | 📄 ../paper_cache/NeurIPS2026/2605.26969.txt
- reconciling causality and non-equilibrium thermodynamics with hamiltonian causal | arXiv: 2606.04822 | 📄 ../paper_cache/NeurIPS2026/2606.04822.txt
- reconsidering positional supervision in masked diffusion language model training | arXiv: 2601.22947 | 📄 ../paper_cache/NeurIPS2026/2601.22947.txt
- reconstructing the vocal tract with differentiable acoustic simulation | arXiv: 2609.36737
- recover resilient llm pre-training system via fault-tolerant collective and vers | arXiv: 2605.11215 | 📄 ../paper_cache/NeurIPS2026/2605.11215.txt
- recovery guarantees for posterior sampling of one-bit compressed sensing | arXiv: 2610.11834 | 📄 ../paper_cache/NeurIPS2026/2610.11834.txt
- recursive semantic divergence for llm agent consistency | arXiv: 2610.33012 | 📄 ../paper_cache/NeurIPS2026/2610.33012.txt
- recursively trained diffusion models limiting collapse distribution and spectral | arXiv: 2606.13796 | 📄 ../paper_cache/NeurIPS2026/2606.13796.txt
- redefining instance matching a unified framework for part-aware matching in pano | arXiv: 2605.31094
- Reducing Credit Assignment Variance via Counterfactual Reasoning Paths | arXiv: 2605.16302
- redvla physical red teaming for vision-language-action models | arXiv: 2604.22591 | 📄 ../paper_cache/NeurIPS2026/2604.22591.txt
- reefnet a large-scale dataset and benchmark for fine-grained coral reef recognit | arXiv: 2510.16822
- RefineAny3D: Depth Refinement as Semantic Alignment for Monocular 3D Detection | arXiv: 2608.09147
- reflectdrive-2 reinforcement-learning-aligned self-editing for discrete diffusio | arXiv: 2605.04647 | 📄 ../paper_cache/NeurIPS2026/2605.04647.txt
- reflective prompted policy optimization trajectory-grounded revision and salienc | arXiv: 2605.08315 | 📄 ../paper_cache/NeurIPS2026/2605.08315.txt
- reformulating kv cache eviction problem for long-context llm inference | arXiv: 2605.07234 | 📄 ../paper_cache/NeurIPS2026/2605.07234.txt
- reformulating neural operators in d1 dimensions for embedding evolution | arXiv: 2505.11766
- ReGDiff: Guided Diffusion in Regulated Latent Space for Exploring Metamaterial Voxel Geometry | arXiv: 2609.34231
- RegimeVGGT: Layer-Wise Spatially Preserving Redundancy Removal for Visual Geometry Grounded Transformer | arXiv: 2606.18439
- register anything model for generalizable and robust point cloud registration | arXiv: 2610.28821
- regret minimization in single-dimensional contract-design with binary actions | arXiv: 2606.06125 | 📄 ../paper_cache/NeurIPS2026/2606.06125.txt
- regretoracle complexity tradeoffs in agnostic online learning | arXiv: 2605.07155 | 📄 ../paper_cache/NeurIPS2026/2605.07155.txt
- reinforced fast weights via next-sequence prediction | arXiv: 2602.16704 | 📄 ../paper_cache/NeurIPS2026/2602.16704.txt
- reinforcement learning for exponential utility algorithms and convergence in dis | arXiv: 2605.08053 | 📄 ../paper_cache/NeurIPS2026/2605.08053.txt
- reinforcement learning from rich feedback with distributional dagger | arXiv: 2606.05152 | 📄 ../paper_cache/NeurIPS2026/2606.05152.txt
- reinforcing multimodal reasoning against visual degradation | arXiv: 2605.09262 | 📄 ../paper_cache/NeurIPS2026/2605.09262.txt
- reinforcing vlas in task-agnostic world models | arXiv: 2605.12334 | 📄 ../paper_cache/NeurIPS2026/2605.12334.txt
- relagent llm agents as data scientists for relational learning | arXiv: 2605.07840 | 📄 ../paper_cache/NeurIPS2026/2605.07840.txt
- relation-aware graph foundation model | arXiv: 2505.12027
- RelationVGGT: Visual Geometry Transformers for 3D Spatial Relation Segmentation | arXiv: 2610.00970
- reloop structured modeling and behavioral verification for reliable llm-based op | arXiv: 2602.15983 | 📄 ../paper_cache/NeurIPS2026/2602.15983.txt
- remember with confidence uncertainty quantification for spatio-temporal memory w | arXiv: 2606.08277 | 📄 ../paper_cache/NeurIPS2026/2606.08277.txt
- remember your trace memory-guided long-horizon agentic framework for consistent | arXiv: 2605.14563
- ReorgGS: Equivalent Distribution Reorganization for 3D Gaussian Splatting | arXiv: 2605.08739
- rep2text decoding full text from a single llm token representation | arXiv: 2511.06571
- repercent scaling disentangled representation learning beyond two modalities | arXiv: 2606.05109 | 📄 ../paper_cache/NeurIPS2026/2606.05109.txt
- replay-buffer engineering for noise-aware quantum circuit optimization | arXiv: 强化学习
- repo-vla recovery-driven policy optimization for vision-language-action models | arXiv: 2605.09410 | 📄 ../paper_cache/NeurIPS2026/2605.09410.txt
- repomirage probing repository context reasoning in code agents with perturbation | arXiv: 2605.26177 | 📄 ../paper_cache/NeurIPS2026/2605.26177.txt
- reporting practice matters the impact of reference choice on chest x-ray report | arXiv: 2609.19093 | 📄 ../paper_cache/NeurIPS2026/2609.19093.txt
- representation forcing for bottleneck-free unified multimodal models | arXiv: 2605.31604 | 📄 ../paper_cache/NeurIPS2026/2605.31604.txt
- representation learning enables scalable multitask deep reinforcement learning | arXiv: 2606.05555 | 📄 ../paper_cache/NeurIPS2026/2606.05555.txt
- RESBev: Making BEV Perception More Robust | arXiv: 2603.09529
- rescast-100k a comprehensive dataset for cross-domain residential load and indoo | arXiv: 2606.02852 | 📄 ../paper_cache/NeurIPS2026/2606.02852.txt
- ReSCUE: Re-translation with Sentence Commitment for Unsegmented Long-Form Simultaneous Sign Language Translation | arXiv: 2610.03022
- rescuebench can embodied agents save lives in the wild | arXiv: 2606.01848 | 📄 ../paper_cache/NeurIPS2026/2606.01848.txt
- reset accurate latency-critical nvfp4 reasoning via step-aware temperature scali | arXiv: 2606.13233 | 📄 ../paper_cache/NeurIPS2026/2606.13233.txt
- residual calibration via local feature-space refinement | arXiv: 2610.30652
- resilience matters for embodied agents system new metrics systematic evaluation | arXiv: 2608.23839 | 📄 ../paper_cache/NeurIPS2026/2608.23839.txt
- Resolving Representation Ambiguity in Feedforward Novel View Synthesis Transformer via Semantic-Spatial Decoupling | arXiv: 2605.18599
- resource-aware parameter-efficient model adaptation for onboard high-dimensional | arXiv: 2609.33687 | 📄 ../paper_cache/NeurIPS2026/2609.33687.txt
- rest-rl reinforcing llm reasoning through unified self-training and value-guided | arXiv: 2508.19576
- rethinking causal action tokenization with conditional annealing in flow matchin | arXiv: 2609.35469 | 📄 ../paper_cache/NeurIPS2026/2609.35469.txt
- rethinking contrastive loss in clip post-training a complementary framework with | arXiv: 2610.11374 | 📄 ../paper_cache/NeurIPS2026/2610.11374.txt
- rethinking cross-layer information routing in diffusion transformers | arXiv: 2605.20708
- rethinking dataset distillation for classification do distilled sets outperform | arXiv: 2606.18209 | 📄 ../paper_cache/NeurIPS2026/2606.18209.txt
- rethinking expressivity and efficiency in test-time training | arXiv: 2608.21308 | 📄 ../paper_cache/NeurIPS2026/2608.21308.txt
- rethinking forward processes for score-based nonlinear data assimilation in high | arXiv: 2604.02889 | 📄 ../paper_cache/NeurIPS2026/2604.02889.txt
- rethinking how to remember beyond atomic facts in lifelong llm agent memory | arXiv: 2605.19952
- rethinking infrared small target detection a foundation-driven efficient paradig | arXiv: 2512.05511
- rethinking language model scaling under transferable hypersphere optimization | arXiv: 2603.28743 | 📄 ../paper_cache/NeurIPS2026/2603.28743.txt
- rethinking layer-wise model merging through chain of merges | arXiv: 2508.21421
- rethinking learning from label proportions via moment matching | arXiv: 2610.21262 | 📄 ../paper_cache/NeurIPS2026/2610.21262.txt
- rethinking llm fine-tuning via weight space reparameterization preserving safety | arXiv: 2610.26443
- rethinking long-video efficiency a joint allocation perspective on frames pixels | arXiv: 2610.04318 | 📄 ../paper_cache/NeurIPS2026/2610.04318.txt
- rethinking lora initialization for robust asymmetric learning rates | arXiv: 2610.32142 | 📄 ../paper_cache/NeurIPS2026/2610.32142.txt
- rethinking molecular graph backdoors under chemistry-aware admission | arXiv: 2606.23361 | 📄 ../paper_cache/NeurIPS2026/2606.23361.txt
- rethinking on-policy self-distillation for thinking models | arXiv: 2607.05184 | 📄 ../paper_cache/NeurIPS2026/2607.05184.txt
- rethinking personalized generation test-time alignment via factorized ranking mo | arXiv: 2609.35695
- rethinking projector training in multimodal llms | arXiv: 2610.18598 | 📄 ../paper_cache/NeurIPS2026/2610.18598.txt
- rethinking psychometric evaluation of llms when and why self-reports predict beh | arXiv: 2606.12730 | 📄 ../paper_cache/NeurIPS2026/2606.12730.txt
- rethinking rubric generation for improving llm judge and reward modeling for ope | arXiv: 2602.05125 | 📄 ../paper_cache/NeurIPS2026/2602.05125.txt
- rethinking sae evaluation an atomic interpretable unit framework reveals hidden | arXiv: 2610.30474
- rethinking semantic id construction for generative recommendation simhash with p | arXiv: 2610.07402 | 📄 ../paper_cache/NeurIPS2026/2610.07402.txt
- rethinking state tracking in recurrent models through error control dynamics | arXiv: 2605.07755 | 📄 ../paper_cache/NeurIPS2026/2605.07755.txt
- rethinking structured generation can graph-based reasoning resolve ambiguity | arXiv: 2610.31681 | 📄 ../paper_cache/NeurIPS2026/2610.31681.txt
- rethinking the readout unlocking video backbones for ai-generated video detectio | arXiv: 2607.15321 | 📄 ../paper_cache/NeurIPS2026/2607.15321.txt
- rethinking the state update gate for long-sequence recurrent 3d reconstruction | arXiv: 重建与渲染
- Rethinking Training Targets, Architectures and Data Quality for Universal Speech Enhancement | arXiv: 2603.02641
- rethinking vector field learning for generative segmentation | arXiv: 2603.19218 | 📄 ../paper_cache/NeurIPS2026/2603.19218.txt
- rethinking xai evaluation a human-centered audit of shapley benchmarks in high-s | arXiv: 2604.22662 | 📄 ../paper_cache/NeurIPS2026/2604.22662.txt
- retrieval over training similarity search-based model selection for time series | arXiv: 2610.20243 | 📄 ../paper_cache/NeurIPS2026/2610.20243.txt
- reviewer scores are not comparable across research areas in ml peer review | arXiv: 2607.27209 | 📄 ../paper_cache/NeurIPS2026/2607.27209.txt
- revisiting cross-view completion self-supervised pre-training via reconstruction | arXiv: 2609.01530 | 📄 ../paper_cache/NeurIPS2026/2609.01530.txt
- revisiting decentralized online convex optimization with compressed communicatio | arXiv: 2607.01665 | 📄 ../paper_cache/NeurIPS2026/2607.01665.txt
- revisiting diffusion fine-tuning for unsupervised domain adaptation | arXiv: 2609.33716
- revisiting diffusion model predictions through dimensionality | arXiv: 2601.21419 | 📄 ../paper_cache/NeurIPS2026/2601.21419.txt
- revisiting on-policy adversarial black-box distillation calibrating groupwise re | arXiv: 2609.39757 | 📄 ../paper_cache/NeurIPS2026/2609.39757.txt
- revitalizing medical time series with vision-informed retrieval a vision-languag | arXiv: 2609.34652
- reviving stale updates data-free knowledge distillation for asynchronous federat | arXiv: 2511.00655
- reward bias substitution single-axis bias mitigations redirect optimization pres | arXiv: 2605.27996 | 📄 ../paper_cache/NeurIPS2026/2605.27996.txt
- reward inflation a healthy stimulus for reinforcement learning | arXiv: 2610.02545 | 📄 ../paper_cache/NeurIPS2026/2610.02545.txt
- reward score matching unifying reward-based fine-tuning for flow and diffusion m | arXiv: 2604.17415 | 📄 ../paper_cache/NeurIPS2026/2604.17415.txt
- reward-conditioned reinforcement learning | arXiv: 2603.05066 | 📄 ../paper_cache/NeurIPS2026/2603.05066.txt
- reward-free pretraining for reinforcement learning via occupancy coverage maximi | arXiv: 2606.21271 | 📄 ../paper_cache/NeurIPS2026/2606.21271.txt
- rheosampling resolving the one-hot dilemma in stochastic dynamic-tree speculativ | arXiv: 2609.21827 | 📄 ../paper_cache/NeurIPS2026/2609.21827.txt
- rifle removal of image flicker-banding via latent diffusion enhancement | arXiv: 2509.24644
- rigidformer learning rigid dynamics using transformers | arXiv: 2605.09196 | 📄 ../paper_cache/NeurIPS2026/2605.09196.txt
- RipplePLM: Structural and Property Decoupling for Protein Mutation Effect Generation | arXiv: 2610.01891
- rise residual subspace expert for generalizable text-centric image forgery local | arXiv: 2610.24480 | 📄 ../paper_cache/NeurIPS2026/2610.24480.txt
- risk-averse online pomdp planning via cvar of the immediate cost with performanc | arXiv: 2609.35874 | 📄 ../paper_cache/NeurIPS2026/2609.35874.txt
- risk-controlled post-processing of decision policies | arXiv: 2605.06479 | 📄 ../paper_cache/NeurIPS2026/2605.06479.txt
- rl-guided temporal localization for dual-channel retrieval in long-horizon agent | arXiv: 2610.23598 | 📄 ../paper_cache/NeurIPS2026/2610.23598.txt
- roar benchmarking lmm agents under real-time constraints in multiplayer action-s | arXiv: 2610.24282 | 📄 ../paper_cache/NeurIPS2026/2610.24282.txt
- roboalign-r1 distilled multimodal reward alignment for robot video world models | arXiv: 2605.03821 | 📄 ../paper_cache/NeurIPS2026/2605.03821.txt
- robowits unexpected challenges for robotic creative problem solving | arXiv: 2605.30326 | 📄 ../paper_cache/NeurIPS2026/2605.30326.txt
- robust and efficient finetuning of vision foundation models via implicit ensembl | arXiv: 2510.06982
- robust diffusion models via divergence-induced weighted denoising | arXiv: 2606.22521 | 📄 ../paper_cache/NeurIPS2026/2606.22521.txt
- robust domain generalization under divergent marginal and conditional distributi | arXiv: 2602.02015 | 📄 ../paper_cache/NeurIPS2026/2602.02015.txt
- Robust Inference-Time Steering of Protein Diffusion Models via Embedding Optimization | arXiv: 2602.05285
- robust multi-view clustering against imperfect information | arXiv: 2606.04343 | 📄 ../paper_cache/NeurIPS2026/2606.04343.txt
- robust pac learning of concurrent stochastic games | arXiv: 2609.04189 | 📄 ../paper_cache/NeurIPS2026/2609.04189.txt
- robust policy optimization to prevent catastrophic forgetting | arXiv: 2602.08813 | 📄 ../paper_cache/NeurIPS2026/2602.08813.txt
- robust residual correction via selective deployment for time series forecasting | arXiv: 2512.22428
- Robustness of Internal Signals for Hallucination Detection in Vision-Language Models | arXiv: 2610.27041
- rocket residual-oriented multi-layer alignment for spatially-aware vision-langua | arXiv: 2602.17951 | 📄 ../paper_cache/NeurIPS2026/2602.17951.txt
- rok-fortress measuring the effect of geopolitical transcreation for national sec | arXiv: 2605.14152 | 📄 ../paper_cache/NeurIPS2026/2605.14152.txt
- rollout pass-rate control steering binary-reward rl toward its most informative | arXiv: 2605.05112 | 📄 ../paper_cache/NeurIPS2026/2605.05112.txt
- root cause analysis of measurement and mechanistic anomalies | arXiv: 2601.23026 | 📄 ../paper_cache/NeurIPS2026/2601.23026.txt
- root-selecting fixed-point inversion for rectified flows via trajectory straight | arXiv: 2606.17584 | 📄 ../paper_cache/NeurIPS2026/2606.17584.txt
- rosa rotational sparse adaptation for memory-efficient fine-tuning | arXiv: 2610.06243 | 📄 ../paper_cache/NeurIPS2026/2610.06243.txt
- rosetta composable native multimodal pretraining | arXiv: 2607.00293 | 📄 ../paper_cache/NeurIPS2026/2607.00293.txt
- rotmole enhancing mixture of low-rank experts through rotational gating mechanis | arXiv: 2605.25565 | 📄 ../paper_cache/NeurIPS2026/2605.25565.txt
- rotvla rotational latent action for vision-language-action model | arXiv: 2605.13403 | 📄 ../paper_cache/NeurIPS2026/2605.13403.txt
- routers learn the geometry of their experts geometric coupling in sparse mixture | arXiv: 2605.12476 | 📄 ../paper_cache/NeurIPS2026/2605.12476.txt
- RPC-GS: Gaussian Splatting with native RPC Rendering for Satellite Imagery | arXiv: 2606.06690
- rpfq-vit rotated phase-frame quantization for extremely low-bit weights in visio | arXiv: 2610.04457 | 📄 ../paper_cache/NeurIPS2026/2610.04457.txt
- rsrcc a remote sensing regional change comprehension benchmark constructed via r | arXiv: 2604.20623 | 📄 ../paper_cache/NeurIPS2026/2604.20623.txt
- Rubato: Transcribing Piano Music with Timestamps | arXiv: 2605.24291
- runtime monitoring of perception-based autonomous systems via embedding temporal | arXiv: 2605.12651 | 📄 ../paper_cache/NeurIPS2026/2605.12651.txt
- rustmizan a compilable contamination-aware benchmarking framework for rust vulne | arXiv: 2607.04729 | 📄 ../paper_cache/NeurIPS2026/2607.04729.txt
- RVLoss: Runoff Vote Loss for Self-Supervised LiDAR Scene Flow Estimation | arXiv: 2608.18864
- rvr retrieve-verify-retrieve for comprehensive question answering | arXiv: 2602.18425 | 📄 ../paper_cache/NeurIPS2026/2602.18425.txt
- RxGS: Receiver-Generalizable 3D Gaussian Splatting for Radio-Frequency Data Synthesis | arXiv: 2605.24290
- rxnoptbench benchmarking llms for reaction-condition optimization in organic met | arXiv: 2610.02242 | 📄 ../paper_cache/NeurIPS2026/2610.02242.txt
- s2d sparse-to-dense keymask distillation for unsupervised video instance segment | arXiv: 2512.14440
- s2mdf a plug-and-play layer for intersection-free multi-object signed distance f | arXiv: 2605.29761 | 📄 ../paper_cache/NeurIPS2026/2605.29761.txt
- s2t-rlhf hierarchical credit assignment for stable preference-based rlhf | arXiv: 2607.18258 | 📄 ../paper_cache/NeurIPS2026/2607.18258.txt
- saas-bench can computer-use agents leverage real-world saas to solve professiona | arXiv: 2605.15777 | 📄 ../paper_cache/NeurIPS2026/2605.15777.txt
- SaaSBench: Exploring the Boundaries of Coding Agents in Long-Horizon Enterprise SaaS Engineering | arXiv: 2605.17526
- safe score matching diffusion policies with hamilton-jacobi reachability for onl | arXiv: 2609.33337
- safeguarding mutual correction in source-free domain adaptation via cut statisti | arXiv: 2610.02981 | 📄 ../paper_cache/NeurIPS2026/2610.02981.txt
- safety geometry collapse in multimodal llms and adaptive drift correction | arXiv: 2605.18104 | 📄 ../paper_cache/NeurIPS2026/2605.18104.txt
- safety reconstructed generative modeling via masked diffusion builds strong safe | arXiv: 2609.33634 | 📄 ../paper_cache/NeurIPS2026/2609.33634.txt
- sagas semantic-aware graph-assisted stitching for offline temporal logic plannin | arXiv: 2512.00775
- sair cost-efficient multi-stage ml pipeline autoscaling via in-context reinforce | arXiv: 2601.22397 | 📄 ../paper_cache/NeurIPS2026/2601.22397.txt
- salart-vqa diagnosing whether vlms understand salient artifacts in generated ima | arXiv: 2606.12671 | 📄 ../paper_cache/NeurIPS2026/2606.12671.txt
- salt when more rollouts dont help in group-based policy optimization and how to | arXiv: 2606.05800 | 📄 ../paper_cache/NeurIPS2026/2606.05800.txt
- SAM 3D Animal: Promptable Animal 3D Reconstruction from Images in the Wild | arXiv: 2605.07604
- same concept different directions cross-modal feature heterogeneity in sparse au | arXiv: 2606.29888 | 📄 ../paper_cache/NeurIPS2026/2606.29888.txt
- same words different judgments how preferences vary across modalities | arXiv: 2602.22710 | 📄 ../paper_cache/NeurIPS2026/2602.22710.txt
- sample-efficient optimization over generative priors via coarse learnability | arXiv: 2503.06917
- sampling-based safe reinforcement learning | arXiv: 2605.19469 | 📄 ../paper_cache/NeurIPS2026/2605.19469.txt
- sampling-free privacy accounting for matrix mechanisms under random allocation | arXiv: 2601.21636 | 📄 ../paper_cache/NeurIPS2026/2601.21636.txt
- Sandboxed Coding Agents are Competitive Omni-modal Task Solvers | arXiv: 2606.00579
- sanity checks for sparse autoencoders do saes beat random baselines | arXiv: 2602.14111 | 📄 ../paper_cache/NeurIPS2026/2602.14111.txt
- sapiensid 20 aligning human recognition foundation models with human perception | arXiv: 2608.10497 | 📄 ../paper_cache/NeurIPS2026/2608.10497.txt
- sas simple attention sparsification via end-to-end optimization of context ranki | arXiv: 2609.13141 | 📄 ../paper_cache/NeurIPS2026/2609.13141.txt
- satnav a scalable benchmark for long-horizon uav vision-language navigation from | arXiv: 2609.31507
- scalable distributed stochastic optimization via bidirectional compression beyon | arXiv: 2605.07795 | 📄 ../paper_cache/NeurIPS2026/2605.07795.txt
- scalable maximum entropy reinforcement learning for diffusion policies via adjoi | arXiv: 2606.22630
- scalable minimal-change learning for controllable image editing | arXiv: 2610.06021 | 📄 ../paper_cache/NeurIPS2026/2610.06021.txt
- scalable variational bayesian fine-tuning of llms via orthogonalized low-rank ad | arXiv: 2604.03388 | 📄 ../paper_cache/NeurIPS2026/2604.03388.txt
- scale improving guidance-free visual generation via self-contrastive alignment f | arXiv: 2610.23263
- scaling laws and tradeoffs in recurrent networks of expressive neurons | arXiv: 2605.12049 | 📄 ../paper_cache/NeurIPS2026/2605.12049.txt
- scaling laws for multimodal data mixtures | arXiv: 2610.14423 | 📄 ../paper_cache/NeurIPS2026/2610.14423.txt
- scaling linear mode connectivity and merging to billion parameter pretrained tra | arXiv: 2606.23607 | 📄 ../paper_cache/NeurIPS2026/2606.23607.txt
- scaling multi-teacher distillation for digital pathology | arXiv: 2610.12574 | 📄 ../paper_cache/NeurIPS2026/2610.12574.txt
- scdbench a benchmark for llm-based smart contract decompilers | arXiv: 2605.29059 | 📄 ../paper_cache/NeurIPS2026/2605.29059.txt
- scenes as objects not primitives instance-structured 3d tokenization from unpose | arXiv: 2606.29513 | 📄 ../paper_cache/NeurIPS2026/2606.29513.txt
- scenescaffold active scene-state construction for unified 3d scene understanding | arXiv: 2609.33518
- SchemaPose: RGB-Based Category-Level Pose Estimation with Parametric Category Schema | arXiv: 2610.18374
- schemearena factorized stress testing of scheming in llm agents | arXiv: 2609.08126 | 📄 ../paper_cache/NeurIPS2026/2609.08126.txt
- scir a controllable benchmark for scientific reasoning in llms | arXiv: 2606.13020
- scope-rl stable and quantitative control of policy entropy in rl post-training | arXiv: 2510.08141
- scope-rl 基于温度自适应正样本的策略熵稳定与定量控制 | arXiv: 2510.08141
- scratchpad patching decoupling compute from patch size in byte-level language mo | arXiv: 2605.09630 | 📄 ../paper_cache/NeurIPS2026/2605.09630.txt
- screenshot a foundation model for few-shot combination drug screening | arXiv: 2608.12219 | 📄 ../paper_cache/NeurIPS2026/2608.12219.txt
- scshapebench discovering geometry from high dimensional scrnaseq data | arXiv: 2605.12662 | 📄 ../paper_cache/NeurIPS2026/2605.12662.txt
- sds-lora overcoming anisotropic gradient scaling in low-rank adaptation | arXiv: 2606.16454 | 📄 ../paper_cache/NeurIPS2026/2606.16454.txt
- sead competence-aware on-policy distillation via entropy-guided supervision | arXiv: 2606.28562 | 📄 ../paper_cache/NeurIPS2026/2606.28562.txt
- seahorse a unified benchmarking framework for spatiotemporal event modeling | arXiv: 2607.01022 | 📄 ../paper_cache/NeurIPS2026/2607.01022.txt
- search at the cost of sampling nearly-instant latent space bayesian optimization | arXiv: 2609.19476 | 📄 ../paper_cache/NeurIPS2026/2609.19476.txt
- search more think less rethinking long-horizon agentic search for efficiency and | arXiv: 2602.22675 | 📄 ../paper_cache/NeurIPS2026/2602.22675.txt
- search-augmented masked diffusion models for constrained generation | arXiv: 2602.02727 | 📄 ../paper_cache/NeurIPS2026/2602.02727.txt
- secure seed-based multi-bit watermarking for diffusion models from first princip | arXiv: 2605.06153 | 📄 ../paper_cache/NeurIPS2026/2605.06153.txt
- secureclaw clawing back control of llm agents | arXiv: 2606.09549 | 📄 ../paper_cache/NeurIPS2026/2606.09549.txt
- securing ai agents with information-flow control | arXiv: 2505.23643
- see it to place it evolving macro placements with vision language models | arXiv: 2603.28733 | 📄 ../paper_cache/NeurIPS2026/2603.28733.txt
- seed self-speculative decoding via implicit encoder-decoder | arXiv: 2609.36590
- seeing is not screening multimodal hidden instruction attacks on agent skill sca | arXiv: 2606.18198 | 📄 ../paper_cache/NeurIPS2026/2606.18198.txt
- seeing speech learning visible articulatory dynamics for speech-driven 3d facial | arXiv: 人体理解
- seeing together multi-robot cooperative egocentric spatial reasoning with multim | arXiv: 2605.18431 | 📄 ../paper_cache/NeurIPS2026/2605.18431.txt
- seeking the unfamiliar but memorable conceptual creativity as meta-learning | arXiv: 2605.16477 | 📄 ../paper_cache/NeurIPS2026/2605.16477.txt
- seg3dparts segmentation-grounded controllable part-level 3d generation | arXiv: 3D生成与编辑
- sega spectral-energy guided attention for resolution extrapolation in diffusion | arXiv: 2605.22668 | 📄 ../paper_cache/NeurIPS2026/2605.22668.txt
- select smarter not more prompt-aware evaluation scheduling with submodular guara | arXiv: 2604.11328 | 📄 ../paper_cache/NeurIPS2026/2604.11328.txt
- select-then-differentiate solving bilevel optimization with manifold lower-level | arXiv: 2605.09209 | 📄 ../paper_cache/NeurIPS2026/2605.09209.txt
- Selection, Not Fusion: Radar-Modulated State Space Models for Radar-Camera Depth Estimation | arXiv: 2605.11840
- selectivity and shape in the design of forward-forward goodness functions | arXiv: 2604.13081 | 📄 ../paper_cache/NeurIPS2026/2604.13081.txt
- self driving datasets from 20 million papers to nuanced biomedical knowledge at | arXiv: 2605.07022 | 📄 ../paper_cache/NeurIPS2026/2605.07022.txt
- self-evolverec self-evolving recommender systems with llm-based directional feed | arXiv: 2602.12612 | 📄 ../paper_cache/NeurIPS2026/2602.12612.txt
- self-improvement imitation with biologically guided search for protein design un | arXiv: 2605.26690 | 📄 ../paper_cache/NeurIPS2026/2605.26690.txt
- self-organized conformal prediction reducing regional coverage gaps with unsuper | arXiv: 2606.29403 | 📄 ../paper_cache/NeurIPS2026/2606.29403.txt
- self-rewarded multimodal coherent reasoning across diverse visual domains | arXiv: 2512.22545 | 📄 ../paper_cache/NeurIPS2026/2512.22545.txt
- self-rewarding sequential monte carlo for masked diffusion language models | arXiv: 2602.01849 | 📄 ../paper_cache/NeurIPS2026/2602.01849.txt
- self-supervised keyframe discovery for horizon-invariant behavior cloning | arXiv: 2610.10857 | 📄 ../paper_cache/NeurIPS2026/2610.10857.txt
- semantic concept steering breaks the explanation drift loop in continual learnin | arXiv: 2610.33877 | 📄 ../paper_cache/NeurIPS2026/2610.33877.txt
- Semantic Motion Anchors: Bridging Motion and Meaning in Co-Speech Gestures | arXiv: 2605.30608
- semantic optimal transport for sparse autoencoder feature matching and circuit c | arXiv: 2605.28567 | 📄 ../paper_cache/NeurIPS2026/2605.28567.txt
- semantic search over 9 million mathematical theorems | arXiv: 2602.05216 | 📄 ../paper_cache/NeurIPS2026/2602.05216.txt
- semgeo-gen unsupervised generation of approximate cross-instance semantic-geomet | arXiv: 2610.32663 | 📄 ../paper_cache/NeurIPS2026/2610.32663.txt
- semiparametrically efficient inference for kernel measures of noise heterogeneit | arXiv: 2605.27526 | 📄 ../paper_cache/NeurIPS2026/2605.27526.txt
- semmsa latent semantic-aided robust multimodal sentiment analysis with incomplet | arXiv: 多模态VLM
- sense semantic neural speech synthesis from brain dynamics via spatial graph enc | arXiv: 2609.37601
- sensebench a benchmark for remote sensing low-level visual perception and descri | arXiv: 2605.10576 | 📄 ../paper_cache/NeurIPS2026/2605.10576.txt
- sentinel a multi-level formal framework for safety evaluation of foundation mode | arXiv: 2510.12985
- sequential probabilistic uncertainty estimation for parallel multi-agent reasoni | arXiv: 2610.08901 | 📄 ../paper_cache/NeurIPS2026/2610.08901.txt
- sequential solution concepts in cooperative games with generalized characteristi | arXiv: 2510.11255
- setcon towards open-ended referring segmentation via set-level concept predictio | arXiv: 2605.20110 | 📄 ../paper_cache/NeurIPS2026/2605.20110.txt
- sgd in multiclass logistic regression sequential learning and scaling laws | arXiv: 2609.07868 | 📄 ../paper_cache/NeurIPS2026/2609.07868.txt
- sgd provably prioritizes a shortcut spurious feature in the xor model | arXiv: 2606.30444 | 📄 ../paper_cache/NeurIPS2026/2606.30444.txt
- shared modular recurrence in contextual mdps for universal morphology control | arXiv: 2506.08630
- sharp capacity scaling of spectral optimizers in learning associative memory | arXiv: 2603.26554 | 📄 ../paper_cache/NeurIPS2026/2603.26554.txt
- sharp convergence and sample complexity of policy mirror descent for average-rew | arXiv: 2610.04117 | 📄 ../paper_cache/NeurIPS2026/2610.04117.txt
- sharp feature-learning transitions and bayes-optimal neural scaling laws in exte | arXiv: 2605.10395 | 📄 ../paper_cache/NeurIPS2026/2605.10395.txt
- sharpness of minima in deep matrix factorization | arXiv: 2509.25783
- sheafstain sheaf-theoretic schrödinger bridge for spatially and biologically coh | arXiv: 2606.11846
- short-context dominance how much local context natural language actually needs | arXiv: 2512.08082
- show me what you dont know efficient sampling from invariant sets for model vali | arXiv: 2603.21782 | 📄 ../paper_cache/NeurIPS2026/2603.21782.txt
- shred retain-set-free unlearning via self-distillation with logit demotion | arXiv: 2605.07482 | 📄 ../paper_cache/NeurIPS2026/2605.07482.txt
- sierpinskicam camera-controlled video retaking with sierpinski triangle pattern | arXiv: 2606.17310 | 📄 ../paper_cache/NeurIPS2026/2606.17310.txt
- sieve overcoming topological obstruction in equivariant self-supervised learning | arXiv: 2610.21087 | 📄 ../paper_cache/NeurIPS2026/2610.21087.txt
- sieves selective prediction generalizes through visual evidence scoring | arXiv: 2604.25855 | 📄 ../paper_cache/NeurIPS2026/2604.25855.txt
- sigma semantic-difference instruction-grounding mask annotator for text-driven i | arXiv: 2605.27924 | 📄 ../paper_cache/NeurIPS2026/2605.27924.txt
- signal-adaptive trust regions for gradient-free optimization of recurrent spikin | arXiv: 2601.21572 | 📄 ../paper_cache/NeurIPS2026/2601.21572.txt
- signature approach for contextual bandits with nonlinear and path-dependent rewa | arXiv: 2605.10313 | 📄 ../paper_cache/NeurIPS2026/2605.10313.txt
- signed-permutation coordinate transport for rmsnorm transformers | arXiv: 2606.31963 | 📄 ../paper_cache/NeurIPS2026/2606.31963.txt
- simple extensions of single-objective acquisition functions and hedge strategies | arXiv: 2609.31940
- simple knn-based outlier detection achieves robust clustering | arXiv: 2605.07130 | 📄 ../paper_cache/NeurIPS2026/2605.07130.txt
- simple projection-free algorithm for contextual recommendation with logarithmic | arXiv: 2603.20826 | 📄 ../paper_cache/NeurIPS2026/2603.20826.txt
- simple yet effective semi-supervised knowledge distillation from vision-language | arXiv: 2505.07675
- simpleevol an agent-loop framework for llm-driven automated heuristic design wit | arXiv: 2609.37172
- simplexuq an evaluation framework and benchmark for conformal uncertainty on sim | arXiv: 2610.00523 | 📄 ../paper_cache/NeurIPS2026/2610.00523.txt
- SimpliHuMoN: Simplifying Human Motion Prediction | arXiv: 2603.04399
- simreg achieving higher performance in the pretraining via embedding similarity | arXiv: 2605.08809 | 📄 ../paper_cache/NeurIPS2026/2605.08809.txt
- simsd simple speculative decoding in diffusion language models | arXiv: 2606.02544 | 📄 ../paper_cache/NeurIPS2026/2606.02544.txt
- simulating human memory with language models | arXiv: 2605.25680 | 📄 ../paper_cache/NeurIPS2026/2605.25680.txt
- simulation-informed diffusion for decentralized multi-robot motion planning | arXiv: 2605.27697 | 📄 ../paper_cache/NeurIPS2026/2605.27697.txt
- sink vs diagonal patterns as mechanisms for attention switch and oversmoothing p | arXiv: 2605.08453 | 📄 ../paper_cache/NeurIPS2026/2605.08453.txt
- sinkhorn based associative memory retrieval using spherical hellinger kantorovic | arXiv: 2603.20656 | 📄 ../paper_cache/NeurIPS2026/2603.20656.txt
- sketching the readout of large language models for scalable data attribution and | arXiv: 2604.16197 | 📄 ../paper_cache/NeurIPS2026/2604.16197.txt
- skillmaster toward autonomous skill mastery in llm agents | arXiv: 2605.08693 | 📄 ../paper_cache/NeurIPS2026/2605.08693.txt
- skillrl evolving agents via recursive skill-augmented reinforcement learning | arXiv: 2602.08234 | 📄 ../paper_cache/NeurIPS2026/2602.08234.txt
- skip the hessian keep the rates globalized semismooth newton with lazy hessian u | arXiv: 2602.08069 | 📄 ../paper_cache/NeurIPS2026/2602.08069.txt
- skip when to skip and when to refine for efficient robot manipulation | arXiv: 2605.15536 | 📄 ../paper_cache/NeurIPS2026/2605.15536.txt
- slaying a diverse and community-validated dataset of queer slang | arXiv: 2509.17449
- sldr defending against malicious fine-tuning via selective layers recovery and d | arXiv: 2610.10345 | 📄 ../paper_cache/NeurIPS2026/2610.10345.txt
- sliceworld a predictive and controllable world-state model for ct report generat | arXiv: 2605.24371 | 📄 ../paper_cache/NeurIPS2026/2605.24371.txt
- slimoo interpretable multi-objective evolutionary search for llm depth pruning | arXiv: 2610.27812
- SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks | arXiv: 2603.24755
- slope optimistic potential landscape shaping for model-based reinforcement learn | arXiv: 2602.03201 | 📄 ../paper_cache/NeurIPS2026/2602.03201.txt
- slowly annealed langevin dynamics theory and applications to training-free guide | arXiv: 2605.07950 | 📄 ../paper_cache/NeurIPS2026/2605.07950.txt
- sls-bench a benchmark for incident log summarization with synthetic observabilit | arXiv: 2610.16412 | 📄 ../paper_cache/NeurIPS2026/2610.16412.txt
- smart picks in the dark towards efficient rlvr for reasoning via tracing metacog | arXiv: 2606.04503 | 📄 ../paper_cache/NeurIPS2026/2606.04503.txt
- smile bridging continuous optimization and discrete symbolic recovery | arXiv: 2609.04639
- smmbench a benchmark for source-distributed multimodal agent memory | arXiv: 2605.15710 | 📄 ../paper_cache/NeurIPS2026/2605.15710.txt
- smog scalable meta-learning for multi-objective bayesian optimization | arXiv: 2601.22131 | 📄 ../paper_cache/NeurIPS2026/2601.22131.txt
- smooth partial lotteries for stable randomized selection | arXiv: 2605.20069 | 📄 ../paper_cache/NeurIPS2026/2605.20069.txt
- smooth piecewise cutting for neural operator to handle discontinuities and sharp | arXiv: 2605.19823 | 📄 ../paper_cache/NeurIPS2026/2605.19823.txt
- snapaudit active auditing of differentially private in-context learning via snap | arXiv: 2511.13502
- SOAR: Regression-based LiDAR Relocalization for UAVs | arXiv: 2602.13267
- social choice foundations for simulation-augmented generation | arXiv: 2609.38287
- socialdirector training-free social interaction control for multi-person video g | arXiv: 2605.10079 | 📄 ../paper_cache/NeurIPS2026/2605.10079.txt
- soft contamination means benchmarks test shallow generalization | arXiv: 2602.12413 | 📄 ../paper_cache/NeurIPS2026/2602.12413.txt
- soft forward-backward representations for zero-shot reinforcement learning with | arXiv: 2602.06769 | 📄 ../paper_cache/NeurIPS2026/2602.06769.txt
- soft geometric inductive bias for object centric dynamics | arXiv: 2512.15493
- soft geometric inductive bias for object centric dynamics | arXiv: 2512.15493
- sol-execbench speed-of-light benchmarking for real-world gpu kernels against har | arXiv: 2603.19173 | 📄 ../paper_cache/NeurIPS2026/2603.19173.txt
- solaris building a multiplayer video world model in minecraft | arXiv: 2602.22208 | 📄 ../paper_cache/NeurIPS2026/2602.22208.txt
- solver-aware decompositions for programming-by-example when dividing requires kn | arXiv: 2608.03461 | 📄 ../paper_cache/NeurIPS2026/2608.03461.txt
- solving every step is not enough milestone oracles reveal a composition gap in l | arXiv: 2609.32235
- SOPO: Socratic Guided Policy Optimization for Span-Level Hallucination Detection | arXiv: 2610.32212
- sort partition randomize optimal binary hypothesis testing under local different | arXiv: 2606.07443 | 📄 ../paper_cache/NeurIPS2026/2606.07443.txt
- sourcebench can ai answers reference quality web sources | arXiv: 2602.16942 | 📄 ../paper_cache/NeurIPS2026/2602.16942.txt
- sp2ec adaptive self-speculative decoding for vision-language models | arXiv: 2610.18735 | 📄 ../paper_cache/NeurIPS2026/2610.18735.txt
- sp3 spherical priors for plug-and-play restoration | arXiv: 2606.16396 | 📄 ../paper_cache/NeurIPS2026/2606.16396.txt
- spanuq span-level uncertainty quantification for large language model generation | arXiv: 2607.05721
- sparkle realizing lively instruction-guided video background replacement via dec | arXiv: 2605.06535 | 📄 ../paper_cache/NeurIPS2026/2605.06535.txt
- sparse attention as compact kernel regression | arXiv: 2601.22766 | 📄 ../paper_cache/NeurIPS2026/2601.22766.txt
- sparse delta memory scaling the state of linear rnns through sparsity | arXiv: 2607.07386 | 📄 ../paper_cache/NeurIPS2026/2607.07386.txt
- sparse koopman autoencoders identify local dynamical regimes in multibasin syste | arXiv: 2608.29057 | 📄 ../paper_cache/NeurIPS2026/2608.29057.txt
- sparse layers are critical to scaling looped language models | arXiv: 2605.09165 | 📄 ../paper_cache/NeurIPS2026/2605.09165.txt
- sparse sum-of-squares layers for certified learning | arXiv: 2610.34590 | 📄 ../paper_cache/NeurIPS2026/2610.34590.txt
- sparse video generation propels real-world beyond-the-view vision-language navig | arXiv: 2602.05827 | 📄 ../paper_cache/NeurIPS2026/2602.05827.txt
- sparsely-supervised data assimilation via physics-informed schrödinger bridge | arXiv: 2603.22319 | 📄 ../paper_cache/NeurIPS2026/2603.22319.txt
- spatialbench is your spatial foundation model an all-round player | arXiv: 2605.27367 | 📄 ../paper_cache/NeurIPS2026/2605.27367.txt
- spatialclaw rethinking action interface for agentic spatial reasoning | arXiv: 2606.13673 | 📄 ../paper_cache/NeurIPS2026/2606.13673.txt
- spatialepibench benchmarking spatial information and epidemic priors in forecast | arXiv: 2605.06530 | 📄 ../paper_cache/NeurIPS2026/2605.06530.txt
- spdebench an extensive benchmark for learning stochastic pdes | arXiv: 2505.18511
- specblock block-iterative speculative decoding with dynamic tree drafting | arXiv: 2605.07243 | 📄 ../paper_cache/NeurIPS2026/2605.07243.txt
- specdrop parameter-free category-conditioned routing for modular specialization | arXiv: 2608.04084
- speclor spectral lookahead rectification for motion-coherent text-to-video gener | arXiv: 2606.11969 | 📄 ../paper_cache/NeurIPS2026/2606.11969.txt
- Spectral Feedback for Test-Time Alignment of Protein Diffusion Models | arXiv: 2609.30456
- spectral geometry of attention from information routing to uncertainty | arXiv: 2610.06012 | 📄 ../paper_cache/NeurIPS2026/2610.06012.txt
- Spectral Graph Sparsification Preserves Representation Geometry in Graph Neural Networks | arXiv: 2605.01136
- spectral reversal counteracting singular value bias for graph prompting | arXiv: 2609.32143
- spectral transformer neural processes | arXiv: 2605.09498 | 📄 ../paper_cache/NeurIPS2026/2605.09498.txt
- spectral-sphere-constrained hyper-connections | arXiv: 预训练
- spectrum-adaptive generalization bounds for trained deep transformers | arXiv: 2605.07297 | 📄 ../paper_cache/NeurIPS2026/2605.07297.txt
- speeding up log-sum-exp kernel fusion at the memory wall integer arithmetic at t | arXiv: 2610.33647 | 📄 ../paper_cache/NeurIPS2026/2610.33647.txt
- spera spherical prior eeg foundation model with geometry- and frequency-aware la | arXiv: 2610.10571 | 📄 ../paper_cache/NeurIPS2026/2610.10571.txt
- spherevad training-free video anomaly detection via geodesic inference on the un | arXiv: 2605.08003 | 📄 ../paper_cache/NeurIPS2026/2605.08003.txt
- spherical flows for sampling categorical data | arXiv: 2605.05629 | 📄 ../paper_cache/NeurIPS2026/2605.05629.txt
- spherical interpolation for backward-compatible multimodal representations | arXiv: 多模态VLM
- spikessl a universal spike inference framework with dynamics-informed state-spac | arXiv: 2610.11456 | 📄 ../paper_cache/NeurIPS2026/2610.11456.txt
- spin-weighted spherical harmonics enable complete and scalable e3-equivariant ne | arXiv: 2607.01408 | 📄 ../paper_cache/NeurIPS2026/2607.01408.txt
- spiral self-evolving action-conditioned video generation via reflective planning | arXiv: 2603.08403 | 📄 ../paper_cache/NeurIPS2026/2603.08403.txt
- splatlab autonomous scientific discovery for 3dgs research | arXiv: 2610.30468
- split the differences pool the rest provably efficient multi-objective imitation | arXiv: 2605.12000 | 📄 ../paper_cache/NeurIPS2026/2605.12000.txt
- sponsored questions and how to auction them | arXiv: 2512.03975
- squeezing capacity from multimodal large language models for subject-driven gene | arXiv: 2605.26111 | 📄 ../paper_cache/NeurIPS2026/2605.26111.txt
- sr-grpo stable rank as an intrinsic geometric reward for large language model al | arXiv: 2512.02807
- sr-prominence a crowdsourced protocol and dataset suite for perceptually-weighte | arXiv: 2605.14847 | 📄 ../paper_cache/NeurIPS2026/2605.14847.txt
- ss3d end2end self-supervised 3d from web videos | arXiv: 2604.22686 | 📄 ../paper_cache/NeurIPS2026/2604.22686.txt
- ssr3d-llm structured spatial reasoning via latent steps for fine-grained groundi | arXiv: 2605.28490 | 📄 ../paper_cache/NeurIPS2026/2605.28490.txt
- ST-DiffEye: Diffusion-based Continuous Gaze Generation via Joint Scanpath-Trajectory Modeling | arXiv: 2606.15486
- stabilizing knowledge promoting reasoning dual-token constraints for rlvr | arXiv: 2507.15778
- stabilizing the dynamic low-rank training | arXiv: 2609.32615
- stable and scalable probabilistic numerical solvers for stiff and high-dimension | arXiv: 2606.08203 | 📄 ../paper_cache/NeurIPS2026/2606.08203.txt
- stable-worldmodel a platform for reproducible world modeling research and evalua | arXiv: 2605.21800 | 📄 ../paper_cache/NeurIPS2026/2605.21800.txt
- stablehand quality-aware flow matching for world-space dual-hand motion estimati | arXiv: 2605.18553 | 📄 ../paper_cache/NeurIPS2026/2605.18553.txt
- stablevq practical guidelines for stable vector-quantized tokenizer training | arXiv: 2609.26774 | 📄 ../paper_cache/NeurIPS2026/2609.26774.txt
- stage light is sequence2 multi-light control via imitation learning | arXiv: 2605.03660 | 📄 ../paper_cache/NeurIPS2026/2605.03660.txt
- stage-wise attention-guided region sequencing for adversarial attacks on large v | arXiv: 2602.04356 | 📄 ../paper_cache/NeurIPS2026/2602.04356.txt
- StaminaBench: Stress-Testing Coding Agents over 100 Interaction Turns | arXiv: 2606.19613
- standing on the shoulders of giants rethinking eeg foundation model pretraining | arXiv: 2603.04478 | 📄 ../paper_cache/NeurIPS2026/2603.04478.txt
- stapo stabilizing reinforcement learning for llms by silencing rare spurious tok | arXiv: 2602.15620 | 📄 ../paper_cache/NeurIPS2026/2602.15620.txt
- star boosting time series foundation models for anomaly detection through state- | arXiv: 2510.16014
- starflow2 bridging language models and normalizing flows for unified multimodal | arXiv: 2605.08029 | 📄 ../paper_cache/NeurIPS2026/2605.08029.txt
- starwm self-supervised trained attention routing for robust world models | arXiv: 2609.30667
- state-of-art minibatches via novel dpp kernels discretization wavelets and rough | arXiv: 2605.13127 | 📄 ../paper_cache/NeurIPS2026/2605.13127.txt
- statetree enhancing long-term dialogue reasoning via reinforcement learning | arXiv: 2609.38809 | 📄 ../paper_cache/NeurIPS2026/2609.38809.txt
- statistical convergence of spherical first hitting diffusion models | arXiv: 2605.07625 | 📄 ../paper_cache/NeurIPS2026/2605.07625.txt
- statistical matching via schrödinger bridge beyond conditional independence | arXiv: 2606.22770
- stay fair ensuring group fairness in diffusion models across guidance scales | arXiv: 2605.28036 | 📄 ../paper_cache/NeurIPS2026/2605.28036.txt
- steadythought mitigating llm under-thinking via thought-level preference optimiz | arXiv: 2610.25045 | 📄 ../paper_cache/NeurIPS2026/2610.25045.txt
- stealth apart harm together skill cascading attacks on skill-based agent systems | arXiv: 2609.30383
- stealthy world model manipulation via data poisoning | arXiv: 2606.18697 | 📄 ../paper_cache/NeurIPS2026/2606.18697.txt
- Steer-to-Detect: Probing Hidden Representations for Detection of LLM-Generated Texts | arXiv: 2605.12890
- steercast retrieval-based latent steering for decoder-only time series forecasti | arXiv: 2610.11229 | 📄 ../paper_cache/NeurIPS2026/2610.11229.txt
- steering away from memorization reachability-constrained reinforcement learning | arXiv: 2603.00140 | 📄 ../paper_cache/NeurIPS2026/2603.00140.txt
- steering externalities benign activation steering unintentionally increases jail | arXiv: 2602.04896 | 📄 ../paper_cache/NeurIPS2026/2602.04896.txt
- steering fields adaptive vector fields for safe image generation and beyond | arXiv: 2609.39573 | 📄 ../paper_cache/NeurIPS2026/2609.39573.txt
- steering frozen llms adaptive social alignment via online prompt routing | arXiv: 2603.15647
- steering visual generation in unified multimodal models with understanding super | arXiv: 2605.05781 | 📄 ../paper_cache/NeurIPS2026/2605.05781.txt
- steervte seamless video text editing with style and glyph control | arXiv: 2606.23254 | 📄 ../paper_cache/NeurIPS2026/2606.23254.txt
- stein kernelized molecular dynamics for active learning of interatomic potential | arXiv: 2606.04100 | 📄 ../paper_cache/NeurIPS2026/2606.04100.txt
- stembind when mllms get lost between rules and instances in abstract visual reas | arXiv: 2606.00148 | 📄 ../paper_cache/NeurIPS2026/2606.00148.txt
- step learning structured embeddings for progressive time series | arXiv: 2605.31061 | 📄 ../paper_cache/NeurIPS2026/2605.31061.txt
- StepCAD: Mesh-to-CAD Code Generation via LLM Policy and Geometry-Guided Search | arXiv: 2610.03799
- stochastic dynamic barrier perturbed gradient methods for nonconvex simple bilev | arXiv: 2607.10957 | 📄 ../paper_cache/NeurIPS2026/2607.10957.txt
- stochastic grouping conformal prediction for effective subgroup reliability | arXiv: 2610.11957 | 📄 ../paper_cache/NeurIPS2026/2610.11957.txt
- stochastic interpolants via conditional dependent coupling | arXiv: 2509.23122
- stochastic matching bandits with rare optimization updates | arXiv: 2509.04194
- stop the sampler classifier-based adaptive stopping for sampling kernels | arXiv: 2606.16073 | 📄 ../paper_cache/NeurIPS2026/2606.16073.txt
- strable benchmarking tabular machine learning with strings | arXiv: 2605.12292 | 📄 ../paper_cache/NeurIPS2026/2605.12292.txt
- STRAND: Sequence-Conditioned Transport for Single-Cell Perturbations | arXiv: 2602.10156
- strata incentivizing agentic reinforcement learning with strategic trajectory ab | arXiv: 2605.06642 | 📄 ../paper_cache/NeurIPS2026/2605.06642.txt
- strategic decision focused learning | arXiv: 2609.14907 | 📄 ../paper_cache/NeurIPS2026/2609.14907.txt
- strategic decision support for ai agents | arXiv: 2606.12587 | 📄 ../paper_cache/NeurIPS2026/2606.12587.txt
- stream stochastic riemannian flow matching with anisotropic decoder for digital | arXiv: 2606.07036 | 📄 ../paper_cache/NeurIPS2026/2606.07036.txt
- streamgaze gaze-guided temporal reasoning and proactive understanding in streami | arXiv: 2512.01707
- streamov streaming omni-video understanding via evidence-guided memory and respo | arXiv: 2605.25621 | 📄 ../paper_cache/NeurIPS2026/2605.25621.txt
- streamphy streaming inference of high-dimensional physical dynamics via state sp | arXiv: 2605.07384 | 📄 ../paper_cache/NeurIPS2026/2605.07384.txt
- strengthening llms for tabular prediction with structural priors | arXiv: 2510.17385
- stride automated evaluation of text-to-trajectory alignment across diverse conte | arXiv: 2609.34799
- strong stochastic flow maps | arXiv: 2606.01086 | 📄 ../paper_cache/NeurIPS2026/2606.01086.txt
- structural rationale distillation via reasoning space compression | arXiv: 2605.07139 | 📄 ../paper_cache/NeurIPS2026/2605.07139.txt
- structure over scale learning visual reasoning from pedagogical video | arXiv: 2601.23251 | 📄 ../paper_cache/NeurIPS2026/2601.23251.txt
- Structure-agnostic Causal Representation Learning | arXiv: 2610.00968
- structure-guided masked autoencoders for ultra-high resolution scientific image | arXiv: 2609.30682
- structured sparse memory for recurrent reasoning | arXiv: 2609.33270
- structured transforms for low-overhead quantization of language models | arXiv: 2609.11687 | 📄 ../paper_cache/NeurIPS2026/2609.11687.txt
- structured unitary tensor network representations for circuit-efficient quantum | arXiv: 2602.16266 | 📄 ../paper_cache/NeurIPS2026/2602.16266.txt
- structuring open-ended nas semi-automated design knowledge structuring with llms | arXiv: 2605.19247 | 📄 ../paper_cache/NeurIPS2026/2605.19247.txt
- stylestream 20 fast and controllable streaming voice style conversion | arXiv: 2610.28940
- sub-gaussian confidence intervals for heavy-tailed data characterizing the limit | arXiv: 2610.15799 | 📄 ../paper_cache/NeurIPS2026/2610.15799.txt
- subliminal learning as trait-direction drift a mechanism and targeted control un | arXiv: 2609.01091 | 📄 ../paper_cache/NeurIPS2026/2609.01091.txt
- subliminal learning is steering vector distillation | arXiv: 2606.00995 | 📄 ../paper_cache/NeurIPS2026/2606.00995.txt
- subliminal transfer of unsafe behaviors in ai agent distillation | arXiv: 2604.15559 | 📄 ../paper_cache/NeurIPS2026/2604.15559.txt
- sublinear time quantum sensitivity sampling | arXiv: 2509.16801
- submodular benchmark selection | arXiv: 2605.02209 | 📄 ../paper_cache/NeurIPS2026/2605.02209.txt
- sugar a scalable human-video-driven generalizable humanoid loco-manipulation lea | arXiv: 2605.20373 | 📄 ../paper_cache/NeurIPS2026/2605.20373.txt
- supervised distributional reduction via optimal transport and dependence maximiz | arXiv: 2605.27619 | 📄 ../paper_cache/NeurIPS2026/2605.27619.txt
- support before frequency in discrete diffusion | arXiv: 2605.13999 | 📄 ../paper_cache/NeurIPS2026/2605.13999.txt
- surgvista long-horizon surgical world modeling with plausible instrument-tissue | arXiv: 2606.19889 | 📄 ../paper_cache/NeurIPS2026/2606.19889.txt
- survivalpfn amortizing survival prediction via in-context bayesian inference | arXiv: 2605.15488 | 📄 ../paper_cache/NeurIPS2026/2605.15488.txt
- svot state-aware visualization-of-thought for spatial reasoning via reinforcemen | arXiv: 2606.11770 | 📄 ../paper_cache/NeurIPS2026/2606.11770.txt
- SWE Atlas: Benchmarking Coding Agents Beyond Issue Resolution | arXiv: 2605.08366
- SWE-Chain: Benchmarking Coding Agents on Chained Release-Level Package Upgrades | arXiv: 2605.14415
- swift sampling selecting temporal surprises via taylor series | arXiv: 2605.22678 | 📄 ../paper_cache/NeurIPS2026/2605.22678.txt
- swiftvlm efficient vision-language model inference via cross-layer token bypass | arXiv: 2602.03134 | 📄 ../paper_cache/NeurIPS2026/2602.03134.txt
- swimba switch mamba model scales state space models | arXiv: 2603.06938 | 📄 ../paper_cache/NeurIPS2026/2603.06938.txt
- symb-xmil symbolic explanations for multiple instance learning in digital pathol | arXiv: 2606.06224 | 📄 ../paper_cache/NeurIPS2026/2606.06224.txt
- symmetry guarantees statistic recovery in variational inference | arXiv: 2604.18310 | 📄 ../paper_cache/NeurIPS2026/2604.18310.txt
- symplectic neural operators for learning infinite dimensional hamiltonian system | arXiv: 2605.15881 | 📄 ../paper_cache/NeurIPS2026/2605.15881.txt
- synbench a benchmark for differentially private text generation | arXiv: 2509.14594
- synclight single-edit multi-view relighting | arXiv: 2601.16981 | 📄 ../paper_cache/NeurIPS2026/2601.16981.txt
- syndorbench evaluating lvlm perceptual robustness under physically constrained v | arXiv: 2609.31823 | 📄 ../paper_cache/NeurIPS2026/2609.31823.txt
- synib informational bottleneck for maximizing synergy in multimodal learning | arXiv: 2606.09853 | 📄 ../paper_cache/NeurIPS2026/2606.09853.txt
- synthesis through simulation generating coherent enterprise data via scalable ag | arXiv: 2610.10549 | 📄 ../paper_cache/NeurIPS2026/2610.10549.txt
- synthetic pre-pre-training improves language model robustness to noisy pre-train | arXiv: 2605.10129 | 📄 ../paper_cache/NeurIPS2026/2605.10129.txt
- synthetic worlds for temporal evaluation and knowledge updating in llms | arXiv: 2609.00184 | 📄 ../paper_cache/NeurIPS2026/2609.00184.txt
- synthforensics benchmarking and evaluating people-centric synthetic video deepfa | arXiv: 2602.04939 | 📄 ../paper_cache/NeurIPS2026/2602.04939.txt
- tabdlm free-form tabular data generation via joint numericallanguage diffusion | arXiv: 2602.22586 | 📄 ../paper_cache/NeurIPS2026/2602.22586.txt
- TAC: Timestamped Audio Captioning | arXiv: 2602.15766
- tackling the data-parallel load balancing bottleneck in llm serving practical on | arXiv: 2605.06113 | 📄 ../paper_cache/NeurIPS2026/2605.06113.txt
- TACT: Mitigating Overthinking and Overacting in Coding Agents via Activation Steering | arXiv: 2605.05980
- tactile mnist benchmarking active tactile perception | arXiv: 2506.06361
- tadpole autoencoders as foundation models for 3d pdes with online learning | arXiv: 2605.15284 | 📄 ../paper_cache/NeurIPS2026/2605.15284.txt
- tagbo llm-driven task-aware graph bayesian optimization for scientific discovery | arXiv: 2610.14626 | 📄 ../paper_cache/NeurIPS2026/2610.14626.txt
- tail competition explains scaling in best-of-n sampling for verifiable problems | arXiv: 2610.19362 | 📄 ../paper_cache/NeurIPS2026/2610.19362.txt
- tail cues principal corrections plug-and-play rectification for open-set test-ti | arXiv: 2610.36870 | 📄 ../paper_cache/NeurIPS2026/2610.36870.txt
- take it or leave it intent-controlled partial optimal transport | arXiv: 2605.20030 | 📄 ../paper_cache/NeurIPS2026/2605.20030.txt
- taking the road less scheduled with adaptive polyak steps | arXiv: 2511.07767
- tales text adventure learning environment suite | arXiv: 2504.14128
- talon confidence-aware speculative decoding with adaptive token trees | arXiv: 2601.07353 | 📄 ../paper_cache/NeurIPS2026/2601.07353.txt
- taming cot obfuscation in vlms from mechanistic evidence to activation-level enf | arXiv: 2609.24243 | 📄 ../paper_cache/NeurIPS2026/2609.24243.txt
- tapioca why task- aware pruning improves ood model capability | arXiv: 2605.14738 | 📄 ../paper_cache/NeurIPS2026/2605.14738.txt
- targeted review for ai-assisted biodiversity surveys active continuous-score occ | arXiv: 2609.25657 | 📄 ../paper_cache/NeurIPS2026/2609.25657.txt
- targeted synthetic control method | arXiv: 2602.04611 | 📄 ../paper_cache/NeurIPS2026/2602.04611.txt
- task-induced riemannian metrics for vision transformer feature spaces | arXiv: 2609.27988 | 📄 ../paper_cache/NeurIPS2026/2609.27988.txt
- taskground structured executable task inference for full-scene household reasoni | arXiv: 2605.18109 | 📄 ../paper_cache/NeurIPS2026/2605.18109.txt
- tastebench multimodal benchmark for sensory prediction from molecules to sustain | arXiv: 2610.02599 | 📄 ../paper_cache/NeurIPS2026/2610.02599.txt
- tatemae detecting alignment faking via tool selection in llms | arXiv: 2604.26511 | 📄 ../paper_cache/NeurIPS2026/2604.26511.txt
- teach-to-reason competition-guided reasoning with a self-improving teacher | arXiv: 2606.25407 | 📄 ../paper_cache/NeurIPS2026/2606.25407.txt
- teaching video generators to remember eliciting dynamic memory for out-of-sight | arXiv: 2605.25333
- ted text-axis evidence decomposition for prompted anomaly localization | arXiv: 2609.39033 | 📄 ../paper_cache/NeurIPS2026/2609.39033.txt
- televal a benchmark designed for spoken language models in chinese interactive s | arXiv: 2507.18061
- tempered guided diffusion | arXiv: 2605.03712 | 📄 ../paper_cache/NeurIPS2026/2605.03712.txt
- tempopfn synthetic pre-training of linear rnns for zero-shot time series forecas | arXiv: 2510.25502
- temporal alignment guidance on-manifold sampling in diffusion models | arXiv: 2510.11057
- temporal backtracking search for test-time generative video reasoning | arXiv: 2606.13861 | 📄 ../paper_cache/NeurIPS2026/2606.13861.txt
- temporal concentration from rollout errors implicit preference optimization for | arXiv: 2607.28058 | 📄 ../paper_cache/NeurIPS2026/2607.28058.txt
- temporal gradient inversion for private trajectory reconstruction in embodied re | arXiv: 2609.30258
- terravis towards evaluation of world-grounded visual consistency in text-to-imag | arXiv: 2610.02959 | 📄 ../paper_cache/NeurIPS2026/2610.02959.txt
- tessellations of semi-discrete flow matching | arXiv: 2605.07513 | 📄 ../paper_cache/NeurIPS2026/2605.07513.txt
- test time training enhances in-context learning of nonlinear functions | arXiv: 2509.25741
- test-time defense against adversarial attacks via stochastic resonance of latent | arXiv: 2510.03224
- test-time gradient guidance of flow policies in reinforcement learning | arXiv: 2606.11087 | 📄 ../paper_cache/NeurIPS2026/2606.11087.txt
- test-time personalization a diagnostic framework and probabilistic fix for scali | arXiv: 2605.10991 | 📄 ../paper_cache/NeurIPS2026/2605.10991.txt
- test-time scaling of diffusions with flow maps | arXiv: 2511.22688
- testable and actionable calibration for full swap regret | arXiv: 2605.17749 | 📄 ../paper_cache/NeurIPS2026/2605.17749.txt
- testable learning of general halfspaces under massart noise | arXiv: 2602.22300 | 📄 ../paper_cache/NeurIPS2026/2602.22300.txt
- text as partial constraint coreresidual alignment for robust visionlanguage lear | arXiv: 2607.03143 | 📄 ../paper_cache/NeurIPS2026/2607.03143.txt
- text-vision co-instructed image editing | arXiv: 2606.16767 | 📄 ../paper_cache/NeurIPS2026/2606.16767.txt
- textseal a localized llm watermark for provenance distillation protection | arXiv: 2605.12456 | 📄 ../paper_cache/NeurIPS2026/2605.12456.txt
- tgpo temporal grounded policy optimization for signal temporal logic tasks | arXiv: 2510.00225
- tgpo trace-guided policy optimization for robot task planning via verifiable sub | arXiv: 2602.12244 | 📄 ../paper_cache/NeurIPS2026/2602.12244.txt
- tgrl temperature-grouped reinforcement learning for efficient exploration in llm | arXiv: 2609.33589 | 📄 ../paper_cache/NeurIPS2026/2609.33589.txt
- the algorithm is not the behavior learned priors override look-ahead in a chess- | arXiv: 2508.21380
- the alignment illusion in multimodal large language models | arXiv: 2609.30210
- the attacker in the mirror breaking self-consistency in safety via anchored bipo | arXiv: 2605.08427 | 📄 ../paper_cache/NeurIPS2026/2605.08427.txt
- the batchnorm illusion diagnosing normalization artifacts in machine unlearning | arXiv: 2609.08901 | 📄 ../paper_cache/NeurIPS2026/2609.08901.txt
- the bayesian learning rule beyond kl geometry | arXiv: 2610.31308 | 📄 ../paper_cache/NeurIPS2026/2610.31308.txt
- the bayesian origin of the probability weighting function in human representatio | arXiv: 2510.04698
- the causal description gap information-theoretic separations across pearls hiera | arXiv: 2605.02177 | 📄 ../paper_cache/NeurIPS2026/2605.02177.txt
- the commit-abstain circuit why language models hallucinate instead of abstaining | arXiv: 2609.32964
- the complexity kink a prompt-side structural complexity index for code-generatio | arXiv: 2609.19616
- the constitutional coverage trilemma in ai governance | arXiv: 2609.01275 | 📄 ../paper_cache/NeurIPS2026/2609.01275.txt
- the curse of multiple mediators hidden interaction effects in activation patchin | arXiv: 2606.27510 | 📄 ../paper_cache/NeurIPS2026/2606.27510.txt
- the dormant spiking neuron a state-driven mechanism for efficient spiking neural | arXiv: 2610.21748 | 📄 ../paper_cache/NeurIPS2026/2610.21748.txt
- the dynamics of policy gradient in social dilemmas with partner selection | arXiv: 2605.18185 | 📄 ../paper_cache/NeurIPS2026/2605.18185.txt
- the era of agentic organization learning to organize with language models | arXiv: 2510.26658
- the expressivity boundary of probabilistic circuits a comparison with large lang | arXiv: 2605.12940 | 📄 ../paper_cache/NeurIPS2026/2605.12940.txt
- the future of facts tracing the factual generation-verification gap | arXiv: 2605.27564 | 📄 ../paper_cache/NeurIPS2026/2605.27564.txt
- the geometry of forgetting temporal knowledge drift as an independent axis in ll | arXiv: 2605.09195 | 📄 ../paper_cache/NeurIPS2026/2605.09195.txt
- the geometry of linear program compression an exact characterization and learnin | arXiv: 2605.25635 | 📄 ../paper_cache/NeurIPS2026/2605.25635.txt
- the geometry of noise why diffusion models dont need noise conditioning | arXiv: 2602.18428 | 📄 ../paper_cache/NeurIPS2026/2602.18428.txt
- the grounding gap how llms anchor the meaning of abstract concepts differently f | arXiv: 2605.08837 | 📄 ../paper_cache/NeurIPS2026/2605.08837.txt
- the hidden power of scaling factor in lora optimization | arXiv: 2606.12883 | 📄 ../paper_cache/NeurIPS2026/2606.12883.txt
- the implicit bias of hyperbolic representation learning for multiclass data a bu | arXiv: 2610.07131 | 📄 ../paper_cache/NeurIPS2026/2610.07131.txt
- the interplay of data structure and imbalance in the learning dynamics of diffus | arXiv: 2605.06367 | 📄 ../paper_cache/NeurIPS2026/2605.06367.txt
- the invisible hand of physics when video diffusion models know more than they sh | arXiv: 2606.05328 | 📄 ../paper_cache/NeurIPS2026/2606.05328.txt
- the limits of ai-driven allocation optimal screening under aleatoric uncertainty | arXiv: 2605.07979 | 📄 ../paper_cache/NeurIPS2026/2605.07979.txt
- the many faces of on-policy distillation pitfalls mechanisms and fixes | arXiv: 2605.11182 | 📄 ../paper_cache/NeurIPS2026/2605.11182.txt
- the master key hypothesis unlocking cross-model capability transfer via linear s | arXiv: 2604.06377 | 📄 ../paper_cache/NeurIPS2026/2604.06377.txt
- the override gap a magnitude account of knowledge conflict failure in hypernetwo | arXiv: 2604.23750 | 📄 ../paper_cache/NeurIPS2026/2604.23750.txt
- the panel complexity of sortition is 12 angry men enough | arXiv: 2504.20508
- the pareto frontier of randomized learning-augmented online bidding | arXiv: 2605.06106 | 📄 ../paper_cache/NeurIPS2026/2605.06106.txt
- the platonic defense backdoor defense for self-supervised encoders in the era of | arXiv: 2606.29451 | 📄 ../paper_cache/NeurIPS2026/2606.29451.txt
- the pokeagent challenge competitive and long-context learning at scale | arXiv: 2603.15563 | 📄 ../paper_cache/NeurIPS2026/2603.15563.txt
- the pokémon theorem and other fairness impossibility results | arXiv: 2605.09221
- the price of locality why forward-forward underperforms backpropagation | arXiv: 2609.33240
- the quantization benefits of residual-free transformers | arXiv: 2605.25880 | 📄 ../paper_cache/NeurIPS2026/2605.25880.txt
- the rate-distortion-polysemanticity tradeoff in saes | arXiv: 2605.14694 | 📄 ../paper_cache/NeurIPS2026/2605.14694.txt
- the reasoning boundary paradox how reinforcement learning constrains language mo | arXiv: 2510.02230
- the reflexivity threshold a phase transition for multi-agent performative predic | arXiv: 2610.29577
- the reward was in your data all along correcting flow matching with discriminato | arXiv: 2606.19162 | 📄 ../paper_cache/NeurIPS2026/2606.19162.txt
- the risk of kv cache compression | arXiv: 2607.01520 | 📄 ../paper_cache/NeurIPS2026/2607.01520.txt
- The Road Ahead in Autonomous Driving: The KITScenes Multimodal Dataset | arXiv: 2606.02956
- the sample complexity of multiple change point identification under bandit feedb | arXiv: 2605.13252
- the sampling complexity of condorcet winner identification in dueling bandits | arXiv: 2603.15189
- the score kalman filter | arXiv: 2605.16644 | 📄 ../paper_cache/NeurIPS2026/2605.16644.txt
- the shape of events edge-based inductive biases via cross-domain distillation | arXiv: 2609.30478
- the sharp directions are against you curvature analysis of activation steering | arXiv: 2610.16084 | 📄 ../paper_cache/NeurIPS2026/2610.16084.txt
- the silent hyperparameter quantifying the impact of inference backends on llm re | arXiv: 2605.19537 | 📄 ../paper_cache/NeurIPS2026/2605.19537.txt
- the spectral amplitude principle for dynamics of quantum neural networks | arXiv: 2409.06682
- the sublevel flood bifiltration towards scalable 2-parameter persistent homology | arXiv: 2610.05441 | 📄 ../paper_cache/NeurIPS2026/2610.05441.txt
- the superactivator mechanism transformers concentrate reliable concept signals i | arXiv: 2512.05038
- the surprising effectiveness of video diffusion models for hand motion reconstru | arXiv: 2606.30308 | 📄 ../paper_cache/NeurIPS2026/2606.30308.txt
- the two clocks and the innovation windowwhen and how generative models learn rul | arXiv: 2605.10019
- the unreasonable effectiveness of text embedding interpolation for continuous im | arXiv: 2603.17998 | 📄 ../paper_cache/NeurIPS2026/2603.17998.txt
- The World is Not Mono: Enabling Spatial Understanding in Large Audio-Language Models | arXiv: 2601.02954
- theia a multimodal dataset and benchmark for vision-language analysis of layout | arXiv: 2609.35035 | 📄 ../paper_cache/NeurIPS2026/2609.35035.txt
- theoretical guidelines for annealed langevin dynamics in compositional simulatio | arXiv: 2605.21253 | 📄 ../paper_cache/NeurIPS2026/2605.21253.txt
- theory guided and interpretable neural operator design for partial differential | arXiv: 2609.33715 | 📄 ../paper_cache/NeurIPS2026/2609.33715.txt
- theory of mind and persuasion beyond conversation assessing the capacity of llms | arXiv: 2606.31916 | 📄 ../paper_cache/NeurIPS2026/2606.31916.txt
- theory of optimal learning rate schedules and scaling laws for a random feature | arXiv: 2602.04774 | 📄 ../paper_cache/NeurIPS2026/2602.04774.txt
- theory on attention dynamics for out-of-distribution in-context learning | arXiv: 2609.36448 | 📄 ../paper_cache/NeurIPS2026/2609.36448.txt
- theory-scale auto-formalization of logics for computer science | arXiv: 2606.26525 | 📄 ../paper_cache/NeurIPS2026/2606.26525.txt
- therapygym evaluating and aligning clinical fidelity and safety in therapy chatb | arXiv: 2603.18008 | 📄 ../paper_cache/NeurIPS2026/2603.18008.txt
- think densely act sparsely latent expert cognitive chains for vision-language-ac | arXiv: 2610.25734 | 📄 ../paper_cache/NeurIPS2026/2610.25734.txt
- think plan paint layout-aware reasoning for controllable image generation in uni | arXiv: 2607.16409 | 📄 ../paper_cache/NeurIPS2026/2607.16409.txt
- think then score decoupled reasoning and scoring for video reward modeling | arXiv: 2605.05922 | 📄 ../paper_cache/NeurIPS2026/2605.05922.txt
- thinking in pictures a systematic benchmark for reasoning-driven image generatio | arXiv: 2609.02864 | 📄 ../paper_cache/NeurIPS2026/2609.02864.txt
- thinking with imagination agentic visual spatial reasoning with world simulators | arXiv: 2606.06476 | 📄 ../paper_cache/NeurIPS2026/2606.06476.txt
- thinkjepa empowering latent world models with large vision-language reasoning mo | arXiv: 2603.22281 | 📄 ../paper_cache/NeurIPS2026/2603.22281.txt
- thousandworlds a benchmark for climate emulation of potentially habitable exopla | arXiv: 2606.18338
- tic-grpo provable and efficient optimization for reinforcement learning from hum | arXiv: 2508.02833
- tiger-fg text-guided implicit fine-grained grounding for e-commerce retrieval | arXiv: 2605.18434 | 📄 ../paper_cache/NeurIPS2026/2605.18434.txt
- tight l infty sample complexity for low-degree and sparse boolean polynomials | arXiv: 2606.17319 | 📄 ../paper_cache/NeurIPS2026/2606.17319.txt
- time-sensitive anytime-valid testing | arXiv: 2605.06521 | 📄 ../paper_cache/NeurIPS2026/2605.06521.txt
- timees probabilistic and deterministic time series forecasting via evolutionary | arXiv: 2609.32384
- timetok granularity-controllable time-series generation via hierarchical tokeniz | arXiv: 2605.01418
- timewarp evaluating web agents by revisiting the past | arXiv: 2603.04949 | 📄 ../paper_cache/NeurIPS2026/2603.04949.txt
- tmpo trajectory matching policy optimization for diverse and efficient diffusion | arXiv: 2605.10983 | 📄 ../paper_cache/NeurIPS2026/2605.10983.txt
- to align or not to align check your compass before you train | arXiv: 2610.18638 | 📄 ../paper_cache/NeurIPS2026/2610.18638.txt
- to copy or not to copy controlling speculative decoding via intrinsic model sign | arXiv: 2609.20186 | 📄 ../paper_cache/NeurIPS2026/2609.20186.txt
- to discretize continually mean shift interacting particle systems for bayesian i | arXiv: 2605.14142 | 📄 ../paper_cache/NeurIPS2026/2605.14142.txt
- to trust or not to trust attention-based trust management for llm multi-agent sy | arXiv: 2506.02546
- token by token compromised backdoor vulnerabilities in unified autoregressive mo | arXiv: 2605.19227 | 📄 ../paper_cache/NeurIPS2026/2605.19227.txt
- token inflation how dishonest providers can overcharge for large language model | arXiv: 2605.30040 | 📄 ../paper_cache/NeurIPS2026/2605.30040.txt
- token time continuous diffusion for language modeling | arXiv: 2607.14106 | 📄 ../paper_cache/NeurIPS2026/2607.14106.txt
- tokenclip token-wise prompt learning for zero-shot anomaly detection | arXiv: 2510.21171
- tokenizer-generator coupling in medical image generation | arXiv: 2608.07713
- tokenrouter efficient serving system for token-level llm routing | arXiv: 2610.12242 | 📄 ../paper_cache/NeurIPS2026/2610.12242.txt
- tokens-per-parameter coverage is critical for robust llm scaling law extrapolati | arXiv: 2605.08541
- tool verification for test-time reinforcement learning | arXiv: 2603.02203 | 📄 ../paper_cache/NeurIPS2026/2603.02203.txt
- tools as continuous flow for evolving agentic reasoning | arXiv: 2605.07339 | 📄 ../paper_cache/NeurIPS2026/2605.07339.txt
- toolsearcher optimizing tool selection at scale via reinforcement learning | arXiv: 2609.30906
- TopoCurve: Geometry-Aware Topology Reasoning via Bézier Curves in Autonomous Driving | arXiv: 2610.09118
- topographrag-bench evaluating multimodal graphrag on layout-grounded evidence re | arXiv: 2610.09360 | 📄 ../paper_cache/NeurIPS2026/2610.09360.txt
- topological out-of-domain generalization in dynamical systems reconstruction | arXiv: 2606.22969 | 📄 ../paper_cache/NeurIPS2026/2606.22969.txt
- topology-aware representation alignment for semi-supervised vision-language lear | arXiv: 2604.26370 | 📄 ../paper_cache/NeurIPS2026/2604.26370.txt
- topoprune robust data pruning via unified latent space topology | arXiv: 2602.02739 | 📄 ../paper_cache/NeurIPS2026/2602.02739.txt
- torchumm a unified multimodal model codebase for evaluation analysis and post-tr | arXiv: 2604.10784 | 📄 ../paper_cache/NeurIPS2026/2604.10784.txt
- total variation distance estimation in autoregressive models | arXiv: 2607.19510 | 📄 ../paper_cache/NeurIPS2026/2607.19510.txt
- total variation rates for riemannian flow matching | arXiv: 2602.05174 | 📄 ../paper_cache/NeurIPS2026/2602.05174.txt
- touch-r1 reinforcing touch reasoning in mllms | arXiv: 2605.27154 | 📄 ../paper_cache/NeurIPS2026/2605.27154.txt
- Toward a Unified Statistical Theory of Unsupervised Pretraining and Supervised Neural Knowledge Graph Learning | arXiv: 2607.26346
- Toward Better Geometric Representations for Molecule Generative Models | arXiv: 2605.07693
- toward skill-native llms skill entropy for benchmarking and training long-horizo | arXiv: 2608.05139 | 📄 ../paper_cache/NeurIPS2026/2608.05139.txt
- toward the goldilocks blind compression of quantum states | arXiv: 2605.01258 | 📄 ../paper_cache/NeurIPS2026/2605.01258.txt
- towards anytime-valid statistical watermarking | arXiv: 2602.17608 | 📄 ../paper_cache/NeurIPS2026/2602.17608.txt
- towards characterizing scientific image utility and upgradability | arXiv: 2606.03401 | 📄 ../paper_cache/NeurIPS2026/2606.03401.txt
- towards complementary keypoint detection via mixture of detectors | arXiv: 2610.16762 | 📄 ../paper_cache/NeurIPS2026/2610.16762.txt
- towards differentially private reinforcement learning with general function appr | arXiv: 2605.07049 | 📄 ../paper_cache/NeurIPS2026/2605.07049.txt
- Towards Effective and Transferable Physical Camouflage against Multi-View BEV-based 3D Perception in Autonomous Driving | arXiv: 2610.32230
- towards error-free ehrs reasoning-intensive consistency verification between cli | arXiv: 2605.26463 | 📄 ../paper_cache/NeurIPS2026/2605.26463.txt
- towards explainable industrial anomaly detection via knowledge-guided latent rea | arXiv: 2602.09850 | 📄 ../paper_cache/NeurIPS2026/2602.09850.txt
- towards fairness under label bias in image segmentation impact measurement and m | arXiv: 2605.06891 | 📄 ../paper_cache/NeurIPS2026/2605.06891.txt
- towards generalizable 3d anomaly detection via relational inconsistency modeling | arXiv: 2609.35059
- towards high semantic fidelity hyperdimensional symbolic messages in multi-agent | arXiv: 2610.23092 | 📄 ../paper_cache/NeurIPS2026/2610.23092.txt
- towards hyperparameter transfer for differentially private optimization | arXiv: 2610.22976
- towards identifiable latent additive noise models | arXiv: 2403.15711
- towards instance-dependent regret optimality in episodic mdps with posterior sam | arXiv: 2610.26029 | 📄 ../paper_cache/NeurIPS2026/2610.26029.txt
- towards mitigating deceptive safety alignment in large reasoning models | arXiv: 2609.36254
- towards more general control of diffusion models using jeffrey guidance | arXiv: 2606.13240 | 📄 ../paper_cache/NeurIPS2026/2606.13240.txt
- towards on-policy data evolution for visual-native multimodal deep search agents | arXiv: 2605.10832 | 📄 ../paper_cache/NeurIPS2026/2605.10832.txt
- towards real-world human behavior simulation benchmarking large language models | arXiv: 2604.08362 | 📄 ../paper_cache/NeurIPS2026/2604.08362.txt
- towards reconstructing geographically diverse architecture with 3d foundation mo | arXiv: 2610.22514 | 📄 ../paper_cache/NeurIPS2026/2610.22514.txt
- towards reliable llm evaluation correcting the winners curse in adaptive benchma | arXiv: 2605.05973 | 📄 ../paper_cache/NeurIPS2026/2605.05973.txt
- towards scalable context-aware single-cell spatial transcriptomics prediction fr | arXiv: 2609.36429
- towards scalable data diversification for language model pretraining via leverag | arXiv: 2609.32484 | 📄 ../paper_cache/NeurIPS2026/2609.32484.txt
- towards understanding self-pretraining for sequence classification | arXiv: 2605.21070 | 📄 ../paper_cache/NeurIPS2026/2605.21070.txt
- towards understanding the power and limits of the muon optimizer a river-valley | arXiv: 2606.21514 | 📄 ../paper_cache/NeurIPS2026/2606.21514.txt
- towards unified dynamic face landmark detection | arXiv: 2608.10346
- towards visual query segmentation in the wild | arXiv: 2603.08898 | 📄 ../paper_cache/NeurIPS2026/2603.08898.txt
- tpo tri-level distributionally robust learning for ood direct preference optimiz | arXiv: 2610.28229
- trace data-free text reconstruction attacks against approximate unlearning in ll | arXiv: 2610.31995 | 📄 ../paper_cache/NeurIPS2026/2610.31995.txt
- trace structure-aware character encoding for robust and generalizable document w | arXiv: 2603.12873 | 📄 ../paper_cache/NeurIPS2026/2603.12873.txt
- trace tourism recommendation with accountable citation evidence | arXiv: 2605.07677 | 📄 ../paper_cache/NeurIPS2026/2605.07677.txt
- tracer verifiable generative provenance for multimodal tool-using agents | arXiv: 2605.09934 | 📄 ../paper_cache/NeurIPS2026/2605.09934.txt
- tracing agentic failure from the flow of success | arXiv: 2607.12747 | 📄 ../paper_cache/NeurIPS2026/2607.12747.txt
- tracingflow a simulation-free trajectory inference framework based on second-ord | arXiv: 2608.21070 | 📄 ../paper_cache/NeurIPS2026/2608.21070.txt
- traction action recognition with sparse trajectories | arXiv: 2606.03490 | 📄 ../paper_cache/NeurIPS2026/2606.03490.txt
- train the agent not the expert learning to harness heterogeneous experts for mul | arXiv: 2605.29894 | 📄 ../paper_cache/NeurIPS2026/2605.29894.txt
- training data attribution in diffusion models via mirrored unlearning and noise- | arXiv: 2605.17938 | 📄 ../paper_cache/NeurIPS2026/2605.17938.txt
- training language models to explain their own computations | arXiv: 2511.08579
- training optimal large diffusion language models | arXiv: 2510.03280 | 📄 ../paper_cache/NeurIPS2026/2510.03280.txt
- training optimal large diffusion language models quokka scaling law
- training transformers for kv-cache compressibility | arXiv: 2605.05971 | 📄 ../paper_cache/NeurIPS2026/2605.05971.txt
- training with swap regret loss in a single-layer self-attention model a case stu | arXiv: 2607.23333 | 📄 ../paper_cache/NeurIPS2026/2607.23333.txt
- training-free cultural alignment of large language models via persona disagreeme | arXiv: 2605.10843 | 📄 ../paper_cache/NeurIPS2026/2605.10843.txt
- training-free task vectors for llm behavioral control | arXiv: 2609.09054 | 📄 ../paper_cache/NeurIPS2026/2609.09054.txt
- training-induced escape from token clustering in a mean-field formulation of tra | arXiv: 2605.07772 | 📄 ../paper_cache/NeurIPS2026/2605.07772.txt
- trajectory as the teacher few-step discrete flow matching via energy-navigated d | arXiv: 2605.07924 | 📄 ../paper_cache/NeurIPS2026/2605.07924.txt
- trajevolve trajectory evolution for reinforcement learning with hindsight credit | arXiv: 2610.28060
- Transcoda: End-to-End Zero-Shot Optical Music Recognition via Data-Centric Synthetic Training | arXiv: 2605.10835
- transcoder adapters for reasoning-model diffing | arXiv: 2602.20904 | 📄 ../paper_cache/NeurIPS2026/2602.20904.txt
- transfer learning of linear regression with multiple pretrained models benefitin | arXiv: 2602.16531 | 📄 ../paper_cache/NeurIPS2026/2602.16531.txt
- transferable scf-acceleration through solver-aligned initialization learning | arXiv: 2604.21657 | 📄 ../paper_cache/NeurIPS2026/2604.21657.txt
- transformers linearly represent highly structured world models | arXiv: 2605.18847 | 📄 ../paper_cache/NeurIPS2026/2605.18847.txt
- TransmissiveGS: Residual-Guided Disentangled Gaussian Splatting for Transmissive Scene Reconstruction and Rendering | arXiv: 2605.10705
- trapping attacker in dilemma examining internal correlations and external influe | arXiv: 2605.08278 | 📄 ../paper_cache/NeurIPS2026/2605.08278.txt
- treewalker partial evaluation for grouped tree-ensemble inference | arXiv: 2610.03939
- triage evaluating prospective metacognitive control in llms under resource const | arXiv: 2605.13414 | 📄 ../paper_cache/NeurIPS2026/2605.13414.txt
- trie-aware transformers for generative recommendation | arXiv: 2602.21677 | 📄 ../paper_cache/NeurIPS2026/2602.21677.txt
- trimming the long-tail of visual world modeling evaluation | arXiv: 2606.24256 | 📄 ../paper_cache/NeurIPS2026/2606.24256.txt
- triopose native triple-stream diffusion transformers for pose-guided text-to-ima | arXiv: 2606.07053 | 📄 ../paper_cache/NeurIPS2026/2606.07053.txt
- trl-bench standardizing cross-paradigm representation-level evaluation of tabula | arXiv: 2606.09323 | 📄 ../paper_cache/NeurIPS2026/2606.09323.txt
- trust guided decision transformer | arXiv: 2609.31586
- trustworthy retrosynthesis eliminating hallucinations with a diverse ensemble of | arXiv: 2510.10645
- truth as a compression artifact in language model training | arXiv: 2603.11749 | 📄 ../paper_cache/NeurIPS2026/2603.11749.txt
- truthful calibration errors for multi-class prediction | arXiv: 2510.06388
- ts-icl a flexible time-indexed foundation model for time series via in-context l | arXiv: 2606.05878 | 📄 ../paper_cache/NeurIPS2026/2606.05878.txt
- tstruct learning shared temporal structures for long-term time-series forecastin | arXiv: 2610.17864 | 📄 ../paper_cache/NeurIPS2026/2610.17864.txt
- tt-vidt decoupling the temporal axis for efficient motion-centric video pretrain | arXiv: 2609.33419
- tunable latent generative priors for compressed sensing and inverse problems | arXiv: 2603.07357 | 📄 ../paper_cache/NeurIPS2026/2603.07357.txt
- TurboVGGT: Fast Visual Geometry Reconstruction with Adaptive Alternating Attention | arXiv: 2605.14315
- two speeds of learning a representation-readout decomposition of grokking and do | arXiv: 2605.27078 | 📄 ../paper_cache/NeurIPS2026/2605.27078.txt
- two-fidelity best-action identification for stochastic minimax tree | arXiv: 2606.01708
- two-level softmax sampling done right correcting bias from size imbalance and di | arXiv: 2610.10483 | 📄 ../paper_cache/NeurIPS2026/2610.10483.txt
- tyche one step flow for efficient probabilistic weather forecasting | arXiv: 2605.06916 | 📄 ../paper_cache/NeurIPS2026/2605.06916.txt
- u-bench a comprehensive understanding of u-net through 100-variant benchmarking | arXiv: 2510.07041
- udt reconciling u-nets and diffusion transformers with data-adaptive token reduc | arXiv: 2608.01298 | 📄 ../paper_cache/NeurIPS2026/2608.01298.txt
- ultradifftransferring high-fidelity priors to compressed latent spaces for high- | arXiv: 2610.21202 | 📄 ../paper_cache/NeurIPS2026/2610.21202.txt
- uncertainty quantification for computer-use agents a benchmark across vision-lan | arXiv: 2606.25760
- uncertainty quantification for multimodal large language models with incoherence | arXiv: 2602.24195 | 📄 ../paper_cache/NeurIPS2026/2602.24195.txt
- uncovering and shaping the latent representation of 3d scene topology in vision- | arXiv: 2605.07148 | 📄 ../paper_cache/NeurIPS2026/2605.07148.txt
- understanding and mitigating under-confidence in gnns from the final layer | arXiv: 2505.11335
- understanding circulant permutation to extend the cminhash estimator | arXiv: 2610.18551 | 📄 ../paper_cache/NeurIPS2026/2610.18551.txt
- understanding gradient orthogonalization for deep learning via non-euclidean tru | arXiv: 2503.12645
- understanding the interplay between memorization and learning in large language | arXiv: 2507.14777
- UnfoldArt: Zero-Shot Recovery of Full Articulated 3D Objects from Text or Image | arXiv: 2606.30608
- UniCon3R: Unified Contact-aware 4D Human-Scene Reconstruction from Monocular Video | arXiv: 2604.19923
- unicustom unified visual conditioning for multi-reference image generation | arXiv: 2605.12088 | 📄 ../paper_cache/NeurIPS2026/2605.12088.txt
- unified noise steering for efficient human-guided vla adaptation | arXiv: 2605.10821 | 📄 ../paper_cache/NeurIPS2026/2605.10821.txt
- uniflow-audio unified flow matching for audio generation from omni-modalities | arXiv: 2509.24391
- uniform diffusion models revisited leave-one-out denoiser and absorbing state re | arXiv: 2605.22765 | 📄 ../paper_cache/NeurIPS2026/2605.22765.txt
- unifunc3d unified active spatial-temporal grounding for 3d affordance segmentati | arXiv: 2603.23478 | 📄 ../paper_cache/NeurIPS2026/2603.23478.txt
- unifying goal-conditioned rl and unsupervised skill learning via control-maximiz | arXiv: 2605.06145
- unigs unified geometry-aware gaussian splatting for multimodal rendering | arXiv: 2510.12174
- unipath adaptive coordination of understanding and generation for unified multim | arXiv: 2605.11400 | 📄 ../paper_cache/NeurIPS2026/2605.11400.txt
- unipro unified multi-mode medical image segmentation from 2d images to 3d volume | arXiv: 2610.06938 | 📄 ../paper_cache/NeurIPS2026/2610.06938.txt
- unirap towards unified part-level physical affordance reasoning and actionable p | arXiv: 2610.29768
- UniSHARP: Universal Sharp Monocular View Synthesis | arXiv: 2606.07514
- unit toward a unified physical language for human-to-humanoid policy learning an | arXiv: 2604.19734 | 📄 ../paper_cache/NeurIPS2026/2604.19734.txt
- universal approximation theorems for dynamical systems with infinite-time horizo | arXiv: 2602.08640 | 📄 ../paper_cache/NeurIPS2026/2602.08640.txt
- universal byte-level encoding utf-8utf-16 routing to reduce cross-script token-b | arXiv: 2610.01984 | 📄 ../paper_cache/NeurIPS2026/2610.01984.txt
- universal cross-prompt adversarial attacks on promptable concept segmentation | arXiv: 2609.39265
- UNIVERSE: Unified Video Action Models for Autonomous Driving with Flexible Mask-Modulated Modality Generation | arXiv: 2607.05133
- univl unified vision-language embedding for spatially grounded contextual image | arXiv: 2605.21611 | 📄 ../paper_cache/NeurIPS2026/2605.21611.txt
- unlearning that lasts utility-preserving robust and almost irreversible forgetti | arXiv: 2509.02820
- unlearningsoup is repeated tuning necessary for large language model unlearning | arXiv: 2609.37076
- unlocking compositional generalization in continual few-shot learning | arXiv: 2605.11710 | 📄 ../paper_cache/NeurIPS2026/2605.11710.txt
- unlocking the duality between flow and field matching | arXiv: 2602.02261
- unrestrained simplex denoising for discrete data a non-markovian approach applie | arXiv: 2603.28572
- unveiling implicit advantage symmetry why grpo struggles with exploration and di | arXiv: 2602.05548 | 📄 ../paper_cache/NeurIPS2026/2602.05548.txt
- Urbex: Agentic Spatial Grounding for City-Scale 3D Scenes | arXiv: 2610.18356
- URSA: Chemistry-Aware Benchmark for Utilitarian Retrosynthesis Assessment | arXiv: 2607.04688
- V2M-Zero: Zero-Pair Time-Aligned Video-to-Music Generation | arXiv: 2603.11042
- vace learning geometrically structured representations for time series anomaly d | arXiv: 2605.23504 | 📄 ../paper_cache/NeurIPS2026/2605.23504.txt
- validating causal abstraction metrics on simulated complex systems | arXiv: 2607.00267 | 📄 ../paper_cache/NeurIPS2026/2607.00267.txt
- value entanglement conflation between different kinds of good in some large lang | arXiv: 2602.19101 | 📄 ../paper_cache/NeurIPS2026/2602.19101.txt
- value-rectified distillation for flow-based offline reinforcement learning | arXiv: 2610.29075 | 📄 ../paper_cache/NeurIPS2026/2610.29075.txt
- variable-length generative protein design via generalized poisson flow | arXiv: 2607.09039
- variational trajectory optimization of anisotropic diffusion schedules | arXiv: 2602.19512 | 📄 ../paper_cache/NeurIPS2026/2602.19512.txt
- vehbench a stage-local diagnostic benchmark for llm-assisted vibration energy ha | arXiv: 2607.18181 | 📄 ../paper_cache/NeurIPS2026/2607.18181.txt
- velocity ambiguity profiles time-resolved bayes-risk diagnostics for flow matchi | arXiv: 2610.30107
- Veri-Sure: Multi-Agent RTL Code Generation with Temporal Tracing, Slicing and Formal Verification | arXiv: 2601.19747
- verification-aware training for speculative decoding | arXiv: 2608.30135 | 📄 ../paper_cache/NeurIPS2026/2608.30135.txt
- Verifiers in the Loop: Decoding Time Verification for Code Translation | arXiv: 2605.17626
- verifying neural networks with reinforcement learning | arXiv: 2609.34553
- verifymas hypothesis verification for failure attribution in llm multi-agent sys | arXiv: 2605.17467 | 📄 ../paper_cache/NeurIPS2026/2605.17467.txt
- veritrip a verifiable benchmark for travel planning agents over unstructured web | arXiv: 2605.28683 | 📄 ../paper_cache/NeurIPS2026/2605.28683.txt
- very fast bayesian additive regression trees on gpu | arXiv: 2410.23244
- VI-Bench: Benchmarking Prompt Inversion from AIGC Videos | arXiv: 2609.08079
- vico a training strategy towards semantic aware dynamic high-resolution | arXiv: 2510.12793
- vico visual environments co-evolving for vision-language model reasoning | arXiv: 2610.10782 | 📄 ../paper_cache/NeurIPS2026/2610.10782.txt
- vicor estimating visual necessity via counterfactual residuals for multimodal me | arXiv: 2610.25202 | 📄 ../paper_cache/NeurIPS2026/2610.25202.txt
- video-zero self-evolution video understanding | arXiv: 2605.14733 | 📄 ../paper_cache/NeurIPS2026/2605.14733.txt
- videoodyssey a benchmark for ultra-long-context and omni-modal video understandi | arXiv: 2605.22907 | 📄 ../paper_cache/NeurIPS2026/2605.22907.txt
- vidic video difference captioning | arXiv: 2512.03405
- vigor zero-shot visual generalization via latent-space consistency in model-base | arXiv: 2610.02801 | 📄 ../paper_cache/NeurIPS2026/2610.02801.txt
- vincie-next unlocking video editing from images via in-context modeling | arXiv: 2610.12104 | 📄 ../paper_cache/NeurIPS2026/2610.12104.txt
- viper an expert-curated benchmark for vision-language models in veterinary patho | arXiv: 2608.26382 | 📄 ../paper_cache/NeurIPS2026/2608.26382.txt
- visd enhancing video reasoning via structured self-distillation | arXiv: 2605.06094 | 📄 ../paper_cache/NeurIPS2026/2605.06094.txt
- vision token pruning via query-vision interaction decomposition | arXiv: 2610.33215 | 📄 ../paper_cache/NeurIPS2026/2610.33215.txt
- vistaqa benchmarking joint visual question answering and pixel-level evidence | arXiv: 2605.20676 | 📄 ../paper_cache/NeurIPS2026/2605.20676.txt
- visual enhanced depth scaling for multimodal latent reasoning | arXiv: 2604.10500 | 📄 ../paper_cache/NeurIPS2026/2604.10500.txt
- visual grounding first multimodal in-context learning follows | arXiv: 2610.30592 | 📄 ../paper_cache/NeurIPS2026/2610.30592.txt
- visual instruction tuning aligns modalities through abstraction | arXiv: 2606.03871 | 📄 ../paper_cache/NeurIPS2026/2606.03871.txt
- visual latents know more than they say unsilencing latent reasoning in mllms | arXiv: 2605.02735 | 📄 ../paper_cache/NeurIPS2026/2605.02735.txt
- visual text compression as measure transport | arXiv: 2605.06708 | 📄 ../paper_cache/NeurIPS2026/2605.06708.txt
- visual-advantage on-policy distillation for vision-language models | arXiv: 2605.21924 | 📄 ../paper_cache/NeurIPS2026/2605.21924.txt
- visual-erm reward modeling for visual equivalence | arXiv: 2603.13224 | 📄 ../paper_cache/NeurIPS2026/2603.13224.txt
- visual-redundancy-controlled parallel decoding for diffusion-based multimodal la | arXiv: 2605.25820 | 📄 ../paper_cache/NeurIPS2026/2605.25820.txt
- visualworldbench a fine-grained multi-task benchmark for evaluating visual world | arXiv: 2610.20083 | 📄 ../paper_cache/NeurIPS2026/2610.20083.txt
- vit-adala adapting vision transformers with linear attention | arXiv: 2603.16063 | 📄 ../paper_cache/NeurIPS2026/2603.16063.txt
- vitex-bench benchmarking high-fidelity video scene text editing | arXiv: 2609.40356
- viverra text-to-code with guarantees | arXiv: 2605.14972 | 📄 ../paper_cache/NeurIPS2026/2605.14972.txt
- vla-corrector lightweight detect-and-correct inference for adaptive action horiz | arXiv: 2607.01804 | 📄 ../paper_cache/NeurIPS2026/2607.01804.txt
- vla-pro cross-task procedural memory transfer for vision-language-action models | arXiv: 2605.29562 | 📄 ../paper_cache/NeurIPS2026/2605.29562.txt
- vla-replica a low-cost reproducible benchmark for real-world evaluation of visio | arXiv: 2605.20774 | 📄 ../paper_cache/NeurIPS2026/2605.20774.txt
- vlrs-bench a vision-language reasoning benchmark for remote sensing | arXiv: 2602.07045 | 📄 ../paper_cache/NeurIPS2026/2602.07045.txt
- VocalCoachBench: Benchmarking Audio-Language Models on Expert Feedback for Singing | arXiv: 2609.04241
- VocalGrad: Evaluating Acoustic Perception in Audio Language Models | arXiv: 2610.23745
- volco volumetric contact for high-fidelity human grasp generation | arXiv: 2610.10197 | 📄 ../paper_cache/NeurIPS2026/2610.10197.txt
- VolFill: Single-View Amodal 3D Scene Reconstruction with Volumetric Flow Matching | arXiv: 2605.31466
- voronoi-markov chain and spatial entropy for point pattern analysis | arXiv: 2609.36158 | 📄 ../paper_cache/NeurIPS2026/2609.36158.txt
- vtv-fm flow matching through variational terminal-velocity closure | arXiv: 2610.00785 | 📄 ../paper_cache/NeurIPS2026/2610.00785.txt
- wasd wasserstein-based knowledge distillation for large language models | arXiv: 2610.07706 | 📄 ../paper_cache/NeurIPS2026/2610.07706.txt
- wasp weakly aligned spatiotemporal pairs for fetal brain mri-ultrasound learning | arXiv: 2610.04601 | 📄 ../paper_cache/NeurIPS2026/2610.04601.txt
- wasserstein gradient flows and forward-only diffusion are not enough for multimo | arXiv: 2610.02081 | 📄 ../paper_cache/NeurIPS2026/2610.02081.txt
- wasserstein residuals learning gradient flows from population dynamics | arXiv: 2607.04738 | 📄 ../paper_cache/NeurIPS2026/2607.04738.txt
- watermarking should be treated as a monitoring primitive | arXiv: 2605.13095
- weather-robust cross-view geo-localization via prototype-based semantic part dis | arXiv: 2605.11654 | 📄 ../paper_cache/NeurIPS2026/2605.11654.txt
- webnavigator global web navigation via interaction graph retrieval | arXiv: 2603.20366 | 📄 ../paper_cache/NeurIPS2026/2603.20366.txt
- WebSpline: Structure-Informed Splines for Real-Time 3D Gaussians from Monocular Videos | arXiv: 2606.02096
- weighted conformal clustering | arXiv: 2606.00436 | 📄 ../paper_cache/NeurIPS2026/2606.00436.txt
- weisfeiler and leman follow the arrow of time expressive power of message passin | arXiv: 2505.24438
- welfare improvability and variance a principal-agent approach to optimal benchma | arXiv: 2605.30916 | 📄 ../paper_cache/NeurIPS2026/2605.30916.txt
- what are key factors for updates in rl for llm reasoning | arXiv: 2606.22570 | 📄 ../paper_cache/NeurIPS2026/2606.22570.txt
- what cohort inrs encode and where to freeze them | arXiv: 2605.08298 | 📄 ../paper_cache/NeurIPS2026/2605.08298.txt
- what comes next and why interpretable next-event prediction with neuro-symbolic | arXiv: 2610.31114
- what dna foundation models learn beyond sequence composition | arXiv: 2610.15711 | 📄 ../paper_cache/NeurIPS2026/2610.15711.txt
- what does a bayes-filtered transformer believe a predictive monte carlo approach | arXiv: 2607.17060 | 📄 ../paper_cache/NeurIPS2026/2607.17060.txt
- what drives test-time adaptation for clip a controlled empirical study from an u | arXiv: 2606.14299 | 📄 ../paper_cache/NeurIPS2026/2606.14299.txt
- what gets measured gets managed sign-aware recommendation needs sign-aware evalu | arXiv: 2609.33346 | 📄 ../paper_cache/NeurIPS2026/2609.33346.txt
- what if agents could imagine reinforcing open-vocabulary hoi comprehension throu | arXiv: 2602.11499 | 📄 ../paper_cache/NeurIPS2026/2602.11499.txt
- what is worth representing representational empowerment for continual model cons | arXiv: 2609.02322 | 📄 ../paper_cache/NeurIPS2026/2609.02322.txt
- what matters for diffusion-friendly latent manifold prior-aligned autoencoders f | arXiv: 2605.07915 | 📄 ../paper_cache/NeurIPS2026/2605.07915.txt
- what mllms learn about when they learn about multimodal reasoning | arXiv: 2510.01719
- what time is it how data geometry makes time conditioning optional for flow matc | arXiv: 2605.08344 | 📄 ../paper_cache/NeurIPS2026/2605.08344.txt
- what to forget in unlearning forget set curation for language models | arXiv: 2608.14855 | 📄 ../paper_cache/NeurIPS2026/2608.14855.txt
- what to remember what to reveal privacy-aware memory for conversational agents | arXiv: 2608.16551 | 📄 ../paper_cache/NeurIPS2026/2608.16551.txt
- whats holding back latent visual reasoning | arXiv: 2605.18445 | 📄 ../paper_cache/NeurIPS2026/2605.18445.txt
- when a zero-shooter cheats improving age estimation via activation steering | arXiv: 2605.17658 | 📄 ../paper_cache/NeurIPS2026/2605.17658.txt
- when and how much to imagine adaptive test-time scaling with world models for vi | arXiv: 2602.08236 | 📄 ../paper_cache/NeurIPS2026/2602.08236.txt
- when and how to canonize a generalization perspective | arXiv: 2605.11008 | 📄 ../paper_cache/NeurIPS2026/2605.11008.txt
- when and why adversarial training improves pinns a neural tangent kernel perspec | arXiv: 2605.15959 | 📄 ../paper_cache/NeurIPS2026/2605.15959.txt
- when and why signsgd outperforms sgd a theoretical study based on ell 1-norm low | arXiv: 2605.06615 | 📄 ../paper_cache/NeurIPS2026/2605.06615.txt
- when are multimodal predictions biologically supported a diagnostic evaluation f | arXiv: 2605.31504 | 📄 ../paper_cache/NeurIPS2026/2605.31504.txt
- when attention closes how llms lose the thread in multi-turn interaction | arXiv: 2605.12922 | 📄 ../paper_cache/NeurIPS2026/2605.12922.txt
- when can digital personas reliably approximate human survey findings | arXiv: 2605.10659 | 📄 ../paper_cache/NeurIPS2026/2605.10659.txt
- when copying is hard copy-constrained decoding for exact span reproduction | arXiv: 2610.28393 | 📄 ../paper_cache/NeurIPS2026/2610.28393.txt
- when debate helps proposal supply and verification-aware readout in multi-agent | arXiv: 2610.04686 | 📄 ../paper_cache/NeurIPS2026/2610.04686.txt
- when do prophets profit in prediction markets | arXiv: 2607.06166 | 📄 ../paper_cache/NeurIPS2026/2607.06166.txt
- when does lejepa learn a world model | arXiv: 2605.26379 | 📄 ../paper_cache/NeurIPS2026/2605.26379.txt
- when does trimming help conformal prediction a retained-law diagnostic under cal | arXiv: 2605.06204 | 📄 ../paper_cache/NeurIPS2026/2605.06204.txt
- when dynamics shift robust task inference wins offline imitation learning with b | arXiv: 2605.17017 | 📄 ../paper_cache/NeurIPS2026/2605.17017.txt
- when empathy misses the goal a benchmark for goal displacement in llm advice | arXiv: 2610.25522 | 📄 ../paper_cache/NeurIPS2026/2610.25522.txt
- when form changes but logic doesnt building logic-invariant llms through logical | arXiv: 2610.25402
- when helpfulness becomes sycophancy sycophancy is a boundary failure between soc | arXiv: 2605.05403 | 📄 ../paper_cache/NeurIPS2026/2605.05403.txt
- when is rank-1 steering cheap geometry granularity and budgeted search | arXiv: 2605.16362 | 📄 ../paper_cache/NeurIPS2026/2605.16362.txt
- when language overrules revealing text dominance in multimodal large language mo | arXiv: 2508.10552
- when latents forget pixels restoring fidelity in diffusion transformer super-res | arXiv: 2608.09133 | 📄 ../paper_cache/NeurIPS2026/2608.09133.txt
- when metropolis and hastings meet bradley and terry exact mcmc from preference v | arXiv: 2609.00905 | 📄 ../paper_cache/NeurIPS2026/2609.00905.txt
- when noise meets long-tail feature-threshold dual calibration for robust pseudo- | arXiv: 2609.33668
- when one leak pays forever context binding and the price of deterring collusion | arXiv: 2609.36667
- when policies cannot be retrained a unified closed-form view of post-training st | arXiv: 2604.22873 | 📄 ../paper_cache/NeurIPS2026/2604.22873.txt
- when policy entropy constraint fails preserving diversity in flow-based rlhf via | arXiv: 2605.12112 | 📄 ../paper_cache/NeurIPS2026/2605.12112.txt
- when reasoning meets its laws | arXiv: 2512.17901
- when riemann flows with wasserstein generative modeling of probability distribut | arXiv: 2609.25659 | 📄 ../paper_cache/NeurIPS2026/2609.25659.txt
- when should llms be less specific selective abstraction for reliable long-form t | arXiv: 2602.11908 | 📄 ../paper_cache/NeurIPS2026/2602.11908.txt
- when simulation lies a sim-to-real benchmark and domain-randomized rl recipe for | arXiv: 2605.11928 | 📄 ../paper_cache/NeurIPS2026/2605.11928.txt
- when stored evidence stops being usable scale-conditioned evaluation of agent me | arXiv: 2605.07313 | 📄 ../paper_cache/NeurIPS2026/2605.07313.txt
- when symbol names should not matter a logistic theory of fresh-symbol classifica | arXiv: 2605.07120 | 📄 ../paper_cache/NeurIPS2026/2605.07120.txt
- when to align when to predict a phase diagram for multimodal learning | arXiv: 2606.11190 | 📄 ../paper_cache/NeurIPS2026/2606.11190.txt
- where do long captions fail position-aware diagnosis and reinforcement learning | arXiv: 2610.31111
- where root cause analysis fails a retrieval-reranking decomposition | arXiv: 2609.36686
- where to look is not how to fix pre-denoising diagnostics and modality-dependent | arXiv: 2610.03068 | 📄 ../paper_cache/NeurIPS2026/2610.03068.txt
- where to look matters rethinking sub-volume sampling in 3d medical self-supervis | arXiv: 2610.13915 | 📄 ../paper_cache/NeurIPS2026/2610.13915.txt
- where what why and importance structured defect grounding for text-to-image feed | arXiv: 2606.06113 | 📄 ../paper_cache/NeurIPS2026/2606.06113.txt
- which tokens to merge diffusion dynamics for efficient image generation | arXiv: 2610.22370 | 📄 ../paper_cache/NeurIPS2026/2610.22370.txt
- which way did it move diagnosing and overcoming directional motion blindness in | arXiv: 2605.22823 | 📄 ../paper_cache/NeurIPS2026/2605.22823.txt
- who needs labels adapting vision foundation models with the metadata you already | arXiv: 2606.05107 | 📄 ../paper_cache/NeurIPS2026/2606.05107.txt
- who says what symbolic trimodal binding mechanisms in audio-visual llms | arXiv: 2609.31193
- whowhen pro can llms really attribute failures in ai agents | arXiv: 2607.09996 | 📄 ../paper_cache/NeurIPS2026/2607.09996.txt
- why are llms confidently wrong correcting overconfident errors via causal head i | arXiv: 2610.34994 | 📄 ../paper_cache/NeurIPS2026/2610.34994.txt
- why deterministic prm guidance underperforms in discrete diffusion reasoning | arXiv: 2609.35472
- why dit models underperform as representation learners without long skip connect | arXiv: 2610.13344 | 📄 ../paper_cache/NeurIPS2026/2610.13344.txt
- why do dit editors drift plug-and-play low frequency alignment in vae latent spa | arXiv: 2605.08250 | 📄 ../paper_cache/NeurIPS2026/2605.08250.txt
- why do time series models need long context windows | arXiv: 2606.01999 | 📄 ../paper_cache/NeurIPS2026/2606.01999.txt
- why geometric continuity emerges in deep neural networks residual connections an | arXiv: 2605.04971 | 📄 ../paper_cache/NeurIPS2026/2605.04971.txt
- why invariance is not enough for biomedical domain generalization and how to fix | arXiv: 2604.02564 | 📄 ../paper_cache/NeurIPS2026/2604.02564.txt
- why latent actions fail and how to prevent it | arXiv: 2605.20223 | 📄 ../paper_cache/NeurIPS2026/2605.20223.txt
- why muon outperforms adam a curvature perspective | arXiv: 2606.04662 | 📄 ../paper_cache/NeurIPS2026/2606.04662.txt
- why struggle with continuous latents interpretable discrete latent reasoning via | arXiv: 2606.29712 | 📄 ../paper_cache/NeurIPS2026/2606.29712.txt
- winning lottery tickets in neural networks via a quantum-inspired classical algo | arXiv: 2605.13979 | 📄 ../paper_cache/NeurIPS2026/2605.13979.txt
- witeness overlap directional provenance inside open-weight model families | arXiv: 2609.31784
- within-model vs between-prompt variability in large language models for creative | arXiv: 2601.21339 | 📄 ../paper_cache/NeurIPS2026/2601.21339.txt
- words that make language models perceive | arXiv: 2510.02425
- working with ai measuring the applicability of generative ai to occupations | arXiv: 2507.07935
- workspace-bench 10 benchmarking ai agents on workspace tasks with large-scale fi | arXiv: 2605.03596 | 📄 ../paper_cache/NeurIPS2026/2605.03596.txt
- world models as adversaries multi-agent self-play fine-tuning for robust motion | arXiv: 2607.10630 | 📄 ../paper_cache/NeurIPS2026/2607.10630.txt
- world models as group actions | arXiv: 2605.24578 | 📄 ../paper_cache/NeurIPS2026/2605.24578.txt
- world motion models flexible sequence modeling of se3 trajectories | arXiv: 2610.01742 | 📄 ../paper_cache/NeurIPS2026/2610.01742.txt
- worldcoder-bench benchmarking physically grounded 3d world synthesis | arXiv: 2606.01869 | 📄 ../paper_cache/NeurIPS2026/2606.01869.txt
- worldmemarena evaluating multimodal agent memory through actionworld interaction | arXiv: 2605.29341 | 📄 ../paper_cache/NeurIPS2026/2605.29341.txt
- worldreasonbench human-aligned stress testing of video generators as future worl | arXiv: 2605.10434 | 📄 ../paper_cache/NeurIPS2026/2605.10434.txt
- worldspeech a multilingual speech corpus from around the world | arXiv: 2605.09167 | 📄 ../paper_cache/NeurIPS2026/2605.09167.txt
- worldsr harnessing world knowledge search for grounded image super-resolution | arXiv: 2610.28423
- worldvln autoregressive world action model for aerial vision-language navigation | arXiv: 2605.15964 | 📄 ../paper_cache/NeurIPS2026/2605.15964.txt
- wovenanchor matcher specialized intra- and inter-image context modeling for feat | arXiv: 2610.30799 | 📄 ../paper_cache/NeurIPS2026/2610.30799.txt
- X-AVDD: Cross-Attentive Audio-Visual Dataset Distillation | arXiv: 2610.13687
- x-palm paired multispectral-to-smartphone dataset for cross-domain palmprint aut | arXiv: 2606.08437 | 📄 ../paper_cache/NeurIPS2026/2606.08437.txt
- x2hdr hdr image generation in a perceptually uniform space | arXiv: 2602.04814 | 📄 ../paper_cache/NeurIPS2026/2602.04814.txt
- xdecomposer learning prior-free set decomposition for multiphase x-ray diffracti | arXiv: 2605.05866 | 📄 ../paper_cache/NeurIPS2026/2605.05866.txt
- xhc expanded hyper-connections | arXiv: 2607.14530 | 📄 ../paper_cache/NeurIPS2026/2607.14530.txt
- xl-safetybench a country-grounded cross-cultural benchmark for llm safety and cu | arXiv: 2605.05662 | 📄 ../paper_cache/NeurIPS2026/2605.05662.txt
- xvgae a hierarchical variational graph autoencoder for exchangeable graphs | arXiv: 2610.30815 | 📄 ../paper_cache/NeurIPS2026/2610.30815.txt
- you cant have it both ways concept entanglement limits diffusion model unlearnin | arXiv: 2609.34137 | 📄 ../paper_cache/NeurIPS2026/2609.34137.txt
- your benchmark is an empirical measure over difficulty | arXiv: 2610.29927
- your embedding model is smarter than you think | arXiv: 2605.24938 | 📄 ../paper_cache/NeurIPS2026/2605.24938.txt
- your language model is its own critic reinforcement learning with value estimati | arXiv: 2605.07579 | 📄 ../paper_cache/NeurIPS2026/2605.07579.txt
- your neighbors know leveraging local neighborhoods for backdoor detection in dec | arXiv: 2605.19969 | 📄 ../paper_cache/NeurIPS2026/2605.19969.txt
- your self-supervised projection head captures object co-occurrence statistics | arXiv: 2610.23915 | 📄 ../paper_cache/NeurIPS2026/2610.23915.txt
- your teacher cant help you here combating supervision fidelity decay in on-polic | arXiv: 2605.30833 | 📄 ../paper_cache/NeurIPS2026/2605.30833.txt
- z0-inf zeroth order approximation for data influence | arXiv: 2510.11832
- zeroth-order sharpness-aware learning with exponential tilting | arXiv: 2510.16157
- zeroth-order stackelberg control in combinatorial congestion games | arXiv: 2602.23277 | 📄 ../paper_cache/NeurIPS2026/2602.23277.txt
- zno stable rational neural operators in the z-domain for discrete-time dynamics | arXiv: 2605.02356 | 📄 ../paper_cache/NeurIPS2026/2605.02356.txt
- 分层保形分类利用类别层次结构构建紧致且具覆盖保证的预测集 hierarchical conformal classification | arXiv: 2508.13288
- 对齐归纳偏置以实现状态空间模型的数据高效泛化 aligning inductive bias for data-efficient generalization | arXiv: 2509.20789
- 记忆决定学习方向状态空间模型中基于梯度的优化理论 | arXiv: 2510.00563
- 𝑓-differential privacy filters validity and approximate solutions | arXiv: 2602.06756 | 📄 ../paper_cache/NeurIPS2026/2602.06756.txt