NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of NeurIPS 2026
Abstract
The safe for work edition of acceptodds: the submissions, without the markets. Search them, browse them on a map laid out by what they are about, follow the ones you care about, keep reading lists with your group, and get recommendations from what you read. There are no odds, no bets and no reputation here. acceptodds is not affiliated with any organisation or institution. acceptodds is an open source project, open to contributions, at github.com/PotentialHedge/acceptodds-sfw.1 Follow for updates on X.
[abs]Synthesis Through Simulation: Generating Coherent Enterprise Data via Scalable Agent-System InteractionYipeng Li, Ashutosh Hathidara, Jane Lo et al.4.67
[abs]MMDiff: Multimodal Model Diffing for Feature Discovery and ControlLachin Naghashyar, Hunar Batra, Ashkan Khakzar et al.4.67
[abs]A Dual-Domain Vision Transformer with Spectral Positional BiasAbdulaziz Alshamsi, Abdulla Alghfeli, Chenghua Lin et al.4.67
[PDF]Missing data and cluster graphs: cluster-level missingness vs variable-level missingnessWillow J. Scott, Eugenio Valdano, Charles Assaad4.67
[PDF]SurvivalPFN: Amortizing Survival Prediction via In-Context Bayesian InferenceShi-ang Qi, Vahid Balazadeh Meresht, Michael Cooper et al.4.67
[abs]Feasible Policy Optimization for Safe Reinforcement LearningYujie Yang, Yuanxu Sun, Wenyu Li et al.4.67
[abs]Revisiting The Power of Closed-Form: Robust Deep Image Prototype Discovery via Scale MixturesZhikang Xu, Jiarui Xing, Jian Wang4.67
[abs]State-Action Selection in General Stochastic Games under Regularized Policy Gradient MethodsOmar Abbadi, Rida Laraki, Panayotis Mertikopoulos4.67
[abs]Implicit-Euler Value Iteration: Long-Horizon Planning via Stable Integration of the Bellman Residual FlowNimrod De La Vega, Amir-massoud Farahmand4.67
[PDF]Native Multi-Dimensional Subquadratic Operators via Input Dependent Long ConvolutionsDavid Wessels, FARHAD RAMEZANGHORBANI, David W Romero et al.4.67
[PDF]Reinforcement Learning for Exponential Utility: Algorithms and Convergence in Discounted MDPsGugan Chandrashekhar Mallika Thoppe, Prashanth L.A., Ankur Naskar et al.4.67
[PDF]On the Importance of Gating: Memorization vs. In-Context Learning in State Space ModelsWilliam Tong, Aryo Lotfi, Emmanuel Abbe et al.4.67
[PDF]Large Language Models Develop Belief State Geometry In-ContextDaniel Balcells, Andrew Jun Lee, Chirag Rastogi et al.4.67
[PDF]Trust Guided Decision TransformerChainesh Gautam, Raghuram Bharadwaj Diddigi, Chandramouli Kamanchi et al.4.67
[abs]Drifting Field Policy: Wasserstein Gradient Flow on Policy Space for Offline-to-Online RLJuil Koo, Mingue Park, Jiwon Choi et al.4.67
[PDF]OmniEgoCap: Camera-Agnostic Sequence-Level Egocentric Motion ReconstructionKyungwon Cho, Jeonghyeon Na, Hanbyul Joo4.67
[abs]Efficient Off-Policy RL for Video Generation via Forward-Consistent Reward MatchingHongzheng Yang, Mengyang LIU, Haoxuan Wu et al.4.67
[PDF]Neural Garbage Collection: Learning to Forget while Learning to ReasonMichael Li, Jubayer Ibn Hamid, Emily Fox et al.4.67
[PDF]Reinforcement Learning with Multi-Step Lookahead Information Via Adaptive BatchingNadav Merlis4.67
[PDF]Heterogeneous Judge-Aware Ranking with Sensitivity, Disagreement, and ConfidenceShibo Yu, Yingzhou Wang, Yan Chen et al.4.67
[abs]Amortized Bayesian Experimental Design with In-Context Knowledge ConditioningZhanghu Zhao, Daolang Huang, Xinyi Wen et al.4.67
[PDF]The Multiscale Single-Index Model: A Toy Model for Hierarchical Feature LearningGordon Dai, Joan Bruna4.67
[abs]What Makes Two States the Same? Value-Aware State Matching for Multi-Turn Agent Credit AssignmentYangyi Fang, Haolin Shi4.67
[PDF]Patch Rebirth: Fast and Transferable Model Inversion of Vision TransformersSeongsoo Heo, Dong-Wan Choi4.67
[abs]Demystifying Classifier-Free Guidance for Auto-Regressive Image GenerationZhiling Zhou, Jiachun Pan, Fengzhuo Zhang et al.4.67
[abs]Elastic Representations via Hyperbolic GeometryArjun Ramesh Kaushik, Rudrasis Chakraborty, Nalini Ratha et al.4.67
[PDF]SAFE-SVD: Sensitivity-Aware Fidelity-Enforcing SVD for Physics Foundation ModelsChengjie Hong, Feixiang He, Yiheng Zeng et al.4.67
[abs]Adversarial Group Fairness in Contextual Bandits: When Robust is Not FairRay Telikani, Jaber valizadeh, Amir H Gandomi et al.4.67
[abs]Sliced Wasserstein Meets Quantum Optics: Provable Wavefunctions Tomography with Scarce Noisy MeasurementsTakahiro Kajisa4.67
[abs]ResKV: Residual-based Channel-wise Unstructured Pruning for KV Cache CompressionYue Chen, Jinze Li, Dajiang Liu4.67
[PDF]Why Geometric Continuity Emerges in Deep Neural Networks: Residual Connections and Rotational Symmetry BreakingKyungwon Jeong, Won-Gi Paeng, Honggyo Suh4.67
[abs]DSAD: Dynamic Soft Anisotropic Diagrams for Reduced-Order Video RepresentationZhiyang Dou, Laki Iinbor, Wojciech Matusik4.67
[PDF]The Geometry of Alignment Collapse: When Fine-Tuning Breaks SafetyMax Springer, Chung Peng Lee, Bohdan Turbal et al.4.67
[abs]Sophon: A Procedural Diagnostic for Spatial Reasoning in Vision-Language ModelsZach Gazak, Ryan Swindle, Justin Fletcher4.67
[PDF]DAWN: Dependency-Aware Fast Inference for Diffusion LLMsLizhuo Luo, Zhuoran Shi, Jiajun Luo et al.4.67
[PDF]Sink vs. diagonal patterns as mechanisms for attention switch and oversmoothing preventionPeter Súkeník, Cristina Lopez Amado, Christoph Lampert et al.4.67
[abs]Designing Effective Monitor-Based Interventions for Mitigating Reward Hacking During RLAria Wong, Joshua Engels, Neel Nanda4.67
[PDF]The Design Space of Tri-Modal Masked Diffusion ModelsLouis Bethune, Victor Guilherme Turrisi da Costa, Bruno Mlodozeniec et al.4.67
[abs]DSSA: Dynamic Sparse Semantic Anchoring for Purifying Protective Perturbations against Diffusion ModelsWeiwei Tan, Rui Wang, Lihua Jing et al.4.67
[abs]Beyond Marginal Coverage: Efficient Localized Conformal Prediction via Residual Rank CalibrationXiangshi Li, Wenqing He4.67
[abs]Neural Expansion: A Unified Mechanism for How Deep Neural Network GeneralizeChashi Mahiul Islam, Samuel Jacob Chacko, Mao Nishino et al.4.67
[abs]Multiple Descent of Generalization Curve for Optimally Regularized Ridge RegressionMaxim Bochkov, Fedor Noskov4.67
[abs]Breaking Noise Shortcuts in Self-Supervised Learning via Noise-Aligned View GenerationOankar Patil, May Dongmei Wang4.67
[PDF]Do Latent-CoT Models Think Step-by-Step? A Mechanistic Study on Sequential Reasoning TasksJia Liang, Liangming Pan4.67
[abs]Less is More: Compact-Token Masked Feature Learning for Skeleton Representation LearningJeonghyeok Do, Yun Chen, Geunhyuk Youk et al.4.67
1 If this project is interesting to you, reach out at [email protected].