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.
[PDF]Constrained Code Generation with Discrete DiffusionLize Shao, Michael Cardei, Zichen Xie et al.4.67
[PDF]Smooth Partial Lotteries for Stable Randomized SelectionAlexander Goldberg, Giulia Fanti, Nihar Shah4.67
[abs]Adaptive Joint Testing of Policies in Discounted Markov Decision ProcessesPo-An Wang, Kaito Ariu4.67
[abs]DynaProto: Dynamic Prototypical Contrast for Temporally Consistent Object-Centric LearningTianran Ouyang, Peiqin Xu, Xingping Dong et al.4.67
[abs]Loyalty Capture: Reporting Relationships and Structural Sycophancy in Frontier AI ModelsEric So, Alex Imas4.67
[abs]Noisy2Latent: Nonparametric Deconvolution and Denoising via Maximum Mean DiscrepancyRitwik Vashistha, Abhra Sarkar, Arya Farahi4.67
[abs]Heterogeneous Graph Federated Learning with Structure-Aware Data-Free DistillationLili Guo, Qi Li, Ruoyu Wang et al.4.67
[abs]FlashMask-3: Efficient and Expressive Mask-Aware Distributed AttentionGuoxia Wang, Qianyue He, Siming Wu et al.4.67
[PDF]Exploring Starts Are Not Enough: Counterexamples and a Fix for Monte Carlo Exploring StartsOctave Oliviers, Glenn Vinnicombe4.67
[abs]LADDERS: Length-Aware Data Distribution and Existing-Response Speculation for Fast RL Rollout GenerationShengpeng Yin, Hui-Ling Zhen, Xing Li et al.4.67
[PDF]Retrieve What’s Missing: Coverage-Maximizing Retrieval for Consistent Long Video GenerationMinseok Joo, Dogyun Park, Taehoon Lee et al.4.67
[abs]FILOsofer: A TEE-Shielded Model Partitioning Framework based on Fisher Information-Guided LoRA ObfuscationFan zhang, Ziqi Zhang, Hossein Khalili et al.4.67
[abs]Sub-Gaussian Confidence Intervals for Heavy-Tailed Data: Characterizing the Limits of InferenceIlyes Hammouda, Stanislav Minsker, Mohamed Ndaoud4.67
[abs]RAPDrive: Shared-Latent Hybrid Decoding for Reasoning and Planning in Autonomous DrivingYuheng Liu, Le Hui, Ziyue Zhu et al.4.67
[PDF]SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized PipeliningYifan Zhang, Zunhai Su, Shuhao Hu et al.4.67
[abs]Preferential dynamic modeling with forward-backward smoothingOmid G. Sani, Trisha Jha, Mohammad Hosseini et al.4.67
[abs]ProQuant: Progressive Quantization-aware Training for Edge MLLMsYufei Xue, Yushi Huang, Jiawei Shao et al.4.67
[abs]In-Context Learning Can Help Vision Language Models Overcome Training PriorKun Wang, Xindi Wu, Sanghyuk Chun et al.4.67
[PDF]When Is Rank-1 Steering Cheap? Geometry, Granularity, and Budgeted SearchJohn Robertson, Jianing Zhu, Haris Vikalo et al.4.67
[abs]Reformulate LLM Reinforcement Learning for Stable Training under Black-box DiscrepancyJiashun Liu, Runze Liu, Xu Wan et al.4.67
[abs]Rethinking Contrastive Targets in Radiology Language-Image PretrainingYunhe Gao, Ashwin Kumar, Jiaming Liu et al.4.67
[PDF]Test-Time Conditioning with Representation-Aligned Visual FeaturesNicolas Sereyjol-Garros, Ellington Kirby, Victor Letzelter et al.4.67
[abs]MiCo: Microstructure-Consistent Flow Matching for Diffusion MRI Angular Super-ResolutionZhixuan Zhou, Tingting Dan, Guorong Wu4.67
[PDF]Reject, Resample, Repeat: Understanding Parallel Reasoning in Language Model InferenceNoah Golowich, Fan Chen, Dhruv Rohatgi et al.4.67
[abs]A Generative Model of Contextual Integrity: Appropriate vs. Inappropriate Information SharingOmer Ebead, Juan Formanek, Joel Leibo4.67
[abs]RADIUM: RadioActive Decay of Image-Underlaid MarksMichel Meintz, Louis Kerner, Maitri V Shah et al.4.67
[abs]Multigroup Fairness and Omniprediction: Separations and EquivalencesSílvia Casacuberta, Parikshit Gopalan, Varun Kanade et al.4.67
[PDF]Online Learning on Hidden-Convex Losses via Algorithmic Equivalence: Optimal Regret, Geometric Barrier, and Bandit FeedbackAnas Barakat, Andreas Kontogiannis, Vasilis Pollatos et al.4.67
[abs]Conservatism Controllable Compositional Guidance for Offline Safe Reinforcement LearningRuiqi Xue, Shenghe Hu, Xin Gao et al.4.67
[PDF]MJ: Multi-turn LLM Jailbreaking via Decomposed Credit AssignmentJunyoung Park, Namgyu Park, Sechan Lee et al.4.67
[abs]Zero-Violation Regret for Cooperative Markov Games with Coupled Instantaneous Hard ConstraintsJialei Liu, Ming Shi4.67
[PDF]Amortized Linear-time Exact Shapley Value for Product-Kernel MethodsMajid Mohammadi, Siu Lun (Alan) Chau, Krikamol Muandet4.67
[abs]Latent Debate: A Surrogate Framework for Interpreting LLM Thinking towards Binary DecisionsLihu Chen, Xiang Yin, Francesca Toni4.67
[PDF]Simple Baselines are Competitive with Code EvolutionYonatan Gideoni, Sebastian Risi, Yarin Gal4.67
[abs]Tight Gap-Dependent Regret Bounds and Problem-Independent Bounds for Cost-aware Cascading BanditsYuji TAMAKOSHI, Shinji Ito4.67
[abs]Optimal Linear Regression Without a VarianceArtin Tajdini, Jasper C.H. Lee, Jonathan Scarlett et al.4.67
[abs]Learning to Undo: Transfer Reinforcement Learning under State Space TransformationsMridul Mahajan, Aldo Pacchiano, Xuezhou Zhang4.67
[PDF]Information-Theoretic Generalization Bounds for Sequential Decision MakingFutoshi Futami, Masahiro Fujisawa4.67
[abs]The Unembedding Bottleneck: A Mechanistic Analysis of Single Digit Counting in LLMsSatwik Sunnam, Raghav Magazine, Vatsalya Singh et al.4.67
[PDF]Robust Conditional Conformal Prediction via Branched Normalizing FlowRui Xu, Xingyuan Chen, Wenxing Huang et al.4.67
[PDF]Dyna-Style Safety Augmented Reinforcement Learning: Staying Safe in the Face of UncertaintyArtur Eisele, Bernd Frauenknecht, Friedrich Solowjow et al.4.67
[PDF]Optimal scaling laws in learning hierarchical multi-index modelsLeonardo Defilippis, Florent Krzakala, Bruno Loureiro et al.4.67
[PDF]Instance-Optimal Estimation with Multiple LLM Judges on a BudgetJunghyun Lee, Sanghwa Kim, Yassir Jedra et al.4.67
[abs]When Transcriptomic Foundation Models Scale: Domain-Focused Pretraining for Drug Development in Immunology and InflammationKarim El Kanbi, Yannis Cattan, Aziz Fouché et al.4.67
[PDF]KroQuant: Kronecker-Structured Block Transforms for Efficient Post-Training Quantization of Diffusion TransformersYann Bouquet, Alireza Khodamoradi, Kristof Denolf et al.4.67
[PDF]Closed Loop Dynamic Driving Data Mixture for Real-Synthetic Co-TrainingHongzhi Ruan, Pei Liu, Weiliang Ma et al.4.67
1 If this project is interesting to you, reach out at [email protected].