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]Back to Blackwell: Closing the Loop on Intransitivity in Multi-Objective Preference Fine-TuningJiahao Zhang, Lujing Zhang, Keltin Grimes et al.4.00
[PDF]Differentiable Bit-Widths: Co-optimizing Pruning and Quantization via SVD for Ultra-Efficient LLM CompressionHankyul Kang, Jongbin Ryu4.00
[abs]Confidence Estimation via Decoupled Smoothing for Dynamic LLM Routing and AggregationHao Luo, Ning Cheng, Yuhao Lin et al.4.00
[abs]Intervention-Guided Image-Free Classifier Expansion for Fine-Grained RecognitionXiangyu Wang, Changxin Rong, Yanze Gao et al.4.00
[PDF]Reasoning as Compression: Unifying Budget Forcing via the Conditional Information BottleneckFabio Valerio Massoli, Andrey Kuzmin, Arash Behboodi4.00
[abs]Rennala-NSGD: Asynchronous Stochastic Optimization Beyond Euclidean GeometryIgor Sokolov, Alexander Tyurin, Peter Richtarik4.00
[PDF]Missing Old Logits in Asynchronous Agentic RL: Semantic Mismatch and Repair Methods for Off-Policy CorrectionZhong Guan, Yongjian Guo, Haoran Sun et al.4.00
[abs]Disen-Forcing: Disentangling Semantic Anchoring from Motion for Autoregressive Video DiffusionZhengyang Yu, Akio Hayakawa, Masato Ishii et al.4.00
[PDF]Assessing Sample Quality in Conditional Generation under Compositional ShiftBerker Demirel, Valentino Maiorca, Marco Fumero et al.4.00
[PDF]Trust Region Continual Learning as an Implicit Meta-LearnerZekun Wang, Anant Gupta, Christopher MacLellan4.00
[abs]Approximate Memory Suffices for Universal Approximation with State Space ModelsYoshihiro Maruyama4.00
[abs]NitroBox: Lightning-Fast Sandbox for Large-Scale RL TrainingYuzhou Nie, Ruilin Zhou, Zhaorun Chen et al.4.00
[PDF]PithTrain: A Compact and Agent-Native MoE Training SystemRuihang Lai, Hao Kang, Haozhan Tang et al.4.00
[abs]Beyond Local Neighborhoods: Fractional Diffusion with Levy Flights on Simplicial Complexes for Link PredictionJaidev Goel, Yuzhou Chen, Konstantin Avrachenkov et al.4.00
[abs]Mutual Predictability Decomposition: Learning Interpretable Cross-Set Structure via Bi-Directional PredictionZixi Qin, Wanqing Li, Yuanhao Zhuo et al.4.00
[abs]VideoMaMa++: Temporally Consistent Video Matting via Preserve-and-Refine TokensSangbeom Lim, Seoung Wug Oh, Heeji Yoon et al.4.00
[PDF]dRAE: Representation Autoencoder with Hyper-Spherical CodesTianren Ma, Lin Long, Chuyan Chen et al.4.00
[PDF]DACA-GRPO: Denoising-Aware Credit Assignment for Reinforcement Learning in Diffusion Language ModelsAmin Karimi Monsefi, Dominic Culver, Nikhil Bhendawade et al.4.00
[abs]Logical Distillation of Transformer EncodersMatteo Forasassi, Thomas Gärtner, Thomas Lukasiewicz et al.4.00
[abs]Adaptive Test Case Discovery for LLM-Assisted Decision Making in High-Stakes DomainsAnjali Parashar, Carson Sobolewski, Yingke Li et al.4.00
[abs]Full Fine-Tuning Is Not the Problem: Why Adam Fails and SGD Succeeds in Few-Shot CLIP AdaptationNairouz Mrabah, Ismail Ayed, Eric Granger4.00
[abs]Self-Evolution Reasoner: Continuous Optimization via Policy-Intrinsic Exploration and ExploitationWenhang Shi, Yiren Chen, Zhe Zhao et al.4.00
[abs]TopoRefine: Plug-and-Play Topology-Aware Contour Refinement for Building SegmentationYunhui Zhu, Buliao Huang4.00
[abs]SuperSycophantic: Stress-Testing Frontier LLMs from Single- to Multi-Turn SycophancyTerry J. C. Zhang, Oscar S Yasunaga, Wenyuan Jiang et al.4.00
[abs]When LLM Routers Overpay: Strong-Model Over-Selection under Loose BudgetsGuannan Lai, Long Chen, Han-Jia Ye4.00
[abs]VideoSailor: Navigating Video Deep Research via Trajectory-to-Policy FlywheelMeng Cao, Pengfei Hu, Yingyao Wang et al.4.00
[abs]Tracing Psychometric Inference in Large Language ModelsChih-Hao Hsu, Feng-Chun B Chou, Pin-Hao A Chen4.00
[abs]A Structured LLM Framework for Inorganic Material Synthesis PlanningHeewoong Noh, Gyoung S. Na, Namkyeong Lee et al.4.00
[PDF]Adapting in the Dark: Efficient and Stable Test-Time Adaptation for Black-Box ModelsYunbei Zhang, Shuaicheng Niu, Chengyi Cai et al.4.00
[PDF]Capturing LLM Capabilities via Evidence-Calibrated Query ClusteringFangzhou Wu, Sandeep Silwal, Qiuyi (Richard) Zhang4.00
[PDF]What should post-training optimize? A test-time scaling law perspectiveMuheng Li, Jian Qian, Wenlong Mou4.00
[abs]DETS: An Interval-Censored Evidential Sampling Framework for Cross-Domain Scientific DiscoveryJiahang Shen, Hongxin Xiang, Wenjie Du4.00
[abs]Efficient Diffusion Policy Fine Tuning with Latent Noise Representation BridgingYuanchu Liang, Yue Yang, An-Chi He et al.4.00
[abs]VideoSleuth: A Narrative-Centric Agentic System with Video-Audio Native MLLM for Long-Form Video UnderstandingConglin Li, Yang Li, Qi Zhang et al.4.00
[PDF]NOFE – Neural Operator Function EmbeddingLars Uebbing, Harald Lykke Joakimsen, Siyan Chen et al.4.00
[PDF]Simulating Students or Sycophantic Problem Solving? On Misconception Faithfulness of LLM SimulatorsHeejin Do, Shashank Sonkar, Mrinmaya Sachan4.00
[PDF]PhyMotion: Structured 3D Motion Reward for Physics-Grounded Human Video GenerationYidong Huang, Zun Wang, Han Lin et al.4.00
[PDF]On the Complexity of Offline Reinforcement Learning with Q*-Approximation and Partial CoverageHaolin Liu, Braham Snyder, Chen-Yu Wei4.00
[abs]Learning When to Think: Dual-Reference Offline Optimization for Adaptive VLM ReasoningHongbin Lin, Sizhe Zou, Juangui Xu et al.4.00
[abs]Hider–Seeker Self-Play: Geometry-Verifiable Process Rewards for Long-Horizon Visual SearchYu Mao, Shengchao Chen4.00
[PDF]Winning Lottery Tickets in Neural Networks via a Quantum-Inspired Classical AlgorithmNatsuto Isogai, Hayata Yamasaki, Sho Sonoda et al.4.00
[abs]Boosting Multiagent Reinforcement Learning at High Replay Ratios with Ensemble ResetYaodong Yang, Hongyao Tang, Guangyong Chen et al.4.00
[abs]SCTI: Self-Calibrated Trident Identification of Black-Box LLM WatermarksZhixiong Nan, Haoyu Lu, Tao Xiang et al.4.00
[PDF]Logit-Contribution Scoring Identifies Non-Literal Retrieval HeadsAryo Gema, Beatrice Alex, Pasquale Minervini4.00
1 If this project is interesting to you, reach out at [email protected].