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]Sequential Behavioral Watermarking for LLM AgentsHyeseon An, Shinwoo Park, Dongsu Kim et al.4.33
[abs]Energy-Adaptive Equivariant State Space Models for Noise-Robust Protein Structure RepresentationZhongyue Zhang, Runze Ma, Yanjie Huang et al.4.33
[PDF]From Denoising to Refining: A Corrective Framework for Vision-Language Diffusion ModelYatai Ji, Teng Wang, Yuying Ge et al.4.33
[abs]MixUni: Joint Multi-Property Prediction for Chemical Mixtures with Physics-Informed HeadsQinan Huang, Weizhi Xue, Weizhou Wang et al.4.33
[PDF]Spectral Progressive Diffusion for Efficient Image and Video GenerationHoward Xiao, Brian Chao, Lior Yariv et al.4.33
[PDF]Teacher-Aware Evolution of Heuristic Programs from Learned Optimization PoliciesMinyu Chen, Song Qin, Ling-I Wu et al.4.33
[abs]Spark: Path-Aware Experiential Self-Evolution for VLMs Spatiotemporal ReasoningChengzhengxu Li, Xiaoming Liu, Zhaohan Zhang et al.4.33
[abs]Past as State, Present as Attention: Persistent-State Blockwise Flow Matching for Long-Horizon Co-Speech Motion GenerationYi Liu, Xiangyue Zhang, Jia Ma et al.4.33
[PDF]Global linear convergence of entropy-regularized softmax policy gradient beyond tabular MDPsZiyue Chen, David Siska, Lukasz Szpruch4.33
[abs]Do Graph Neural Networks Learn Generalizable Algorithms for Clustering Graphs?Mitchell Black, Sanjoy Dasgupta, Yusu Wang4.33
[abs]On Lipschitz Explosion in Deep Neural Networks with Normalization: Consequences for Optimization and RobustnessAshkan Soleymani, Reyhaneh Hosseinpourkhoshkbari, Hadi Daneshmand et al.4.33
[PDF]Measure Less, Know More: Self-Supervised Test-Time Feature AcquisitionEeshaan Jain, Linus Bleistein, Bart Deplancke et al.4.33
[PDF]Understanding Generalization through Decision Pattern ShiftHuiqi Deng, Yibo Li, Quanshi Zhang et al.4.33
[PDF]World Models as Adversaries: Multi-Agent Self-Play Fine-Tuning for Robust Motion PlanningTong Nie, Yuewen Mei, Junlin He et al.4.33
[abs]Flow-based Spectral Kernel Learning for Nonstationary AttentionZi Yang, Ying Li, Alejandro Lancho et al.4.33
[abs]Efficient Knowledge Transfer in Federated Bayesian Optimization through Neural Network SurrogatesAlexander Gräfe, Max van Gemmeren, Paul Brunzema et al.4.33
[abs]Mirror descent actor-critic methods for entropy regularised MDPs in general spaces: stability and convergenceDenis Zorba, David Siska, Lukasz Szpruch4.33
[abs]MemeEconomy : Do LLM Agents Trade Ethics for Survival?Syed Nazmus Sakib, Nafiul Haque, Ahnaf Manan et al.4.33
[abs]Towards Precise Knowledge Distillation for Large Language Models via Knowledge ProbingJiajun Liu, Yao He, Wenjun Ke et al.4.33
[abs]Tree-Sliced Orlicz Integral Probability MetricTuan Hoang, Trung-Khang Tran, Viet-Hoang Tran et al.4.33
[PDF]How Hard Is It for Message-Passing GNNs to Simulate One Weisfeiler-Lehman Color-Refinement Step?Guanyu Cui, Yuhe Guo, Zhewei Wei et al.4.33
[PDF]NEXUS: Neural Energy Fields for Physically Consistent Contact-Rich 3D Object DynamicsQizhen Ying, Guangming Wang, Yangchen Pan et al.4.33
[PDF]Online Min-Max Optimization: From Individual Regrets to Cumulative Saddle PointsAbhijeet Vyas, Brian Bullins4.33
[PDF]Generating in the Limit with Infinitely Many HallucinationsIrene Strauss, Alexandra Butoi, Ryan Cotterell4.33
[abs]Transfer Entropy as a Measure of Information Flow in VLMs and LLMsJessica E Liang, Jianbo Shi4.33
[abs]Escaping the Curse of Dimensionality in One‑Step Flow-Based Generative ModelsKonstantin Yakovlev4.33
[abs]PORT: Preference Optimization via Robust Token-Level ReweightingDing Zhu, Xiukun Wei, Tian Xie et al.4.33
[PDF]TokenCLIP: Token-wise Prompt Learning for Zero-shot Anomaly DetectionQihang Zhou, Bin-Bin Gao, Guansong Pang et al.4.33
[PDF]Latent Action Reparameterization for Efficient Agent InferenceWenhao Huang, Qingwen Zeng, Qiyue Chen et al.4.33
[abs]CoTs as Probabilistic Programs: A Programmatic View of Thinking Step-by-Step in Language ModelsKyle Richardson, Yu Feng, Poorva Garg et al.4.33
[abs]Adaptive Multi-view Graph Contrastive Learning via Fractional Continuous DynamicsYanan Zhao, Feng Ji, Jingyang Dai et al.4.33
[abs]Off-policy Learning with Excursion PoliciesJiamin He, Mark Rowland, Daniel (Zhaohan) Guo et al.4.33
[PDF]DARTS: Targeting Prognostic Covariates in Budget-Constrained Sequential ExperimentsKateryna Husar, Alexander Volfovsky4.33
[PDF]CLeaR: A Unified Framework for Resolving the Leakage–Degradation Dilemma in Style TransferTeng Zhou, Yunhao Chen4.33
[PDF]StateTree: Enhancing Long-term Dialogue Reasoning via Reinforcement LearningNaen Xu, Wanqing Cui, Yibo Hu et al.4.33
[abs]ProxySearch: Decoupled Inference-Time Scaling for Diffusion Models via Asymmetric Noise-Rank TransferSeungwook Kim, Jongmin Lee4.33
[PDF]Towards Direct Evaluation of Harness Optimizers via Priority RankingKai Ong, Minseok Kang, Dongwook Choi et al.4.33
[abs]Worst-Case Regret Bounds for Combinatorial Bandits with Ranking FeedbackCristiano Migali, Gianmarco Genalti, Alberto Maria Metelli et al.4.33
[abs]FerQ: Fermat Quotient Reformulation of High-Order Binary OptimizationPhuong Nam Nguyen, Seng Loke, Anil Prabhakar et al.4.33
[PDF]When is Warmstarting Effective for Scaling Language Models?Neeratyoy Mallik, Maciej Janowski, Johannes Hog et al.4.33
[abs]Semantic Residual: A Paired-Oracle Decomposition of LLM Multi-Agent Systems under Lossy ChannelsHaotong Sun, Hang Yang4.33
[abs]Towards Principled Efficient Rollout Allocation in Test-Time TrainingYoukang Wang, Jian Wang, Tianyi Zeng et al.4.33
[PDF]Learning CLI Agents with Structured Action Credit under Selective ObservationHaoyang Su, Ying Wen4.33
[abs]RGF: Recursive Generative Framework for the Edge-Cut Separable ProblemsBo Peng, Rongzhen Ye, Yaohua Li et al.4.33
1 If this project is interesting to you, reach out at [email protected].