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]BReD: Block Replay Dithering for Stable Low-Bit EMA Optimizer StatesHeshen Zhan, Youhan Huang, Yunke Peng et al.4.00
[abs]SimpleEvol: Efficient Intelligence Conversion via Less Human Prior in Automated Heuristic DesignJianghan Zhu, Cong Zhang, Rongjie Zhu et al.4.00
[PDF]Understanding Schedule-Free Methods in Nonconvex Optimization: Rate Guarantees and Escaping SaddlesJiseok Chae, Donghwan Kim4.00
[PDF]Mixture-of-Top- Attention: Efficient Attention as Scalable Fast WeightsQishuai Wen, Zhiyuan Huang, meng xianghan et al.4.00
[abs]Saddle-to-Saddle Dynamics in Self-Supervised Shortcut LearningJuhwan Kim, yoonsoo nam, Sungyoon Lee4.00
[PDF]RoboAlign-R1: Distilled Multimodal Reward Alignment for Robot Video World ModelsHao Wu, Yuqi Li, Yuan Gao et al.4.00
[PDF]RA-CFGCache: From Branch-Level Criteria to Guided-Risk Control under Classifier-Free GuidanceYiming Liu, Ben Wan, Hui Chen et al.4.00
[abs]Mode-Controlled Policy Optimization: A Geometry-Aware Recipe for LLM Post-TrainingZhenyu Sun, Dylan Hadfield-Menell, Weiguo Feng et al.4.00
[PDF]Wavelet Flow Matching for Multi-Scale Physics EmulationGabriele Accarino, Juan Nathaniel, Carla Roesch et al.4.00
[PDF]UnlearningSoup: Is Repeated Tuning Necessary for Large Language Model Unlearning?Puning Yang, Qizhou Wang, Junchi Yu et al.4.00
[abs]Semantic Priors Meet Statistical Evidence: Robust Forests for Few-Shot Tabular LearningXuanliang Zhang, Dingzirui Wang, Keyan Xu et al.4.00
[abs]From Document Layout to Causal Topology: An End-to-End Architecture for Temporal Causal ReasoningZhifeng Yang, Wei Luo, Yongjian Chen et al.4.00
[PDF]ScreenShot: A Foundation Model for Few-Shot Combination Drug ScreeningAntoine De mathelin, Christopher Tosh, Wesley Tansey4.00
[abs]EviSAM3: Evidence-Driven SAM3 for Referring Remote Sensing Image SegmentationYuhang Duan, Xiaoshuai Wu, Chengqi Zhang et al.4.00
[PDF]Diffusion Subgoal Planning for Long-Horizon Offline Goal-Conditioned Reinforcement LearningHengrui Zhang, Yuhu Cheng, C.L.Philip Chen et al.4.00
[abs]GAPS: Gradient-Aware Adaptation-Gap Scoring for Time-Series Anomaly Detection with Foundation ModelsJongwon Kim, Byunghun Song, Young Myoung Ko4.00
[abs]GoT: A Game-Theoretic Approach to the Game of Twenty QuestionsLangyuan Cui, Chun Kai Ling, Hwee Tou Ng4.00
[abs]Improving Context-Shift Robustness of Convolutional Networks via Context-Regularized Cross-EntropyJinen Setpal, Chaoyue Liu4.00
[abs]TopoScope: A Graph-Scoped LLM Agent for Printed Circuit Board Schematic DesignJiale Guo, Shiji Tong, Weihao Li et al.4.00
[abs]Efficient Multi-Source Prompt Adaptation for Cross-Domain Open-Vocabulary LearningXiaofan Que, Dingrong Wang, Daniel Krutz et al.4.00
[PDF]Baba in Wonderland: Online Self-Supervised Dynamics Discovery for Executable World ModelsSeungWon Seo, DongHeun Han, SeongRae Noh et al.4.00
[PDF]Mitigating Object Hallucination in Large Vision-Language Models via False Discovery Controlled Visual Data SplittingChang Liu, Yu Tian, Rui Xie4.00
[PDF]Understanding Goal Generalisation in Sequential Reinforcement LearningJason Brown, Edward Young4.00
[abs]Beyond Hard Negatives: Grounded Positive Supervision for Compositional CLIPHarsh Udai, Konda Reddy Mopuri, Vineeth N Balasubramanian4.00
[PDF]SnapAudit: Active Auditing of Differentially Private In-Context Learning via Snapshot-Based SimulationYuyang Xia, Ruixuan Liu, Li Xiong4.00
[abs]METAFORGET: Audit-Driven Update-Policy Learning for Reliable Language Model UnlearningPinlong Zhao, Xiaoling Zhou, Zhou Zhaoting et al.4.00
[PDF]PLANING: A Loosely Coupled Triangle-Gaussian Framework for Streaming 3D ReconstructionChangjian Jiang, Kerui Ren, Xudong Li et al.4.00
[PDF]Learning to Evolve Scenes: Reasoning about Human Activities with Scene GraphsFrancesca Pistilli, Simone Alberto Peirone, Giuseppe Averta4.00
[abs]Correction Space Steering for Hallucination Mitigation in Large Vision-Language ModelsSongbo Yang, Shuliang Liu, Sihang Jia et al.4.00
[abs]Online Bayesian Recalibration of Brain–Computer Interfaces with Language Model PotentialsNoah Cowan, Scott Linderman4.00
[PDF]An Empirical Study on Noisy Data and LLM Pretraining Loss DivergenceQizhen (Irene) Zhang, Ankush Garg, Jakob Foerster et al.4.00
[abs]Unifying Sparsity and Discreteness: One-Shot Pruning for Quantized LLMs via Discrete OptimizationHaozhen Zhang, Hanyuan Zheng, Teng Hou et al.4.00
[abs]Sparse Multimodal Switching State-Space Models for Regime-Dependent Neural Connectivity under Partial ObservationsRahul K Sharma, Feng Liu, Xiaochen Xian4.00
[abs]ENGINE: Endogenous Variational MultiScale Optimization for Zeroth-Order LLM Fine-TuningZhuoli Ouyang, Changxi Chi, Siyuan Li et al.4.00
[abs]MuEdit: An efficient multi-task editing method towards inter-domain knowledge conflictsSongshi Liang, Ting-En Lin, Zixuan Huang et al.4.00
[abs]TwinPrune: Density-Aware Two-Phase Token Pruning for Vision-Language ModelsKai Liu, Anqi Li, Junxian Li et al.4.00
[abs]SIRAS: Sibling-Relative Advantage Shaping for Reinforcement Learning from Verifiable RewardsZairun Yang, Jun Xu, Lei Liang et al.4.00
[abs]VAR-Q: Tuning-free KV Cache Quantization for Visual Autoregressive Image and Video GenerationBoxun Xu, Jiaji Lu, Yuxuan Yin et al.4.00
[PDF]TaskGround: Structured Executable Task Inference for Full-Scene Household ReasoningZhiYuan Feng, Yu Deng, Ruichuan An et al.4.00
[PDF]Just Ramp-Up: Debiasing Regression-based Estimator for A/B Tests under Network InterferenceQianyi Chen, Bo Li4.00
[PDF]Indications of Belief-Guided Agency and Meta-Cognitive Monitoring in Large Language ModelsNoam Steinmetz Yalon, Ariel Goldstein, Liad Mudrik et al.4.00
[PDF]Conditional misalignment: common interventions can hide emergent misalignment behind contextual triggersJan Dubiński, Jan Betley, Anna Sztyber-Betley et al.4.00
[abs]PhysFlow: Physics-Intrinsic Velocity Regularization for Motion-Intensive Video GenerationXianglong Guo, Chang Yu, Haobo Xu et al.4.00
[abs]Controlling Temporal Pseudo-Label Marginals for Stable Online Test-Time AdaptationRani Amar, Ofir Lindenbaum4.00
[abs]Cross-Architecture Transferability is Width-Confounded:Diagnosis and Subspace CorrectionQIN LIU, Chen Zhong, Fengshan Zhao4.00
1 If this project is interesting to you, reach out at [email protected].