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]Few-Step Diffusion Language Models via Trajectory Self-DistillationTunyu Zhang, Xinxi Zhang, Ligong Han et al.4.33
[abs]Escaping Path Mirages in Offline Goal-Conditioned Reinforcement LearningSeungyul Han, Junhyeon Bae, Jaebak Hwang et al.4.33
[abs]AbSpecAlign: Specificity Reward Alignment for Antigen-Conditioned Antibody GenerationJingbo Zeng, Yang Xiao, Shenghua Gao4.33
[abs]HCInfer: An Efficient Inference System via Heterogeneous Error Compensation for Resource-Constrained DevicesShen Xu, Xiangwen Zhuge, Zhe Xu et al.4.33
[PDF]When Attention Closes: How LLMs Lose the Thread in Multi-Turn InteractionVardhan Dongre, Joseph Hsieh, Viet Lai et al.4.33
[abs]How New Strategies Emerge in RL Post-Training: A Controlled StudyAzwar Azwar, Nishil Patel, Andrew Saxe4.33
[PDF]A Principled Self-Referenced Early Stopping Approach for Deep Image PriorChaoyan Huang, Cheng-Han Huang, Ismail Alkhouri et al.4.33
[PDF]Structuring Open-Ended NAS: Semi-Automated Design Knowledge Structuring with LLMs for Efficient Neural Architecture SearchYuiko Sakuma, Masakazu Yoshimura, Marcel Gröpl et al.4.33
[abs]Spend Only What You Need: Defect-Aware Residual Coverage for Efficient Multi-Agent ReasoningMaisha Maliha, Dean F Hougen4.33
[abs]Concise Reasoning Through the Lens of Lagrangian OptimizationChengqian Gao, Haonan Li, Taylor Killian et al.4.33
[abs]ORCA: Orthogonal Residual Consensus Alignment for Multi-View ClusteringXiaojian Ding, Xian Li, Xiaoying Zhu et al.4.33
[PDF]WASP: Weakly Aligned Spatiotemporal Pairs for Fetal Brain MRI-Ultrasound LearningFrancesco Correnti, Gabriele Magrini, Marco Mistretta et al.4.33
[PDF]Imitation from Observations with Trajectory-Level Generative EmbeddingsYongtao Qu, Shangzhe Li, Weitong Zhang4.33
[PDF]MURPHY: Feedback-Aware GRPO with Retrospective Credit Assignment for Multi-Turn Code GenerationChanakya Ekbote, Vijay Lingam, Sujay Sanghavi et al.4.33
[PDF]SpatialVAM: Spatial-Aware Multi-View Video Diffusion as a Data-Efficient Robot PolicyPeiyan Li, Yixiang Chen, Yuan Xu et al.4.33
[PDF]In-Expectation Convergence of Stochastic Gradient Methods under Heavy-Tailed NoiseZijian Liu4.33
[abs]Pretraining Data Statistics Shape the Phases of Learning Entity Comparison in Language ModelsYik Siu Chan, Jing Huang, Yanai Elazar et al.4.33
[PDF]StableVQ: Practical Guidelines for Stable Vector-Quantized Tokenizer TrainingBao Tang, Jiahao Guo, Haoxiang Cao et al.4.33
[abs]A Differentiable Interior-Point Method in Single PrecisionJon Arrizabalaga, Kevin Tracy, Zac Manchester4.33
[PDF]Transferable SCF-Acceleration through Solver-Aligned Initialization LearningEike S. Eberhard, Viktor Kotsev, Timm Güthle et al.4.33
[PDF]The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement LearningJing Liang, Hongyao Tang, Yi Ma et al.4.33
[abs]Who Should Evolve? Uncertainty-Aware Role Bottleneck Inference for Multi-Agent LLM TrainingQiyu Qin, Yichen Li, Haozhao Wang et al.4.33
[abs]Learning Generative Dynamics for 3D Molecule Generation via Sequential Neuro-Symbolic ConstraintsZhuoran Li, Xu Sun, Chang Chen et al.4.33
[abs]FlowBatt: Flow Matching for Probabilistic Battery Degradation PredictionHamidreza Eivazi, Eslam Sharaawy, Stefan Wittek et al.4.33
[abs]Image Matting without Matting-Specific Annotations via Eikonal FieldsTao Huang, Yi Wang, Xiaohong Zhang et al.4.33
[PDF]Concepts Worth Having: Refining VLM-Guided Concept Bottleneck Models with Minimal AnnotationsNicola Debole, Stefano Teso, Andrea Passerini et al.4.33
[abs]DetectViT: Test-time Backdoor Detection for Vision Transformers via Inter-Head Attention DiscrepancySiquan Huang, Yijiang Li, Xingfu Yan et al.4.33
[abs]BootstrapAgent: Turning Repository Setup into Reusable Agent KnowledgeSihan Fu, Oucheng Liu, Shiyuan Wang et al.4.33
[PDF]ProCLIP: Progressive Vision-Language Alignment via LLM-based EmbedderXiaoxing Hu, Kaicheng Yang, Ziqi Ye et al.4.33
[abs]Emergent Steering Beyond Endpoint Alignment in Chemical Reaction ModelsYili Shen, Kehan Guo, Haomin Zhuang et al.4.33
[PDF]Mean Testing under Truncation beyond GaussianYuhao Wang, Roberto I Oliveira, Themis Gouleakis4.33
[PDF]Cornerstones or Stumbling Blocks? Deciphering the Rock Tokens in On-Policy DistillationYuxuan Jiang, Runchao Li, Shubhashis Roy Dipta et al.4.33
[abs]Not All Tokens Should Be Treated Equally: Context Credits ReassignmentShujian Gao, Yuan Wang, Jiamei Yan et al.4.33
[PDF]RotVLA: Rotational Latent Action for Vision-Language-Action ModelQiwei Li, Xicheng Gong, Xinghang Li et al.4.33
[abs]SimVLA: Attributing Gains in VLA Models Through Controlled AblationYuankai Luo, Woping Chen, Tong Liang et al.4.33
[abs]SIGA: Scientific Simulation Coding Agent Adapter- A Geophysics Case StudyMatthew Ho, Brian Z. Liu, Jixuan Chen et al.4.33
[abs]Learning Reusable Motor Motifs for Continuous Animal Behavior ModelingJiyi Wang, Jingyang Ke, Bo Dai et al.4.33
[PDF]Entropy-Gated Latent RecursionSoham Bhattacharjee, Dushyant Singh Chauhan, Salem Lahlou et al.4.33
[abs]Consistency-Verified Backdoor Defense for Federated Graph Learning via Cross-Layer DriftYanwen Jia, Yinuo Zhang, Zitong Shi et al.4.33
[abs]DropKV: Decoupling Residual-Output Perturbation for Near-Optimal KV-Cache EvictionAozhong Zhang, Selcuk Gurses, Yanxia Deng et al.4.33
[PDF]DecQ: Detail-Condensing Queries for Enhanced Reconstruction and Generation in Representation AutoencodersTianhang Wang, Yitong Chen, Wei Song et al.4.33
[abs]TargetSage: Identifying Therapeutic Target Genes with Interpretable and Robust LLM ReasoningZiheng Duan, Tong Wu, Xi Li et al.4.33
[PDF]APIVOT: Adaptive Planning with Interleaved Vision-Language ThoughtsEmily Jin, Joy Hsu, Yiqing Xu et al.4.33
[PDF]Fine-Tuning Improves Information Conveyance in Language ModelsYuwei Cheng, Weiyi Tian, Haifeng Xu4.33
[abs]AR-Edit: Training-Free Streaming Video Editing without InversionHovhannes Margaryan, Vicky Kalogeiton, Quentin Bammey et al.4.33
[abs]ReVMap: Vectorized Global Mapping via Connectivity-Aware Local Map FusionHongjae Shin, Jungho Kim, Donghyuk Kwak et al.4.33
1 If this project is interesting to you, reach out at [email protected].