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]Saliency-Aware Multi-Route Thinking: Grounding and Reasoning on Vision-Language AgentsMingjia Shi, Yinhan He, Yaochen Zhu et al.3.67
[PDF]Training Transformers for KV-Cache CompressibilityYoav Gelberg, Yam Eitan, Michael Bronstein et al.3.67
[abs]Representing Part-Whole Hierarchy with Nested Neuronal CoherenceHao Zheng, Hui Lin, Rong Zhao3.67
[PDF]Untrusted Content Masking for Web Agents with Security GuaranteesKristina Nikolić, Egor Zverev, Javier Rando et al.3.67
[abs]IncAgg: Efficient Memory-Enhanced Graph Learning via Incremental AggregationXingyue Shi, Zhichao Hou, Jiahao Zhang et al.3.67
[PDF]CAM: Question Answering on Entity-Centric Videos with Continuous Extraction and Adaptive QueryingYizhou Tian, Zizhe Chen, Shiyuan Deng et al.3.67
[PDF]Conservative Continuous-Time Treatment OptimizationNora Schneider, Georg Manten, Niki Kilbertus3.67
[abs]Perturb, Repair, Verify: Self-Play Vision-Language Verifiers for Compositional UnderstandingZijun Huang, Yingjun Du, Cees Snoek3.67
[PDF]Natural Language Actor-Critic: Scalable Off-Policy Learning in Language SpaceJoey Hong, Kang Liu, Zhan Ling et al.3.67
[abs]Instability of Meta-Learning Intrinsic Rewards for Policy Gradient Reinforcement LearningDilith Jayakody, Domenic Rosati, Janarthanan Rajendran3.67
[PDF]A Communication-Theoretic Framework for LLM Agents: Cost-Aware Adaptive ReliabilityHamed Omidvar, Vahideh Akhlaghi3.67
[PDF]CausalTab: Pretraining Across Causal Environments for Tabular Causal DiscoveryZi-Rong Li, Si-Yang Liu, Tian-Zuo Wang et al.3.67
[PDF]LOTION: Smoothing the Optimization Landscape for Quantized TrainingMujin Kwun, Depen Morwani, Huangyuan Su et al.3.67
[PDF]Meta: Recursive Self-Improvement through Emergent DepthZae Myung Kim, Young-Jun Lee, Seungyeon Jwa et al.3.67
[abs]Adaptive-Margin Masking and Restoration for Balanced Multimodal LearningGuangbin Zhang, Zheyang Luo, Jiangming Liu3.67
[PDF]DetailAnywhere: Fashion Detail Generation via Cross-Modal Feature Alignment DistillationZijun Li, Yimin Zhou, Jia Sun et al.3.67
[abs]SARA: Step-Adaptive Rank Adjustment for Diffusion Inference AccelerationDongHoon Lim, Jinwoo Jung, Won-Gook Choi et al.3.67
[abs]The Quiet Prompt: Erasing Ineffable Styles from Diffusion Models via Concept Leakage-aware Negative GuidanceKiyun Park, Min Hee Cha, Hyeok Nam et al.3.67
[abs]When Safety Becomes An Outlier: Understanding the Retention of LLM Safety BehaviorsBinchi Zhang, Hadi Abdullah, Yiwei Cai et al.3.67
[PDF]ModelLens: Finding the Best for Your Task from Myriads of ModelsRui Cai, Wenjie Mo, Xiaofei Wen et al.3.67
[PDF]Progressive Residual Warmup for Language Model PretrainingTianhao Chen, Xin Xu, Lu Yin et al.3.67
[abs]C2FT: Enhancing Fine-Grained Perception in MLLMs via Confuse-then-Contrast Fine-TuningShaoxuan He, Benlei Cui, Shikai Qiu et al.3.67
[PDF]RAO-Nav: Probing Omni-Language Models for Zero-shot Semantic Audio-Visual NavigationQilang Ye, Meng Liu, Yu Zhou3.67
[abs]PreFT: Prefill-only finetuning for inference efficiencyAndrew Lanpouthakoun, Aryaman Arora, Zhengxuan Wu et al.3.67
[abs]ReFlex: Faithful Panorama Reconstruction from a Single Image with ReflectionsYikai Pan, Zhiyuan Zhou, Yuxiang Yan et al.3.67
[abs]Youdunit: Single-Call Counterfactual Necessity in Multi-Agent LLM SystemsMarissa Li, Stephanie Gao, Kenny Guo et al.3.67
[abs]SeaPilot: Mobile Agent with Self-refining Environment AlignmentZhigang Zuo, Senyao Li, Yufeng Jiang et al.3.67
[PDF]Extrapolative Weight Averaging Reveals Correctness–Efficiency Frontiers in Code RLKunhao Zheng, Juliette Decugis, Pierre Chambon et al.3.67
[abs]: A Unified Mechanism for Fine-Grained Part Localization and GenerationVaibhav Agrawal, Varghese P Kuruvilla, Harsh Rangwani et al.3.67
[abs]Speeding up Log-Sum-Exp: Kernel Fusion at the Memory Wall, Integer Arithmetic at the Compute WallLingyun Yao, Martin Andraud, Niki Loppi et al.3.67
[abs]Beyond the Grid: Continuous Dictionary Pursuit for Interpretable Signal DecompositionNick Janssen, Melanie Schaller, Bodo Rosenhahn3.67
[PDF]Fast and Accurate Probing of In-Training LLMs' Downstream PerformancesZhichen Liu, Tianle Lun, Zhibin Wen et al.3.67
[PDF]Training-Free Cultural Alignment of Large Language Models via Persona DisagreementDao S Minh, Trung-Kiet Huynh, Chi Nguyen Tran et al.3.67
[abs]Context-Aware Autoregressive Image Generation for Emerging Reasoning PropertiesJixuan Ying, Haoyu Liu, Timing Yang et al.3.67
[PDF]When the Merge Coefficient Stops Mattering: Proximity Regularized Merging for Continual LoRA AdaptationYixuan Liu, Yuhao Sun, Sen Song et al.3.67
[PDF]ForceFlow: Learning to Feel and Act via Contact-Driven Flow MatchingShuoheng Zhang, Yifu Yuan, Hongyao Tang et al.3.67
[PDF]DISTMOE: Rehearsal-free Routing in Mixture-of-Experts for Distributed Instruction TuningMainak Singha, Niccolò Biondi, Elisa Ricci et al.3.67
[PDF]CM2: Reinforcement Learning with Checklist Rewards for Multi-Turn and Multi-Step Agentic Tool UseZhen Zhang, Kaiqiang Song, Sean Wang et al.3.67
[PDF]Advancing Narrative Long Video Generation via Training-Free Identity-Aware MemoryJinzhuo Liu, Jiangning Zhang, Wencan Jiang et al.3.67
[abs]GeoReason: Bridging Logical Reasoning and Spatial Fidelity in Remote Sensing SegmentationCheng Fan, Han Wu, Tingzhang Luo et al.3.67
[abs]A Faster Algorithm for the Half-Trek Criterion in Structural Causal ModelsYasmine Briefs, Markus Bläser3.67
[abs]TIGER: Bridging the Multimodal Reasoning-Access Gap via Modality CounterfactualsGregory Kang Ruey Lau, Huynh Minh Nguyen, Bryan Kian Hsiang Low3.67
[abs]Pointillism: Probing-Based Model Compatibility for Robust Collaborative Machine LearningYang Li, Adams Wai Kin Kong3.67
1 If this project is interesting to you, reach out at [email protected].