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]M: Reframing Training Measures for Discretized Physical SimulationsYuan Mei, Xingyu Song, Xiaowen Song et al.3.67
[PDF]MedExAgent: Training LLM Agents to Ask, Examine, and Diagnose in Noisy Clinical EnvironmentsYicheng Gao, Xiaolin Zhou, Yahan Li et al.3.67
[abs]Preventing Error Cascades in Long-Horizon Multimodal Agents with Edge-Reliability Graph MemorySaman Forouzandeh, Wei Peng, Xinghuo Yu et al.3.67
[abs]Train at the Moving Edge: Rollout-Efficient RL for Large Reasoning ModelsJiahao Wu, Ning Lu, Shengcai Liu et al.3.67
[abs]HierFlow: Hierarchical Coupled Dual-Space Search for Automatic Agentic Workflow GenerationDong Li, Yanchi Liu, Xujiang Zhao et al.3.67
[abs]FoldAbS: Repurposing the Protein Folding Model as a Foundation Encoder for Antibody ScreeningJun Wu, FANDI WU, Xinyuan Zhu et al.3.67
[PDF]Efficient Reasoning via Constrained Optimization in Latent SpaceZhinan Hou, Xingchen Li, Keyou You3.67
[PDF]Hyper Hawkes Processes: Interpretable Models of Marked Temporal Point ProcessesAlex Boyd, andrew warrington, Taha Kass-Hout et al.3.67
[abs]ProtoVis-Nav: Prototypical Visual Imagination for Visual-Spatial Aligned UAV NavigationGuangyuan Sui, Yunzhong Hou, Chi Liu3.67
[abs]LocalAgent: Collaborative Agentic Verification for Fine-Grained Instance-Level Consistencyjiachen Guo, Xinshan Zhu, Boyun Wang et al.3.67
[PDF]A Scalable Multi-Task Model for Virtual SensorsLeon Götz, Lars Frederik Peiss, Erik Sauer et al.3.67
[abs]Stabilizing Off-policy LLM Optimization with Prefix Importance RatioShiye Lei, Zhihao Cheng, Dacheng Tao3.67
[abs]Control Under the Wrong Model Is Better Than Under the Correct OneFrancesco Damiani, Ruben Moreno Bote3.67
[abs]Module-Aware Optimization for Graph Neural NetworksGuy Hadad, Haggai Roitman, Moshe Eliasof et al.3.67
[PDF]Joint Learning of Hierarchical Neural Options and Abstract World ModelTop Piriyakulkij, Wolfgang Lehrach, Kevin Ellis et al.3.67
[abs]Rethinking Sequential Locate-Then-Edit: Optimality and StabilityBingqing Liu, Wei Liu, Zhiying Deng et al.3.67
[PDF]Beyond Appearance Shifts: Task-Semantic Action Calibration for VLA ModelsShuaijun Liu, Feiyang You, Chengyu Wu et al.3.67
[PDF]DPPE: Rethinking Camera-Based Positional Encoding for Scaling Multi-View TransformersShun Kenney, Teppei Suzuki3.67
[PDF]Teach-to-Reason: Competition-Guided Reasoning with a Self-Improving TeacherXiao Han, Hao Liu, Zhimin Bao et al.3.67
[abs]Example-Based Spatial Guidance for Training-Free Concept Erasure in Diffusion ModelsYounghwan Kil, Joonhyeong Park, Giung Nam et al.3.67
[abs]Rethinking Incompleteness: Formalizing Protocol Divergence and Train-Once Learning for Robust IMVCHAOLU LIU, XIYUE WANG, Xuanting Xie et al.3.67
[abs]Riemannian Optimization for Low-Rank Adaptation via DesingularizationTiancan Feng, Daorui Ding, Fanhua Shang et al.3.67
[PDF]HiPhy: Hierarchical Alignment for Physically-Plausible Multi-Principle Video GenerationTahira Kazimi, Shubhankar Borse, Munawar Hayat et al.3.67
[abs]TabWorld: A World-Modeling Foundation Model for Tabular GenerationXiaofeng Lin, Chunhe Wang, Tung Sum Thomas Kwok et al.3.67
[PDF]Diffusion-DRF: Free, Rich, and Differentiable Reward for Video Diffusion Fine-TuningYifan Wang, Yanyu Li, Guocheng Qian et al.3.67
[PDF]Visual Instruction Tuning Aligns Modalities through AbstractionLuis Palacios, Lorenzo Basile, Diego Doimo et al.3.67
[abs]Georeferenced Cross-View 3D Reconstruction from Ground and Satellite ImagesDavid G Shatwell, Mubarak Shah3.67
[abs]Distance-Dependent Connectivity Shapes Continual Learning by Synaptic-Resource-Delimited Separation of Neural DynamicsCHIU-CHANG CHENG, Ching-Lung Hsu, Ya-Ning Chang et al.3.67
[PDF]How to Instruct Your Robot: Dense Language Annotations Power Robot Policy LearningBosung Kim, Ruiyi Wang, David Acuna et al.3.67
[abs]Intent-Aware Caching for Efficient LLM ServingKazi Hasan Ibn Arif, JinYi Yoon, Dimitrios S Nikolopoulos et al.3.67
[abs]Multi-Scale Representation Learning for Single-Cell Multi-OmicsZhijie Zheng, Meng Lan, Fei Gu3.67
[PDF]Multivariate Time Series Forecasting needs Cross Variable LossKuiye Ding, Yifan Hu, Hanchen Wang et al.3.67
[PDF]Integrating Local and Global Entropy for Uncertainty Quantification in LLMsJohanne Medina, Tianyi Zhou, Keivin Isufaj et al.3.67
[abs]Trajectory Forcing: Exploiting Diffusion Trajectories for Autoregressive Long Video GenerationBohan Wang, Shuo Chen, Yunzhi Li et al.3.67
[abs]Tail Cues, Principal Corrections: Plug-and-Play Rectification for Open-Set Test-Time AdaptationYingkai Yang, Chaoqi Chen, Hui Huang3.67
[PDF]Forced Deferral: Manipulating Routing Decisions in Multimodal LLM CascadesZhongye Liu, Yaopei Zeng, Yurui Chang et al.3.67
[PDF]Credit Assignment with Resets in Language Model ReasoningAnkur Samanta, Akshayaa Magesh, Ayush Jain et al.3.67
[PDF]Maximin Robust Bayesian Experimental DesignHany Abdulsamad, Sahel Iqbal, Christian Andersson Naesseth et al.3.67
[PDF]Fisher Decorator: Refining Flow Policy via A Local Transport MapXiaoyuan Cheng, Haoyu Wang, Wenxuan Yuan et al.3.67
[abs]Trajectory Planning without Trajectory Data: A Manifold-Guided ApproachSilong Yong, Anji Liu, Cunxi Dai et al.3.67
[PDF]Multi-agent Collaboration with State ManagementMengyang Liu, Taozhi Chen, Zhenhua Xu et al.3.67
[abs]DUDS: Dual-stage Data Selection for Efficient Reinforcement Learning with Verifiable RewardsHongling Zheng, Li Shen, Zichuan Lin et al.3.67
[abs]Learning from Disagreement: Multi-Teacher Distillation for Chinese Spelling CorrectionHongcheng Ding, Xuanze Zhao, Ziping Hu et al.3.67
[PDF]Efficient Serving for Dynamic Agent Workflows with Prediction-based KV-Cache ManagementHaoyu Zheng, Fangcheng Fu, Jia Wu et al.3.67
[PDF]SePO: Self-Evolving Prompt Agent for System Prompt OptimizationWangcheng Tao, Han Wu, Weng-Fai Wong3.67
1 If this project is interesting to you, reach out at [email protected].