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]What Was That Again? Certified Robustness for Automatic Speech RecognitionAndrew Cullen, Neil Marchant, Jiani Xie et al.4.33
[abs]Reinforcement learning enhanced flow matching for reference-based tumor generation on unpaired CT imagesXiaoxuan Gong, Zhilin Zheng, Tiancheng Lin et al.4.33
[PDF]Visual-Redundancy-Controlled Parallel Decoding for Diffusion-Based Multimodal Large Language ModelsYulin Yuan, Hongshuo Zhao, Xiangming Meng4.33
[PDF]Deep Probabilistic Supervision for Image ClassificationAnton Adelöw, Matteo Gamba, Atsuto Maki4.33
[abs]Axiomatic Reinforcement Learning for Open Multi-Agent Systems from Shapley AxiomsJianhong Wang, Yang Li, Samuel Kaski et al.4.33
[PDF]Direction-Aware Offline-to-Online Learning in Linear Contextual BanditsZean Han, Ruihan Lin, Zezhen Ding et al.4.33
[abs]Rethinking Bayesian Optimization for Co-Optimizing LLM Training ConfigurationsZhiliang Chen, Alfred Leong, Shao Yong Ong et al.4.33
[PDF]CRUMB: Efficient Prior Fitted Network Inference via Distributionally Matched Context BatchingJamie Heredge, Mattia Jacopo Villani, Pranav Deshpande et al.4.33
[PDF]Procedural Memory Distillation: Online Reflection for Self-Improving Language ModelsYe Liu, Srijan Bansal, Bo Pang et al.4.33
[PDF]Steering Fields: Adaptive Vector Fields for Safe Image Generation and BeyondSimone Facchiano, Jan Eric Lenssen, Bernt Schiele et al.4.33
[PDF]Routers Learn the Geometry of Their Experts: Geometric Coupling in Sparse Mixture-of-ExpertsSagi Ahrac, Noya Hochwald, Mor Geva4.33
[PDF]On the Overscaling Curse of Parallel Thinking: System Efficacy Contradicts Sample EfficiencyYiming Wang, Zhuosheng Zhang, Rui Wang4.33
[abs]Cross-User Poisoning: User-Task Boundary Failures in Multi-User Collaborative Language AgentsAtharv Singh Patlan, Peiyao Sheng, S Ashwin Hebbar et al.4.33
[PDF]Social Choice Foundations for Simulation-Augmented GenerationSonja Kraiczy, Smitha Milli, Ratip Emin Berker et al.4.33
[abs]Medical LLMs as Medical World Models: Unified Policy-Dynamics Learning with Test-Time SearchYucheng Zhou, Peng Luo, Jianbing Shen4.33
[PDF]Towards Anytime-Valid Statistical WatermarkingBaihe Huang, Eric Xu, Kannan Ramchandran et al.4.33
[PDF]Heterogeneous Agent Collaborative Reinforcement LearningZhixia Zhang, Zixuan Huang, Gonxun Li et al.4.33
[abs]Combating Catastrophic Forgetting in Continual Domain Adaptation via Knowledge RecastingZijie Liu, Zhen Tan, Charles Fleming et al.4.33
[abs]Discovering Phase Space Structure in Learned Hamiltonian SystemsJiayin Liu, Yulong Yang, Vineet Bansal et al.4.33
[PDF]Active Flow Expansion for Out-of-Distribution Discovery: from Theory to MoleculesRiccardo De Santi, Bruce D Lee, Cristian Jensen et al.4.33
[abs]A Theoretical Bridge Between Long-Tailed Recognition and Continual LearningMahdiyar Molahasani, Michael Greenspan, Ali Etemad4.33
[abs]RankVQ: Low-Rank Parameterized Commutative Vector Quantization for KV Cache CompressionJianglin Zhou, Huaming Wu, Huijun Tang4.33
[abs]Semantic-Statistical Prior Banks for Federated Low-Shot Learning under Non-IID ClientsJiaying Wu, Can Gao, Lei Shi et al.4.33
[PDF]Optimal Hidden-Target Learning for Online Inventory Optimization on General Convex SetsAnthony Pineci, Yunzong Xu4.33
[PDF]IFDECORATOR: Wrapping Instruction Following Reinforcement Learning with Verifiable RewardsXu Guo, Tianyi Liang, Jian Tong et al.4.33
[abs]How Do Agentic LLMs Decide to Call Tools? A Scaffold Default Controlled by SuppressionXijie Gong, Tingxu Han, Jiahao Zhang et al.4.33
[PDF]AgentRoom: Concurrent Multi-Agent Coding in a CRDT-Backed Shared WorkspaceSeonglae Cho, Donghyun Lee4.33
[PDF]ORCAID: Oblique Rule-Based Continuous-Action Interpretation for Deep RL PoliciesIgnacio D. Lopez-Miguel, Ezio Bartocci, Thomas Eiter et al.4.33
[abs]Discovering Unseen Degradations to Adapt Open-World Image RestorationBoseong Kim, Tae Hyun Kim, Donghyeon Cho4.33
[abs]Structure-Prompted Multimodal Protein Language Model for Preference-Aligned Fitness PredictionXiaowen Hu, Yichao Cao, Hongyi Huang et al.4.33
[PDF]Existence Precedes Value: Joint Modeling of Observational Existence and Evolving States in Time Series ForecastingYifan Hu, Hongzhou Chen, Peiyuan Liu et al.4.33
[abs]AKTD: FDR Control for LLM Training Data Detection under Approximate ExchangeabilityJingcheng Wang, Yingjie Wang, Yisheng Lv4.33
[PDF]Intrinsic Riemannian Cross-covariance for Manifold-valued Random ObjectsCarlos Soto, Cheng Wang, Yujing Huang et al.4.33
[abs]Factorized Gradients for Scalable Highly-expressive Parametric DiffeomorphismsAmit Aflalo, Eran Treister, Chaim Baskin et al.4.33
[PDF]Leech Lattice Vector Quantization for Efficient LLM CompressionTycho F van der Ouderaa, Mart van Baalen, Paul Whatmough et al.4.33
[abs]InfiniteVL: A Systematic Approach to Highly-Efficient, Ultra-Long Multimodal UnderstandingHongyuan Tao, Bencheng Liao, Shaoyu Chen et al.4.33
[abs]DP-EGGROLL: Centered Fitness-Vector Privatization for Backprop-Free Differentially Private OptimizationDavid T Zagardo4.33
[PDF]Beyond Parameter Arithmetic: Sparse Complementary Fusion for Distribution-Aware Model MergingWeihong Lin, Lin Sun, Qilong Shi et al.4.33
[abs]Frequency-Structured Hamiltonian Neural Network for Multi-Timescale DynamicsYaojun Li, Yulong Yang, Christine Allen-Blanchette4.33
[abs]OPSRL-SSP: Optimistic Posterior Sampling for Stochastic Shortest Path with Minimax-Optimal RegretYIMING XU, Xian Wei, Cheng Chen4.33
[abs]PACE: Partial-state Amortized Constraint Editing for Neural Combinatorial OptimizationBohao Li, Chenhao Yuan, Ying Li et al.4.33
[PDF]Delve into the Applicability of Advanced Optimizers for Multi-Task LearningZhipeng Zhou, Linxiao Cao, Yiming Cao et al.4.33
[PDF]Automated Kernel Discovery Towards Understanding High-dimensional Bayesian OptimizationTaeyoung Yun, Woocheol Shin, Inhyuck Song et al.4.33
[abs]Robust and Scalable Collaborative Learning via Pull-Based Epidemic CommunicationAbdellah El Mrini, Sadegh Farhadkhani, Rachid Guerraoui4.33
[PDF]LYNX: Learning Dynamic Exits for Confidence-Controlled ReasoningÖmer Faruk Akgül, Yusuf H Kalayci, Rajgopal Kannan et al.4.33
[PDF]Feedforward Novel View Synthesis for Heterogeneous CamerasMeng Wei, Cheng Zhang, Boying Li et al.4.33
1 If this project is interesting to you, reach out at [email protected].