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]Off-Policy Evaluation of Large Language Models via Learned Semantic Bottleneck EmbeddingsYounwoo Choi, Hadi Sheikhi, Leo Feng et al.4.00
[PDF]XBRIDGE: Entity-Grounded Latent Bridge for Heterogeneous LLM CommunicationWooseong Yang, Wei-Chieh Huang, Weizhi Zhang et al.4.00
[abs]Improved Regret bounds in Tabular Reinforcement Learning under Local Differential PrivacyHugo Richard4.00
[abs]Orlicz–Sobolev with Musielak: An Efficient Regularization Approach for Graph-based IPMTam Le, Truyen Nguyen, Hideitsu Hino et al.4.00
[abs]Reconfiguring Procedural Knowledge for Compositional Robot Skill AdaptationDaehee Lee, Dongsu Lee, Sanghyun Ahn et al.4.00
[PDF]Step-by-Step Optimization-like Reasoning in LLMs over Expanding Search SpacesNicolás Astorga, Nabeel Seedat, Mihaela van der Schaar4.00
[abs]Universal Approximation Theorems for Dynamical Systems with Infinite-Time Horizon GuaranteesÁbel Ságodi, Memming Park4.00
[PDF]Flow Matching for Offline Reinforcement Learning with Discrete ActionsFairoz Nower Khan, Nabuat Zaman Nahim, Ruiquan Huang et al.4.00
[PDF]When Do Multi-Agent Systems Help? An Information Bottleneck PerspectiveWendi Yu, Lianhao Zhou, Xiangjue Dong et al.4.00
[abs]Temporal Behavior Trees for Reinforcement Learning: Specifications as Rewards, Curricula, and DiagnosticsVladimir Krsmanovic, Bernd Finkbeiner4.00
[PDF]CoRDS: Coreset-Based Representative and Diverse Selection for Streaming Video UnderstandingAilar Mahdizadeh, Puria Azadi Moghadam, Muchen Li et al.4.00
[abs]SCDM: Scalable Causal Discovery in Nonlinear Temporal Systems with Meta-LearningJingbo Wang, Kegeng Tang, Zihao Wang et al.4.00
[PDF]Optimal Dimension-Free Sampling for Regularized ClassificationMeyam Alishahi, Alexander Munteanu, Simon Omlor et al.4.00
[abs]Quantum Speedup of Multi-armed Bandits at Scale by Tackling Memory DecoherenceRohit Muralitharan, Mark Squillante, Chen Wang et al.4.00
[PDF]Distributionally Robust Listwise Preference OptimizationXudong Wu, Jian Qian, Pangpang Liu et al.4.00
[abs]SSD: Shell-Guided Spherical Diffusion for Molecular Geometry GenerationYun-Yen Chuang, Chen-Sheng Gu, Hung-Min Hsu et al.4.00
[abs]ACDP: Architecture-aware Cross-Dataset Performance Predictor for NASJiawen Deng, Yuqi Feng, Han Ji et al.4.00
[PDF]On the Sparsity-Storage-Accuracy Tradeoff in Parsimoniously Activated Dictionary LearningZihui Zhao, Yang Li4.00
[abs]Beyond Pixel-wise Supervision: Local Structure Regularization for Semantic SegmentationWei Huang, Chenying Liu, Yilei Shi et al.4.00
[PDF]Transformers Provably Implement In-Context Reinforcement Learning with Policy ImprovementHaodong Liang, Lifeng LAI4.00
[PDF]How Neural Reward Models Learn Features for Policy Optimization: A Single-Index AnalysisRei Higuchi, Ryotaro Kawata, Akifumi Wachi et al.4.00
[PDF]Characterizing Trainability of Instantaneous Quantum Polynomial Circuit Born MachineKevin Shen, Susanne Pielawa, Vedran Dunjko et al.4.00
[abs]Darwin-7B: A Multi-Omic Foundation Model for the Human Gut Microbiome via Sparsified Quality-Aware TokenizationArvid Ernst Gollwitzer, David de Gruijl4.00
[abs]Enabling Preference-driven Unlearning in Few-step Distilled Text-to-Image Diffusion ModelsGaurav Patel, Jun Fang, Greg Ver Steeg et al.4.00
[abs]The Geometry of Linear Program Compression: An Exact Characterization and Learning AlgorithmYuhan Ye, Omar Bennouna4.00
[PDF]Adversary-Robust Learning from Fully Asynchronous Directional Derivative EstimatesAnik Kumar Paul, Nibedita Roy, Nagesh Talagani et al.4.00
[abs]Iterative Scarcity-Guided Exploration: Bootstrapping Generative Auto-bidding from Narrow SupportQingmao Yao, Guangzheng Hu, Yusen Huo et al.4.00
[PDF]Beyond Prediction: Steering VLM Agents with Retrospective World ModelingYongjiang Liu, Jie ZHANG, Haoyue Zhang et al.4.00
[PDF]CAST: Causal Anchored Simplex Transport for Distribution-Valued Time SeriesJiecheng Lu, Jieqi Di, Runhua Wu et al.4.00
[abs]PVFormer: Proper Velocity Transformer for Stable and Scalable Hyperbolic Representation LearningXianglong Shi, Nicu Sebe, Bernhard Schölkopf et al.4.00
[abs]Posterior Sampling-based Online Learning for Episodic POMDPsDengwang Tang, Dongze Ye, Rahul Jain et al.4.00
[abs]Spectral Estimation with Deformed DecompressionSiavash Ameli, Chris van der Heide, Liam Hodgkinson et al.4.00
[abs]Binary Regression: Universal Ising Model, Binary Expansion and BeyondJerry Yao-Chieh Hu, YI-CHEN LEE, Mingcheng Lu et al.4.00
[abs]On Concentration Inequalities for Sampling without ReplacementShaojie Li, Bowei Zhu, Yong Liu4.00
[PDF]A Measure-Theoretic Analysis of Reasoning: Structural Generalization and Approximation LimitsYuyang Zhang, Yifu Zhang, Xuehai Zhou et al.4.00
[abs]Riemannian Admissibility Flow for Offline-to-Online Safe Reinforcement LearningYuan Chu, Xuewu Ji4.00
[PDF]SEAD: Competence-Aware On-Policy Distillation via Entropy-Guided SupervisionMichael Lee, Zelei Cheng, Yu Wang et al.4.00
[PDF]Trajectory as the Teacher: Few-Step Discrete Flow Matching via Energy-Navigated DistillationAmin Karimi Monsefi, Dominic Culver, Nikhil Bhendawade et al.4.00
[PDF]Pause and Reflect: Conformal Aggregation for Chain-of-Thought ReasoningYu Gu, Zijun Yu, Vahid Partovi Nia et al.4.00
[abs]Interactive 4D Volumetric Liquid Forecasting under Moving-Solid InteractionJongwon Ryu, Sunjae Yoon, Junyeong Kim4.00
[abs]When Are Semivalue-Based Decisions Identifiable? Robust Data Selection under Utility AmbiguityHannah Diehl, Justin Steil, Ashia Wilson4.00
[PDF]MaskForge: Structure-Aware Adaptive Attacks for Jailbreaking Diffusion Large Language ModelsYingzi Ma, Zhengyue Zhao, Xiaogeng Liu et al.4.00
[PDF]In-context learning to predict critical transitions in dynamical systemsYunus Sevinchan, Juan Nathaniel, Kai Ueltzhöffer et al.4.00
[PDF]Dynamic Delayed Tree Expansion For Improved Multi-Path Speculative DecodingRahul K Thomas, Teo Kitanovski, Micah Goldblum et al.4.00
[abs]Towards Effective and Transferable Physical Camouflage against Multi-View BEV-based 3D Perception in Autonomous DrivingLinye Lyu, Jiawei Zhou, Daojing He et al.4.00
1 If this project is interesting to you, reach out at [email protected].