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]Interleaved Latent Thinking and Adaptive Termination for Efficient Reasoning LLMsZhao Jin, Rong-Cheng Tu, Wenhao Sun et al.4.67
[PDF]Robust Nash Alignment under Preference UncertaintyShihab Ahmed, Debamita Ghosh, David Tang et al.4.67
[abs]Stochastic Approximation Approach for Decentralized Optimization on Time Varying Random NetworksChung-Yiu Yau, Haoming Liu, Hoi-To Wai4.67
[PDF]Heavy-Tailed Flow Matching via Random ClocksZhouhao Yang, Yezhen Wang, Kenji Kawaguchi et al.4.67
[PDF]Graph-Based Stochastic-Power-UCT: Monte-Carlo Graph Search with Power Mean EstimationTung Tran, Viet Bao, Hoang Ta et al.4.67
[abs]Vibe-Spike: An Energy-Preserving EEG Foundation Model Through the Landscape of Neural CoherenceJun Ye, yuting li, Tingting Dan et al.4.67
[abs]From Link Prediction to Linear Community Detection: A Finite-Sample Guarantee for Graph PretrainingYing Chen, Zhangyang "Atlas" Wang, Yixuan He4.67
[PDF]Few-Step Boltzmann Generators via Scalable Likelihood Flow MapsRuiKang OuYang, Hanlin Yu, Xinyue Ai et al.4.67
[PDF]The sublevel Flood bifiltration: towards scalable 2-parameter persistent homologyMattéo Clémot, Julie Digne, Julien Tierny4.67
[PDF]Learning What's Real: Disentangling Signals and Measurement Artifacts in Multi-Sensor Data, with Applications to AstrophysicsPablo Mercader-Perez, Carolina Cuesta Lazaro, Daniel Muthukrishna et al.4.67
[PDF]Denoising Time Matters: Diverse Generation in Diffusion Language Modelsjingxuan wu, Zhenglin Wan, Yuzhe YANG et al.4.67
[PDF]PATCH: Learnable Tile-Level Hybrid Sparsity for LLMsMohammad Mozaffari, Younes Hourri, Maryam Mehri Dehnavi4.67
[abs]Learning Contextual Causal Dynamics for Robust Exploration in Reinforcement LearningJiaming Pu, Yibo Zhang, Xu Dong et al.4.67
[PDF]A Single-Sample Polylogarithmic Regret Bound for Nonstationary Online Linear ProgrammingHaoran Xu, Owen Shen, Peter W Glynn et al.4.67
[abs]On the Existence of Uniformly Optimal Policies in MDPs under Epistemic UncertaintyAxel Benyamine, Julien Grand-Clément, Marek Petrik et al.4.67
[PDF]Reward Modeling for Multi-Agent OrchestrationKing Yeung Tsang, Zihao Zhao, Vishal Venkataramani et al.4.67
[abs]FusionAudit: Pathway-Conditioned Robustness Auditing for Native Multimodal ModelsJiaming Zhang, Zherui Li, Siqi Guo et al.4.67
[PDF]STEP: Learning STructured Embeddings for Progressive Time SeriesLucas Thil, Jesse Read, Rim Kaddah et al.4.67
[PDF]Delayed homomorphic reinforcement learning for environments with delayed feedbackJongsoo Lee, Jangwon Kim, Soohee Han4.67
[abs]Selective Critique for Cost-Aware LLM Agents in Long-Horizon Decision MakingHeewon Park, Somin Im, Minhae Kwon4.67
[abs]MilliVid: Adaptive Latents for Long-Range Consistency in Video GenerationIshaan Chandratreya, David Charatan, Basile Van Hoorick et al.4.67
[abs]AEGIS: Adaptive Efficient Generative Inference Scheduling for Structured Latent ModelsHaoqi Ruan, Ruihan Hu, XinruiCheng et al.4.67
[abs]Despa: Resolving Spatial Collapse in VLMs via Depth-Grounded GeometryYujing Lou, Pingyi Chen, Shen Cao et al.4.67
[abs]Fine-tuning Does Not Reach All: Uneven Safety and Knowledge Dynamics in Language ModelsZiwei Wang, Xinwei Guo, Jiaxin Zhang et al.4.67
[abs]Data Diversity Drives the Emergence of Symbolic Mechanisms Supporting Abstract ReasoningMelody Li, Taylor Webb4.67
[abs]Tikhonov-Stabilized Bezier Representation Forecasting for Training-free Diffusion AccelerationLei Zhu, Mujie Lin, Ruochong Zheng et al.4.67
[abs]TimeOperator: A Function-to-Function Approach to Time Series ModelingSheoYon Jhin, B. Aditya Prakash, Noseong Park4.67
[abs]Verification-Guided Abstraction Generation with Large Language Models for Generalized PlanningZhenhe Cui, Huaxiang Xia, Hangjun Shen et al.4.67
[PDF]On the Nonlinearity of Learning Rate Scaling for LLM TrainingZAIWEN YANG, Huaqing Zhang, Jing Xu et al.4.67
[PDF]Root Cause Analysis of Measurement and Mechanistic AnomaliesHendrik Suhr, David Kaltenpoth, Jilles Vreeken4.67
[PDF]When and How Much to Imagine: Adaptive Test-Time Scaling with World Models for Visual Spatial ReasoningShoubin Yu, Yue Zhang, Zun Wang et al.4.67
[PDF]What Does the AI Doctor Value? Auditing Pluralism in the Clinical Ethics of Language ModelsPayal Chandak, Victoria Alkin, David Wu et al.4.67
[PDF]Reward Score Matching: Unifying Reward-based Fine-tuning for Flow and Diffusion ModelsJeongjae Lee, Jinho Chang, Jeongsol Kim et al.4.67
[PDF]Optimizer-Induced Mode Connectivity: From AdamW to MuonFangzhao Zhang, Sungyoon Kim, Erica Zhang et al.4.67
[PDF]PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent OptimizationWonjoong Kim, Yeonjun In, Sangwu Park et al.4.67
[PDF]Neural Continuous-Time Markov Chain: Discrete Diffusion via Decoupled Jump Timing and DirectionJingyuan Li, Xiaoyi Jiang, Fukang Wen et al.4.67
[abs]Settling the Sample Complexity of Deterministic Agnostic PAC LearningShai Ben-David, Steve Hanneke, Farnam Mansouri et al.4.67
[PDF]Natural Policy Gradient as Doubly Smoothed Policy Iteration: A Bellman-Operator FrameworkPhalguni Nanda, Zaiwei Chen4.67
[abs]Adapting to Conflict: Equilibrium Structure and Adaptive Learning in Harmonic GamesDavide Legacci, Panayotis Mertikopoulos, Bary Pradelski4.67
[PDF]Learning to Discover Iterative Spectral AlgorithmsZihang Liu, Oleg Balabanov, Yaoqing Yang et al.4.67
[PDF]Flow-Corrected Shape Optimization: Taming Manifold Drift in High-Dimensional 3D ModelsEmilien Seiler, Nicolas Talabot, Yingxuan You et al.4.67
[PDF]Instance-Adaptive Online MulticalibrationZhiming Huang, Jamie Morgenstern, Aaron Roth et al.4.67
[abs]HeMeR: Heterogeneous Memory Reconciliation for Embodied Agents via Structured KV ReuseSaehun Chun, Wonje Choi, Jinwoo Jang et al.4.67
1 If this project is interesting to you, reach out at [email protected].