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]OxyGen: Unified KV Cache Management for VLA Inference under Multi-Task ParallelismXiangyu Li, Huaizhi Tang, Xin Ding et al.4.33
[PDF]Safety Geometry Collapse in Multimodal LLMs and Adaptive Drift CorrectionJiahe Guo, Xiangran Guo, Jiaxuan Chen et al.4.33
[PDF]Query-Limited Community Recovery in Stochastic Block ModelsSabyasachi Basu, MANUJ MUKHERJEE, Lutz Oettershagen et al.4.33
[PDF]Sparse Koopman Autoencoders Identify Local Dynamical Regimes in Multibasin SystemsAidan Li, Uday Kiran Reddy Tadipatri, Mahan Fathi et al.4.33
[PDF]PACE: Two-Timescale Self-Evolution for Small Language Model AgentsChen Ling, Pei Chen, Xiangchen Guan et al.4.33
[PDF]Bug or Feature: Weight Drift, Activation Sparsity, and SpikesEgor Shvetsov, Aleksandr Serkov, Shokorov Viacheslav et al.4.33
[PDF]Preference Conditioned Multi-Objective Reinforcement Learning: Decomposed, Diversity-Driven Policy OptimizationTanmay Ambadkar, Sourav Panda, Shreyash Kale et al.4.33
[PDF]It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMsSangwoo Park, Woongyeong Yeo, Yumin Choi et al.4.33
[PDF]A Theoretical Analysis of Why Masked Diffusion Models Mitigate the Reversal CurseMoongyu Jeon, Sangwoo Shin, Bumjun Kim et al.4.33
[PDF]StreamPhy: Streaming Inference of High-Dimensional Physical Dynamics via State Space ModelsPanqi Chen, Yifan Sun, Shikai Fang et al.4.33
[PDF]Taming CoT Obfuscation in VLMs: From Mechanistic Evidence to Activation-Level EnforcementXutao Mao, Jianing Zhu, Jinman Zhao et al.4.33
[abs]CAPO: A Primal-Dual Framework for Constraint-Aware Prompt OptimizationVictor Ye Dong, Reid Pryzant, Yi Liu et al.4.33
[abs]Transductive Generalization for GNNs via Optimal TransportMoonJeong Park, Seungbeom Lee, Kyungmin Kim et al.4.33
[abs]MedCache: Training-Free Spatially Aware Caching for Accelerated Medical Video GenerationUfaq Khan, Umair Nawaz, Sathira Silva et al.4.33
[abs]From Contexts to Conditionals: Statistical Self-Consistency of Persona PromptingPatrik Wolf, Thomas Kleine Buening, Andreas Krause et al.4.33
[PDF]Learning Rate Transfer for Hybrid Transformer-SSM ArchitecturesJimin Seo, Gyubok Lee, Yeonsik Jo et al.4.33
[PDF]HeatKV: Head-tuned KV-cache Compression for Visual Autoregressive ModelingJonathan Cederlund, Axel Berg, Durmus Alp Emre Acar et al.4.33
[abs]InfoNav: A Unified Value Framework Integrating Semantic Relevance and Information Gain for Zero-Shot Object Goal NavigationZhi Yang, Chengpu Yu, Gonzalo Ferrer4.33
[abs]Fast Alignment of Embeddings: Computational Guarantees for Anisotropic Procrustes-WassersteinJakob Maier, Laurent Massoulié4.33
[abs]Dual-Space Preconditioning for Variational Inequalities and Root-Finding ProblemsJan Quan, Konstantinos Oikonomidis, Alexander Bodard et al.4.33
[PDF]SGD in Multiclass Logistic Regression: Sequential Learning and Scaling LawsKonstantinos Tsiolis, Denny Wu, Christos Thrampoulidis et al.4.33
[PDF]Zero-Shot Instruction Following in RL via Structured LTL RepresentationsMathias Jackermeier, Mattia Giuri, Jacques Cloete et al.4.33
[PDF]Stage Light is Sequence: Multi-Light Control via Imitation LearningZijian Zhao, Dian Jin, Zijing Zhou et al.4.33
[PDF]Stable and Scalable Probabilistic Numerical Solvers for Stiff and High-Dimensional ODEsNathanael Bosch4.33
[PDF]SDFlow: Similarity-Driven Flow Matching for Time Series GenerationWei Li, FENG SHIBO, Pengcheng Wu et al.4.33
[abs]Visual Grounding First, Multimodal In-context Learning FollowsMinhyuk Seo, Minjae Lee, Chaeeun Lee et al.4.33
[PDF]Efficient Lookahead Encoding and Abstracted Width for Learning General Policies in Classical PlanningMichael Aichmüller, Simon Ståhlberg, Martin Funkquist et al.4.33
[abs]From Seeing to Foreseeing: Unleashing LVLM Thinking in Dynamic Latent SpaceYuxuan Liang, Xu Li, Xiaolei Chen et al.4.33
[PDF]The Bayesian Origin of the Probability Weighting Function in Human Representation of ProbabilitiesXin Tong, Thi Thu Uyen Hoang, Xue-Xin Wei et al.4.33
[abs]Structure vs. Chaos: Asymmetric Entropic Optimization for Enforcing Instruction HierarchyTianxiao Huang, Xinwei Liu, Zitong Shi et al.4.33
[abs]Search-Tree Scaling in Parallel Monte Carlo Tree SearchScott Cheng, Meng-Yu Tsai, Ding-Yong Hong et al.4.33
[abs]Structured Human-Like Agentic Flow for RTL DesignYu-Tung Liu, Zhan Song, Chenhui Deng et al.4.33
[PDF]Attention-Discounted Adaptive Sampler for Masked Diffusion Language ModelsYusuf Sahin, Ahmed R Saikia, Volkan Cevher et al.4.33
[PDF]Adaptive Delayed-Update Cyclic Algorithm for Variational InequalitiesYi Wei, Xufeng Cai, Jelena Diakonikolas4.33
[PDF]CASL-VAE: Learning Structured Latent Variables from Unpaired Data for Semi-supervised Clustering and Paired Sample GenerationSai Spandana Chintapalli, Pratik Chaudhari, Christos Davatzikos4.33
[abs]Data-Efficient Learning for Constraint Satisfaction Problems via Relational Biases and Hard Axiom ClampingEnqiang Zhu, Ke Wang, Yu Zhang et al.4.33
[abs]Unbiased First-Order Randomized Smoothing for Differentiable SimulationMathis SCHEFFLER, Wilson Jallet, Cordelia Schmid et al.4.33
[abs]Epistemic Social Learning: Latent Behavioral Structure under Endogenous Multi-Agent InteractionJainendra Shukla, Dhruv Jaiswal, Divyanshi Beniwal et al.4.33
[PDF]Scalable Maximum Entropy Reinforcement Learning for Diffusion Policies via Adjoint MatchingSerge Thilges, Onur Celik, Denis Blessing et al.4.33
[abs]Looking Through the Mirror: Minimax-Optimal Regularized Regrets in Online Learning and BanditsJunghyun Lee, Yujun Kim, Chulhee Yun et al.4.33
[abs]Selling Information While Being an Interested PartyFrancesco Bacchiocchi, Matteo Castiglioni, Alberto Marchesi et al.4.33
[PDF]Per-Loss Adapters for Gradient Conflict in Physics-Informed Neural NetworksBum Jun Kim, Gnankan Landry Regis N'guessan4.33
[abs]Plan2Sense: Open-World Task Planning in Epistemic States via Interleaved Ontic and Sensing ActionsXiaotian Liu, Armin Toroghi, Jiazhou Liang et al.4.33
[abs]Approximate Matrix–Vectors Under a Bounded Assumption and Applications to Kernel MatricesRikhav Shah, Sandeep Silwal, Tony C Wang4.33
[abs]MSP: Modality Self-Play for Training Multimodal LLMs Without Paired Cross-Modal DataRobert Moseley, Md Kaykobad Reza, Ameya Patil et al.4.33
[abs]Traversal-Invariant Positional Encoding for Serialized GraphsKrish Mody, Sridhar Radhakrishnan, Chandra N Sekharan4.33
1 If this project is interesting to you, reach out at [email protected].