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]What Kind of Diffusion Models Do We Need in Online Reinforcement Learning?Zihao Wu, Hongyao Tang, Yi Ma et al.4.33
[abs]A Simple Unigram Cross-Entropy Lens on the Lexical Imprint of Pre-training DataJeonghoon Kim, Woojin Chung, Woomin Song et al.4.33
[abs]PLACE: Patch-Level Agnostic Concept ExtractionGabriele Onorato, Fabrizio Silvestri, Nathaniel D Bastian et al.4.33
[PDF]Thinking in Boxes: 3D Editing in Real Images Made EasyPradhaan Bhat, Naveen Chandra R, Rishubh Parihar et al.4.33
[PDF]Online Set Learning from Precision and Recall FeedbackLee Cohen, Yishay Mansour, Shay Moran et al.4.33
[PDF]Soft geometric inductive bias for object centric dynamicsHampus Linander, Conor Heins, Marco Perin et al.4.33
[PDF]Resolving Representation Ambiguity in Feedforward Novel View Synthesis Transformer via Semantic-Spatial DecouplingYihang Wu, Yihang Sun, Shaofeng Zhang et al.4.33
[PDF]Zeroth-Order Stackelberg Control in Combinatorial Congestion GamesSaeed Masiha, Sepehr Elahi, Negar Kiyavash et al.4.33
[abs]Analyzing Learning-Dynamics Across Loss and Prediction Choices for Diffusion ModelsDongwoo Kim4.33
[abs]Verifiers in the Loop: Decoding Time Verification for Code TranslationTianyang Zhou, Somesh Jha, Mihai Christodorescu et al.4.33
[abs]3D Fresnel Volumizing for Efficient Implicit Velocity Field ReconstructionSihan Chen, haochen sun, Peng Jiang et al.4.33
[abs]Bet Imaginatively, not Historically in Independent-Data Sequential TestingNathaniel Xu, Feng Liu, Danica J. Sutherland4.33
[PDF]Muon Does Not Converge on Convex Lipschitz FunctionsTetiana Parshakova, Ahmed Khaled, Michael Crawshaw et al.4.33
[PDF]Logit-Gap Steering: A Forward-Pass Diagnostic for Alignment RobustnessTung-Ling Li, Hongliang Liu4.33
[abs]Geometry-Aware Zeroth-Order Optimization for Fine-Tuning Quantized LLMsShaocong Ma, Weidong Cai, Heng Huang4.33
[PDF]Geometric Latent Reasoning Induces Shorter Generations in LLMsShashi Kumar, Yacouba Kaloga, Petr Motlicek et al.4.33
[PDF]SCOT: Multi-Source Cross-City Transfer with Optimal-Transport Soft-Correspondence ObjectivesYuyao Wang, Min Yang, Meng Chen et al.4.33
[PDF]Tell Me What To Learn: Generalizing Neural Memory to be Controllable in Natural LanguageMax Bennett, Thomas Zollo, Richard Zemel4.33
[abs]Not All Noise Is Harmful: Towards Perception Aware and Controllable RAW Image Joint Denoising and DemosaicingQianjun Huang, Qingguo Liu, Hui Zeng et al.4.33
[PDF]The Unreasonable Effectiveness of Text Embedding Interpolation for Continuous Image SteeringYiğit Ekin, Yossi Gandelsman4.33
[abs]In STeP: Speculative Tensor Parallelism for Concurrent Heterogeneous Inference of LLMsViren Luke Radhakrishnan, Dhruva Kashyap, Pranav K Nayak et al.4.33
[abs]OASIS: Online Adaptive Steering for In-Training Safety of LLMsYifan Sun, Qiang Sheng, Ya Wu et al.4.33
[PDF]Designing Reinforcement Learning for Diffusion Models: A Unified Path-Space ViewYixian Xu, Yuanrui Zhang, Shengjie Luo et al.4.33
[abs]Fair Bubble Sort: Provably Optimal Fair Ranking with Continuous Sensitive AttributesAntonio Ferrara, Fabio Vitale, Atsushi Miyauchi et al.4.33
[PDF]Generative Modeling under Non-Monotone MAR Missingness via Approximate Wasserstein Gradient FlowsGitte Kremling, Jeffrey Näf, Johannes Lederer4.33
[PDF]Grasp-Then-Plan with Failure Attribution: A Closed Two-Stage Framework for Precise and Generalizable Robotic ManipulationJiahao Xu, Peiyuan Wang, Hanzhuo Zhang et al.4.33
[PDF]Denoise First, Orthogonalize Later: Understanding Momentum in Muon via Spectral FilteringXianliang Li, Zihan Zhang, Weiyang Liu et al.4.33
[PDF]Branching Flows: Discrete, Continuous, and Manifold Flow Matching with Splits and DeletionsLukas Billera, Hedwig Nora Nordlinder, Jack C Ryder et al.4.33
[abs]On Minimizing Regret in Fixed-Confidence -Best Arm IdentificationTianyuan Jin, Junwen Yang, Vincent Tan4.33
[abs]BLANP: Memory-Efficient Backpropagation-Free Local Training via Antithetic Node PerturbationMehrzad Karamimanesh, Marcel A. J. van Gerven, Mahyar Shahsavari4.33
[PDF]The Interplay of Data Structure and Imbalance in the Learning Dynamics of Diffusion ModelsFlavio Nicoletti, Chenxiao Ma, Enrico Ventura et al.4.33
[PDF]Supervised Distributional Reduction via Optimal Transport and Dependence MaximizationSai-Aakash Ramesh, Archit Sood, Andrew Corbett et al.4.33
[PDF]Explaining and Preventing Alignment Collapse in Iterative RLHFEtienne Gauthier, Francis Bach, Michael Jordan4.33
[PDF]Distribution Shift in Missing Data Imputation: A Risk-Based Perspective and Importance-Weighted Correction under MARLuke Shannon, Song Liu, Katarzyna Reluga4.33
[abs]GramStatTexNet: Efficient, Interpretable, and Neuro-Inspired Texture Analysis-by-SynthesisVasha DuTell, Zeyu Yun, Anne Harrington et al.4.33
[abs]Beyond Langevin: Sampling Multimodal Densities using the Witten Laplacian on 1-formsSahani Pathiraja, Panos Parpas4.33
[PDF]AI-Mediated Communication Can Steer Collective OpinionStratis Tsirtsis, Kai Rawal, Chris Russell et al.4.33
[PDF]Not Every Rubric Teaches Equally: Policy-Aware Rubric Rewards for RLVRUtkarsh Tyagi, Xingang Guo, MohammadHossein Rezaei et al.4.33
[PDF]Z0-Inf: Zeroth Order Approximation for Data InfluenceNarine Kokhlikyan, Diego Garcia-Olano, Kamalika Chaudhuri et al.4.33
[abs]CipherFlow: Hardware-Aware Compiler Framework for Low-Latency Hybrid Secure InferenceHedong Zhang, Mengxin Zheng, Qian Lou4.33
[abs]A Surrogate Perspective on Convergence of Fixed-Target DQNZichu Liu, Nneka M Okolo, Ryan D'Orazio et al.4.33
[abs]SpanFormer: Multi-Level Adaptive Sparsity for Object Detection in High-Resolution Wide ShotsXiang Li, Chen Zhang, Wenxi Li et al.4.33
[PDF]Scaling Storm-Resolving Atmospheric AI Simulation to the Entire PlanetZeyuan Hu, Noah Brenowitz, Akshay Subramaniam et al.4.33
[PDF]SWE-Protégé: Learning to Selectively Collaborate With an Expert Unlocks Small Language Models as Software Engineering AgentsPatrick Tser Jern Kon, Archana Pradeep, Ang Chen et al.4.33
[PDF]Extracting Governing Equations from Latent Dynamics via Multi-View Contrastive LearningPaolo Muratore, Mackenzie Mathis4.33
[PDF]The Query Complexity of Local Search in Rounds on General GraphsSimina Branzei, Ioannis Panageas, Dimitris Paparas4.33
1 If this project is interesting to you, reach out at [email protected].