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]Flowette: Flow Matching with Graphette Priors for Graph GenerationAsiri Wijesinghe, Sevvandi Kandanaarachchi, Daniel M Steinberg et al.4.33
[abs]Dataset Mismatch Matters in Group Relative Policy Optimization for Reinforcement Learning from Verifiable RewardsZhen-Yu Zhang, Jiandong Zhang, Huaxiu Yao et al.4.33
[PDF]CanViT: Toward Active-Vision Foundation ModelsYohaï-Eliel BERREBY, Sabrina Du, Audrey Durand et al.4.33
[PDF]Learned Lagrangian Models of PDEs via Euler–Lagrange Residual MinimizationLyra Zhornyak, Eric Forgoston, M. Ani Hsieh4.33
[abs]Monotone Inclusion Approach to Weakly Monotone Discrete-Time Finite-Horizon Mean-Field GamesUgur Aydin, Tamer Basar, Naci Saldi4.33
[abs]Flux: Online, Fine-Grained Data Scheduling for Training Machine Learning Interatomic PotentialsYuanchang Zhou, Chen Wang, Hongtao Xu et al.4.33
[PDF]LookThere! Sparse Vision by Reinforced SelectionSreehari Rammohan, Yousef Yassin, Anthony Fuller et al.4.33
[PDF]Local linear convergence of gradient methods for overparameterized Gaussian mixturesJingxing Wang, Vasileios Charisopoulos, Maryam Fazel4.33
[PDF]Provably Efficient Regularized Online RLHF with Generalized Bilinear PreferencesJunghyun Lee, Minju Hong, Kwang-Sung Jun et al.4.33
[abs]Towards Generalizable Partially Relevant Video RetrievalWoojin Jun, Cheol-Ho Cho, MinSeok Jung et al.4.33
[PDF]TALON: Confidence-Aware Speculative Decoding with Adaptive Token TreesTianyu Liu, Qitan Lv, Yuhao Shen et al.4.33
[abs]MissPath-FM: Flow Matching with Structured Priors for Partially Observed Time SeriesGenpei Zhang4.33
[abs]CAST: Certifiable Aggregation of Smoothed Teachers for Robust Policy AdaptationZhongrui Zhao, Yanan Cai, Zhigang Lu et al.4.33
[PDF]FARE: Forensic Acceptance Region Estimation for Catching Bait-and-Switch Image GeneratorsKai Yao, Marc Juarez4.33
[abs]Second-Order Complexity Theory for Risk, Explanation, and Calibration in Machine LearningYoshihiro Maruyama4.33
[abs]ProMo3D: Probing Motion Cues in Frozen 3D Foundation ModelsXiaoang Zhang, Mert Kiray, Yordanka Velikova et al.4.33
[abs]Counterfactual Estimation under Composite Treatments via Progressive Distribution AlignmentAbhirup Mondal, Anirban Majumder, Vineet Chaoji4.33
[PDF]Agent Meltdowns: The Road to Hell Is Paved with Helpful AgentsRishi Jha, Harold Triedman, Vitaly Shmatikov et al.4.33
[PDF]Dr. MAS: Stable Reinforcement Learning for Multi-Agent LLM SystemsLang Feng, Longtao Zheng, Shuo He et al.4.33
[PDF]To Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM AgentsWei Shi, Ziheng Peng, Sihang Li et al.4.33
[PDF]Improving Diffusion Posterior Samplers with Lagged Temporal Corrections for Image RestorationDavide Evangelista, Elena Morotti, Francesco Pivi et al.4.33
[PDF]SMOG: Scalable Meta-Learning for Multi-Objective Bayesian OptimizationLeonard Papenmeier, Petru Tighineanu4.33
[PDF]Phaedra: Learning High-Fidelity Discrete Tokenization for the Physical SciencesLevi Lingsch, Georgios Kissas, Johannes Jakubik et al.4.33
[PDF]LLM-Auction: Generative Auction towards LLM-Native AdvertisingChujie Zhao, Qun Hu, Shiping Song et al.4.33
[PDF]MonoPhysics: Estimating Geometry, Appearance, and Physical Parameters from Monocular VideosDaniel Rho, Jun M Choi, Matthew Thornton et al.4.33
[PDF]LLM-Based Multi-Agent Blackboard System for Information Discovery in Data ScienceAlireza Salemi, Mihir Parmar, Palash Goyal et al.4.33
[abs]Aligning LLMs Toward Multi-Turn Conversational Outcomes Using Iterative RLHFDaniel Jiang, Ankur Samanta, Yukai Yang et al.4.33
[PDF]The Attacker in the Mirror: Breaking Self-Consistency in Safety via Anchored Bipolicy Self-PlayGabriele La Malfa, Emanuele La Malfa, Saar Cohen et al.4.33
[abs]Relative Energy Barriers for Copyright-Aware Language Model AdaptationWei Sun, Yuhang Zhang, Zhicheng Liang et al.4.33
[PDF]Generalized Intention Modeling in Multi-Agent Reinforcement LearningMateusz Odrowaz-Sypniewski, Jasmine Bayrooti, Ajay Shankar et al.4.33
[PDF]The Reward Was in Your Data All Along: Correcting Flow Matching with Discriminator-Guided RL.Nicolas Beltran Velez, Felix Friedrich, Xiaofeng Zhang et al.4.33
[PDF]Correlating Cross-Iteration Noise for DP-SGD using Model CurvatureXin Gu, Yingtai Xiao, Guanlin He et al.4.33
[PDF]Geometry-Aware Optimal Transport: Fast Intrinsic Dimension and Wasserstein Distance EstimationFerdinand Genans, Olivier Wintenberger4.33
[abs]Harnessing Data Asymmetry in Manifold LearningThomas Dagès, Simon Weber, Daniel Cremers et al.4.33
[PDF]Memory Inception: Latent-Space KV Cache Manipulation for Steering LLMsZeyi (Andy) Liu, Michael Zhang, Ilana Greenberg et al.4.33
[abs]From Tokens to Tactics: Adversarial Text Optimization in an Axis-Aligned Rhetorical Strategy Space for Harmful Content DetectionJinjie Wang, Shu Jiang, Hai Zhao4.33
[PDF]RepoLaunch: Automating Build and Management of Code Repositories across Languages and PlatformsKenan Li, Rongzhi Li, Linghao Zhang et al.4.33
[PDF]Rethinking Language Model Scaling under Transferable Hypersphere OptimizationLiliang Ren, Yang Liu, yelong shen et al.4.33
[PDF]HaM-World: Soft-Hamiltonian World Models with Selective Memory for PlanningHaoyun Tang, Haodong Cui, Keyao Xu et al.4.33
[abs]VALOR: Vector-Aware Low-Rank Restructuring of Neural Networks for RISC-V InferenceZhihao Xu, Xiaoning Du, Bixin Li et al.4.33
[abs]Causal heteroscedastic structure learning from incomplete temporal dataAbdellah Rahmani, Pascal Frossard4.33
[PDF]Boule or Baguette? A Study on Task Topology, Length Generalization, and the Benefit of Reasoning TraceWilliam Tong, Ege Çakar, Cengiz Pehlevan4.33
[PDF]SymDrift: One-Shot Generative Modeling under SymmetriesSamir Darouich, Vinh Tong, Lluis Pastor Perez et al.4.33
[PDF]Adaptive Inference for Functionals of M-EstimandsJames Leiner, Aurelien Bibaut, Nathan Kallus et al.4.33
[PDF]Breaking the Grid: Distance-Guided Reinforcement Learning in Large Discrete Action SpacesHeiko Hoppe, Fabian Akkerman, Wouter van Heeswijk et al.4.33
1 If this project is interesting to you, reach out at [email protected].