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]Escaping Parameter Space: Tight Generalization Bounds via Representation QualityNiclas A Göring, Shuofeng Zhang, Branton DeMoss et al.3.50
[abs]Co-GRPO: Co-Optimized Group Relative Policy Optimization for Masked Image GenerationRenping Zhou, Zanlin Ni, Tianyi Chen et al.3.50
[abs]META-PAP: Meta-learning for Prompt-aware Preference Pairing in LLM AlignmentPinlong Zhao, Shiyu Hu, Jing Zhang et al.3.50
[PDF]Scaling Reward Modeling without Human SupervisionJingxuan Fan, Yueying Li, Zhenting Qi et al.3.50
[abs]QUEST: Q-Learning for Uncertainty-Guided Efficient Search TeamsArsh Verma, Tejus Gupta, Jeff Schneider3.50
[PDF]PRIM: Meta-Learned Bayesian Root Cause AnalysisChristopher Lohse, Anish Dhir, Amadou Ba et al.3.50
[PDF]Follow the Mean: Reference-Guided Flow MatchingPedro Curvo, Maksim Zhdanov, Floor Eijkelboom et al.3.50
[abs]Frontier Task Synthesis Via Solution-Centric EvolutionYangzhen Wu, Aaron Li, Wenjie Ma et al.3.50
[PDF]RoSA: Rotational Sparse Adaptation for Memory-Efficient Fine-TuningMuhammad Azeem Lodhi, chao zhou, Rebekka Burkholz3.50
[abs]Scattered by Design: Why Per-Output Pruning Resists Structured CompressionVictor Omolaoye, Gerard de Melo3.50
[abs]Tree-Ensemble Repair through Constrained OptimizationLorenzo Cascioli, Chaahat Jain, Marcel Steinmetz et al.3.50
[abs]Revisiting Activation Steering Through an Optimization LensRyan Lee, Dung V Nguyen, Minh Hieu Vu et al.3.50
[abs]From Matching to Reasoning: Query-Aware Long Video SummarizationMingu Kang, Sumin Kim, Hyunjin Lee et al.3.50
[PDF]Compositional Reasoning in Language Models under Reinforcement Learning Post-TrainingYu He, Yingxi Li, Yifei Wang et al.3.50
[abs]Empirical regularities in subjective decision-making by LLMsKaty Blumer, Jon Kleinberg, Ravi Kumar et al.3.50
[abs]Heteroscedastic TrueSkill: Modeling Match Noise and Player ConsistencyPhilipp Kolbe, Johann Ukrow, Anna Kazachkova et al.3.50
[PDF]Complexity of Classical Acceleration for -Regularized PageRankKimon Fountoulakis, David Martínez-Rubio3.50
[PDF]Slower Generalization, Faster Memorization: A Sweet Spot in Algorithmic LearningShin So, Kyelim Lee, Albert No3.50
[abs]Restoring the RNA-Ligand Interaction Manifold via Topology-Preserving Contrastive Learning under Epistemic UncertaintyKai Zheng, Jinhui Xu, Jianxin Wang3.50
[PDF]BSO: Safety Alignment Is Density Ratio MatchingTien-Phat Nguyen, Truong Nguyen, Thin Nguyen et al.3.50
[PDF]Causal Representation Learning for Generalisable RecommendationYorgos Felekis, Michael O'Riordan, Oriol Corcoll Andreu et al.3.50
[PDF]The Override Gap: A Magnitude Account of Knowledge Conflict Failure in Hypernetwork-Based Instant LLM AdaptationShuaizhi Cheng, Xiang Shi, Zhiwei Zhang et al.3.50
[abs]Tokenizer Choice Shapes Generalization in State-Centric Learning for PlanningVishal Pallagani, Nitin Gupta, John A Aydin et al.3.50
[abs]Is a Linear Probe Evidence of a Linear Representation?Nadir Kutluozen, Christian Internò, David Klindt3.50
[abs]NestedVLA: Learning to Consolidate and Generate Skills for Vision-Language-Action ModelGuodong DU, Wanyu Lin3.50
[PDF]Variance Reduction for Expectations with Diffusion TeachersJesse Bettencourt, Xindi Wu, Matan Atzmon et al.3.50
[abs]On the Pitfalls of Instance-Based Dynamic CurriculaAlexandre Galashov, Amal Rannen-Triki, Yee Whye Teh et al.3.50
[abs]Matching2Matching: Zero-Shot Light Field Image Denoising with Matching View ConstructionShuo Zhang, Qian Tian, Chen Gao et al.3.50
[PDF]Explanation of Dynamic Physical Field Predictions using WassersteinGrad: Application to Autoregressive Weather ForecastingYounes Essafouri, Laure Raynaud, Luciano DROZDA et al.3.50
[abs]Gradient-based Graph Structure Optimisation for Research NetworksLouis Mahon, Mirella Lapata3.50
[PDF]Sketching the Readout of Large Language Models for Scalable Data Attribution and Valuationyide ran, Jianwen Xie, Minghui Wang et al.3.50
[PDF]Controllable Generative Sandbox for Causal InferenceQi Zhang, Harsh Parikh, Ashley I Naimi et al.3.50
[abs]Deadline-Constrained Dynamic Workflow Scheduling Can be Cast as a Representation Learning ProblemYa Shen, Gang Chen, Hui Ma et al.3.50
[abs]GCD: GCM-consistent Diffusion for Zero-shot Downscaling across Heterogeneous GCMsRuian Tie, Wenbo Xiong, Zhengyu Shi et al.3.50
[abs]Unlearning Diffusion Policies via Relative Fisher ForgettingManuel Kelly, Yingxue Zhang, Fangzhou Lin et al.3.50
[PDF]GPU-Accelerated Synthesis of Mixed-Boolean Arithmetic: Beyond CachingGabriel Bathie, Nathanaël Fijalkow3.50
[abs]Boundary Mass in Feature Space as a Label-Budget Diagnostic for RepresentationsSiming Zhang, Zhehui Shen, Shijie Chen et al.3.50
[PDF]Embedding Security Properties into AI-Enabled Cyber-Physical SystemsZiyan An, John Stankovic, Meiyi Ma3.50
[abs]The Block Catastrophe of Marginal Calibration in Certified Requirements TraceabilityJikun Wu, Dongxin Guo, Siu Ming Yiu3.50
[abs]When Does Structure Help? Statistical Tradeoffs for Structured Reverse Processes in Diffusion Large Language ModelsRuofeng Yang, Jingyuan Liu, Shuai Li3.50
[PDF]Toward a Unified Statistical Theory of Unsupervised Pretraining and Supervised Neural Knowledge Graph LearningSuqi Liu, Miklos Z. Racz, Jifan Zhang3.50
[abs]Optimizing Analytic Constants via AI-Guided Lean Proof RefinementRahul Saha, Alan Li, Anton Xue et al.3.50
[abs]Do Glimpse Policies See Like Humans? A Behavioral Audit Reveals Dissociated Viewing Priors in Classification-Trained Active Visionboheng liu, Ziyu Li, Chenghua Duan et al.3.40
[abs]Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural NetworksMarte Eggen, Eirik Reiestad, Kristian Gjøsteen et al.3.40
1 If this project is interesting to you, reach out at [email protected].