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]Uncertainty Estimation for Pretrained Medical Image Registration Models via Transformation EquivarianceLin Tian, Xiaoling Hu, Juan Eugenio Iglesias3.67
[abs]SpectralKV: Redundancy-Aware KV Cache Compression via Spectral Coreset SelectionFangming Zhao, Fulun Ye, Xiaofei Yue et al.3.67
[PDF]Masked Diffusion Language Models are Strong and Steerable Text-Based World Models for Agentic RLDarshan Deshpande3.67
[PDF]On Observation Time for Recovering Latent Hawkes NetworksJonas Linkerhägner, Michele Bortolasi, Lorenzo Baldassari et al.3.67
[PDF]Generative Molecular Morphing for Flexible-Size Design via Unbalanced Optimal TransportMalte Franke, Stefan P. Schmid, Žarko Ivković et al.3.67
[abs]Where Reusable Computation Becomes Detectable: Solution-Frame Path Triage for Modular-Arithmetic GrokkingRuian Lei, Ruoxi Jiang, Marley M Vellasco et al.3.67
[PDF]Training with (Swap) Regret Loss in a Single-Layer Self-Attention Model: A Case Study on the Probability SimplexChanwoo Park, Asuman Ozdaglar3.67
[PDF]Prompts to Proxies: Emulating Human Preferences via a Compact LLM EnsembleBingchen Wang, Zi-Yu Khoo, Jingtan Wang3.67
[abs]ControlJEPA: Principled Trajectory Regularization via Lyapunov Tube LossKhanh T Nguyen, Yen N Pham, Uyen N.B. Vo et al.3.67
[PDF]When to Align, When to Predict: A Phase Diagram for Multimodal LearningIlay Kamai, Hugues Van Assel, Aviv Regev et al.3.67
[abs]Mixture-of-Hierarchical Experts: Optimized Mamba Architecture for Vision DiffusionYejun Jung, Dongyun Kim, Jinsun Park3.67
[abs]Behavioral Probes for Information Flow in LLM SwarmsJunhui Chen, Yu Zhang, Lantian Li et al.3.67
[PDF]Neurosymbolic Learning for Inference-Time ArgumentationGabriel Freedman, Adam Dejl, Adam Gould et al.3.67
[PDF]Flow Matching from Viewpoint of Proximal OperatorsKenji Fukumizu, Wei Huang, Han Bao et al.3.67
[abs]UniDBO: A Unified Dual-Branch One-Step Denoising Framework for Autonomous Driving Scenario GenerationDa Zhao, Yuhang Chen, Jie Sun et al.3.67
[PDF]Geometry-Aware Online Scheduling for LLM Serving: From Theoretical Bound to System PracticeLi Kong, Qi Qi, Yinyu Ye et al.3.67
[PDF]Diffusion fine-tuning with Rewarded Moment Matching DistillationAlexis Jacq, Guillaume Couairon, Quentin Berthet et al.3.67
[abs]A method to automatically discover symbolic local learning rulesAndrea Perin, Fabio Anselmi, Stephane Deny3.67
[PDF]Signed Rectified Flow: Negativity Controlled GenerationRunlong Liao, Baiyu Su, Lizhang Chen et al.3.67
[PDF]Hide-and-Seek in Trajectories: Discovering Failure Signals for VLA Runtime MonitoringSeongheon Park, Wendi Li, Changdae Oh et al.3.67
[PDF]Efficient Learning of Truncated Boolean Product Distributions: Influence to the RescueRohan Chauhan, Ioannis Panageas3.67
[abs]Noise-Level KL Rates for Multi-Marginal Schrödinger Bridge SurrogatesHui Chen, Shen Xu, Vikas Singh3.67
[abs]Few-shot Task Learning via Compositional Concept InferenceHanming Ye, Yiding Song, Yilun Du3.67
[abs]RnR: a meta-solver for causal discovery in undersampled time series dataMohammadsajad Abavisani, Kseniya Solovyeva, David Danks et al.3.67
[PDF]TIDE: Asymmetric Neural Circuits for Stabilized Temporal Inhibitory-Excitatory DynamicsAlexander Kyuroson, Denis Kleyko, Marcus Liwicki3.67
[abs]Relaxation-Aligned State Control for Test-Time Scaling in Generative Combinatorial OptimizationBohao Li, Ying Li, Pei He et al.3.67
[abs]Learning Reusable Options by Decomposing Neural PoliciesParnian Behdin, Reza Abdollahzadeh, Kiarash Aghakasiri et al.3.67
[PDF]BSTabDiff: Block-Subunit Diffusion Priors for High-Dimensional Tabular Data GenerationAl Zadid Sultan Bin Habib, Md Younus Ahamed, Prashnna K Gyawali et al.3.67
[abs]SAFE-DRIFT: Data Selection for Supervised Fine-tuning with Controllable Off-Target DriftsYeo Jin Jung, Yating Liu, Lalchand Pandia et al.3.67
[abs]On the Necessity of Guidance Decay: From Three-Phase Analysis in Gaussian Mixture Models to Dynamic OptimizationYiyu Qiu, Ruofeng Yang, Tong Yu et al.3.67
[PDF]Replicable Constrained BanditsMatteo Bollini, Gianmarco Genalti, Francesco Emanuele Stradi et al.3.67
[PDF]Diversity Combining for Multi-Path LLM ReasoningGuangsheng Yu, Litianyi Zhang, Qin Wang et al.3.67
[abs]One-Shot Private Confidence Regions via ResamplingPo-Ling Loh, Debepsita Mukherjee, Shourya Pandey et al.3.67
[PDF]Selective Disk Bispectrum: A Complete and Rotation Invariant Image DescriptorAdele Lantow, Nina Miolane3.67
[abs]TailDiff: Elicitable Tail-Guided Diffusion for Risk-Sensitive GenerationShuning Zhao, Patrick Wong, Rongshang Li et al.3.67
[abs]Beyond IPS: Reliable Counterfactual Evaluation in Multi-Stage Ad Systems without Logged PropensitiesMohsen Malmir, Mohamed A Radwan, houssam nassif et al.3.67
[abs]How Does Pruning Change Decisions in Large Language Models?Jiang Li, Tian Lan, Chenxi Zhou et al.3.67
[abs]Dynamics-Informed Adaptive Offline RL for Real-Time Tokamak Plasma ControlRohit Sonker, Xiaoyan Hu, Hiro J Kaga et al.3.67
[abs]Beyond Unidirectional: Unsupervised Trajectory Learning for Omnidirectional Controllable Underwater Image EnhancementXiaofeng Cong, Xuhao Guo, Kang Zheng et al.3.67
[abs]Trust What Matters: Language-Conditioned Evidence Routing for Video-IMU Action Question AnsweringTengjun Ni, Xin Yuan, Shenghong Li et al.3.67
[abs]HALO: Homotopy-Augmented Layer Optimization for Stable LLM Supervised Post-trainingMengxiang Zhang, Lingyuan Liu3.67
[abs]Certified Single-Level Reformulation for Tri-Level Cyber-Physical Grid SecurityDebraj Banerjee, Gurunath Gurrala, Kunal Narayan Chaudhury3.67
[abs]Keep or Preempt? Termination-Aware Scheduling for LLM Serving with Speculative DecodingZiyu Cheng, Songtao Guo, Mingyan Li et al.3.67
[PDF]Hitting Time Isomorphism for Multi-Stage Planning with Foundation PoliciesMagnus Victor Boock, Abdullah Akgül, Mustafa Mert Çelikok et al.3.67
[abs]Block-OBS-GS: Exact Per-Block Joint Brain Surgery with Gauss–Seidel Refinement for LLM PruningYuwen Huang, Xiang Pan3.67
[abs]GeoPMR: Preserving Relational and Hierarchical Geometry in Multimodal Molecular Representation LearningLusheng Li, Menglin Yang3.67
[abs]MaxIM: Maximally Informative Incremental Summarization via Reinforcement LearningJihwan Jeong, Guy Tennenholtz, Yinlam Chow et al.3.67
1 If this project is interesting to you, reach out at [email protected].