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]Learning Sparse Compositional Functions with Norm-Constrained Neural Networksshuo HUANG, Lorenzo Fiorito, Lorenzo Rosasco et al.3.67
[abs]No Model Required: Text Entropy Rate Filtering Prevents Iterative Fine-Tuning CollapseLewis Mitchell3.67
[PDF]Balancing Image Compression and Generation with Bootstrapped TokenizationHaozhe Chi, Jinghan Li, Hao Jiang et al.3.67
[abs]Same Function, Different Mechanism: Implementation-Local Geometry Beyond AccuracyMiroslav Lžičař3.67
[abs]What Does an Observability Forecasting Foundation Model Know?Dhyey Mavani, Tairan Ji, Rian Atri3.67
[abs]Breadcrumbing Search Agents: Per-Turn Scheming Over Long-Horizon TrajectoriesXuebin Li, Hanqing Zhao, Siyuan Liang et al.3.67
[PDF]Sharper Guarantees for Misspecified Kernelized Bandit OptimizationDavide Maran, Csaba Szepesvari3.67
[abs]Paleoinspired Vision: From Exploring Colour Vision Evolution to Inspiring Camera DesignYijie Lu, Zhimin Zong, Junjie Zhang et al.3.67
[abs]Shellsort as Multi-Scale Relaxation: Learning Spectrum-Matched Gap SchedulesQingyun Li, Ruoyun Li, Yunqi Li et al.3.67
[abs]End-to-End Verification of Neuro-symbolic Automata via Contrastive Logit-GapsAbdelrahman Hekal, Vasileios Manginas, Nikolaos Manginas et al.3.67
[PDF]Convex Compositional Reasoning ModelsMeir Roketlishvili, Semen Semenov, Maksim Bobrin et al.3.67
[abs]MCM-DM: Towards Better Spatio-Temporal Event Representation Learning via Discrete Morse TheoryYuanheng Zhang, Jennifer Rozenblit, Chenguang Yang et al.3.67
[PDF]Learning from the Self-future: On-policy Self-distillation for dLLMsYifu Luo, Zeyu Chen, Haoyu Wang et al.3.67
[abs]Beyond MSE: Differentiable Complexity Priors for Structure-Preserving Neural DenoisingXiangyu Jiang, Jie Huang3.67
[abs]RoLL: Robust Low-Rank Learning via Nesterov MomentumZhaojun Hu, Wenchen Liu, Ting Wei et al.3.67
[abs]Two is better than one: designing heterogeneous scales in binary rating systemsLiren Shan, Alec Sun, Jingyan Wang3.67
[abs]Physics-Conditioned Video Diffusion with Kinematic Priors for Fusion Capsule PolishingShashank Galla, Abhishek Hanchate, Monika Biener et al.3.67
[abs]Differentiable Range-Partition Entropy for Entropy-Sensitive Geometric AlgorithmsIbne Farabi Shihab, Sanjeda Akter, Anuj Sharma3.67
[PDF]Perceive, Interact, Reason: Building Tool-Augmented Visual Agents for Spatial ReasoningChangye Li, Meng Lu, YI WU et al.3.60
[abs]AnyEdit: A Unified Framework for Speech and Singing Voice Editing with Real-World Environmental ConsistencyYunjia Zhang, Junan Zhang, Jing Yang et al.3.60
[abs]Does Inference-Time Reasoning Really Improve Video Understanding?Zhuohao Yu, Yu Zhou, Zhecan Wang et al.3.60
[abs]Membrane Sensitivity and Deployment Fragility of Learnable Time Constants in Spiking Neural NetworksCHIU-CHANG CHENG, Ya-Ning Chang, Chao-Hung Wang3.60
[abs]Ask in the Crowd: Differentially Private LLM Inference via Dummy-Augmented ShufflingZhihao Liu, Zixiong Guo, Shuo Shao et al.3.60
[abs]Canonical Predictive Quotients: A Theory of Prediction under Hidden Predictive State Uncertainty with ICL ImplicationsHiroyuki Kasai3.60
[PDF]Risk-Averse Online POMDP Planning via CVaR of the Immediate Cost with Performance GuaranteesYaacov Pariente, Vadim Indelman3.60
[abs]BRIDGE: Brain-Vision Representation Integration through Depth and Granularity EncodingChenyuan Hong, Binghao Ye, Yufei Guo et al.3.50
[PDF]VLA-Corrector: Lightweight Detect-and-Correct Inference for Adaptive Action HorizonYi Pan, Miao Pan, Qi Lu et al.3.50
[abs]TENET: Time-point Encoding Network for Multivariate Time Series Anomaly DetectionDongchan Cho, Juwon Hwang, Keumyeong Kang et al.3.50
[abs]ASAP: Assembly-Source Aligned Pseudocode Refinement For Binary DecompilationYujian Zhuang, Dehong Gao, Qichao Zhang et al.3.50
[PDF]Code2World: A GUI World Model via Renderable Code GenerationYuhao Zheng, Li'an Zhong, Yi Wang et al.3.50
[PDF]SCOPE-RL: Stable and Quantitative Control of Policy Entropy in RL Post-TrainingChen Wang, Zhaochun Li, Bai Jionghao et al.3.50
[PDF]D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion ModelsDengyang Jiang, Xin Jin, Dongyang Liu et al.3.50
[abs]ElasticFit: Fit-Aware 3D Object Insertion via VLM Reasoning and Generative AdaptationTzu-Hsin Hsieh, Ricardo Marroquim3.50
[abs]Coverage-Verified Sparse Attention: Closed-Loop Quality Control for Long-Context LLM DecodingYan-Cheng Li, Chun-Yi Lee3.50
[PDF]KG-Guard: Graph-Based Hallucination Detection for Knowledge Base Question AnsweringAlbert Sawczyn, Piotr Bielak, Tomasz Kajdanowicz3.50
[PDF]Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor’s Internal StatesYunho Choi, Jongwon Lim, woojin Ahn et al.3.50
[PDF]Reward Bias Substitution: Single-Axis Bias Mitigations Redirect Optimization PressureMax Lamparth, Daniel Fein, Andreas Haupt et al.3.50
[PDF]Stay Fair! Ensuring Group Fairness in Diffusion Models Across Guidance ScalesMyeongsoo Kim, Eunji Kim, Minwoo Chae et al.3.50
[abs]OT-Robust3DVLA: A Wasserstein Barycenter is the Right Inductive Bias for Robust Multi-View 3D Vision-Language-Action PoliciesPawan Kumar3.50
[PDF]CAB: Accelerating Flow and Diffusion Sampling via Rectification and Corrected Adams-BashforthAnuska Roy, Pravin Ramachandran Nair3.50
[abs]Spectral Unlearning: Transformer Structure-Preserving Updates for Language ModelSung Il Choi, Junhao Cai, Dohun Kim et al.3.50
[abs]SVG-3D: Mining Decision Boundaries with Generative Splatting Priors for Zero-Shot 3D ClassificationRyo Umagami, Shohei Ohsawa3.50
[abs]Replicas-as-Variables: A Planner for Throughput-Optimal Routing in LLM DeploymentShaojiang Wang, Geer Yang, Wenbo Wang et al.3.50
1 If this project is interesting to you, reach out at [email protected].