acceptodds

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.

Try review:"data leakage"sort:ratingnewestmost read
[abs]Causal Discovery under Time-Varying DelaysLénaïg Cornanguer, David Kaltenpoth, Jilles Vreeken4.33
[abs]Substrata: Know What You Don't KnowYizhou Li, Jinyi Xu, Qingyi Yang et al.4.33
[PDF]LensDesigner: A Self-Improving Agent for Optical Lens DesignLei Sun, Haoran Liang, Dannong Xu et al.4.33
[PDF]AdaOcc: Adaptive 3D Occupancy Prediction for Embodied TasksJinglong Wang, Yunjie Wang, Zhiyang Zhang et al.4.33
[PDF]RigidFormer: Learning Rigid Dynamics using TransformersZhiyang Dou, Minghao Guo, Haixu Wu et al.4.33
[PDF]Graph-Regularized Sparse Autoencoders for LLM Safety SteeringJehyeok Yeon, Federico Cinus, Yifan Wu et al.4.33
[PDF]Drift Q-LearningAchraf Anas El Houssaini, Mohamad Hosein Danesh, Amin Abyaneh et al.4.33
[PDF]Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive BiasMohua Das, Pierfrancesco Beneventano, Shibshankar Dey et al.4.33
[PDF]Driving Video Retrieval for Complex Queries with Structured GroundingManyi Yao, Sparsh Garg, Christian Shelton et al.4.33
[abs]AEGIS: Almost Surely Safe Offline Reinforcement LearningJunseo Lee, Hyeokjin Kwon, Songhwai Oh4.33
[abs]Antibody Generation via Redistributed Latent DiffusionAndrey Shevtsov, Viacheslav Meshchaninov, Pavel Strashnov et al.4.33
[abs]Where to Approximate in Neurosymbolic Inference?Samy Badreddine, Emile van Krieken, Luciano Serafini et al.4.33

1 If this project is interesting to you, reach out at [email protected].

Privacy