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 "reward hacking" OR "specification gaming"sort:ratingnewestmost read
[abs]Debiased DPO for Diffusion ModelsDuc Khiem Pham, Quang Nguyen, Tung D Nguyen et al.4.00
[PDF]Equilibrium Forcing: Adaptive Video Generation Without Noise ConditioningHansen Lillemark, Alex Rojas, Zachary Novack et al.4.00
[abs]DynaPFN: Zero-Shot Dynamical System Forecasting with Tabular Prior-Fitted NetworksChiara Roverato, Joseph Cotnareanu, Pablo Piantanida et al.4.00
[PDF]Next Forcing: Causal World Modeling with Multi-Chunk PredictionGangwei Xu, Qihang Zhang, Jiaming Zhou et al.4.00
[PDF]Tight Sample Complexity for Low-Degree and Sparse Boolean PolynomialsJasper van Doornmalen, Mathieu Molina, Victor Verdugo et al.4.00
[abs]Scaling Laws for Synthetic Pretraining in Radio-Map PredictionKhoren Petrosyan, Artashes Mkrtchyan, Rafayel Mkrtchyan et al.4.00
[PDF]The Symmetries of Three-Layer ReLU NetworksJohanna Marie Gegenfurtner, Moritz Grillo, Guido Montufar4.00
[abs]A Private Empirical Defense Against Privacy AuditsSaloni Modi, Srivi Balaji, Yusong Zhu et al.4.00
[abs]Adaptive Random Forests from Online Learning and Testing by BettingSalim I. Amoukou, Saumitra Mishra, Manuela Veloso4.00
[PDF]Why Invariance is Not Enough for Biomedical Domain Generalization and How to Fix ItSebastian Diaz, Polina Golland, Elfar Adalsteinsson et al.4.00

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

Privacy