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]Measuring Robustness and Efficiency in a Connectome-Constrained Fly Visual System Model on a Collision-Detection TaskAlexandre Garcia-Duran, Alejandro Rodriguez-Garcia, Manuel Molano-Mazon et al.3.67
[PDF]Point Tracking Improves World Action ModelsJiarui Guan, Wenshuai Zhao, Yue Pei et al.3.67
[abs]Parasite Features: Causal Abstraction Through Spurious PathwaysDenis Sutter, Qing Yao, Sasha Boguraev et al.3.67
[PDF]FM-ChangeNet: Learning Change through Pathwise Feature TransportRoie Kazoom, George Leifman, Genady Beryozkin3.67
[abs]ExperiGen: Agentic Hypothesis Discovery from Observational DataJishu Sen Gupta, Harini S I, Somesh K Singh et al.3.67
[PDF]DiLaDiff: Distilled Latent-augmented Diffusion for Language ModelingJean-Marie Lemercier, Tomas Geffner, Morteza Mardani et al.3.67
[PDF]PanoWorld: Towards Spatial Supersensing in 360◦ Panorama WorldChangpeng Wang, Xin Lin, Junhan Liu et al.3.67
[abs]Thompson Sampling using Prior-fitted Diffusion TransformersSihwa Park, Jingsen Zhu, Vinamr Jain et al.3.67
[PDF]PLATO: Pointer Learner for Agent and Task OpennessAlireza Saleh Abadi, Leen-Kiat Soh, Daniel A Redder et al.3.67
[PDF]SkipSR: Faster Super-Resolution with Token SkippingRohan Choudhury, Shanchuan Lin, Jianyi Wang et al.3.67

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

Privacy