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 title:benchmark presentation>=3sort:ratingnewestmost read
[PDF]What to Forget in Unlearning? Forget Set Curation for Language ModelsAnimesh Jha, Arpandeep Khatua, Youssef Allouah et al.3.00
[abs]When Prompts Override Vision: Instruction-Induced Hallucinations in LVLMsPegah KHAYATAN, Jayneel Parekh, Arnaud Dapogny et al.3.00
[PDF]Structured Sparse Memory for Recurrent ReasoningZixuan Zhao, Sam Wheeler, Neil Getty et al.3.00
[abs]Information Propagation via Sign-Flip DynamicsHyunwoo Lee, Hyojae Lim, Dohyun Kwon3.00
[PDF]Controlling for Omitted Variable Bias in Deep Neural NetworksManuel Pfeuffer, Roshan P Rane, Kerstin Ritter et al.3.00
[PDF]When and How to Canonize: a Generalization PerspectiveYonatan Sverdlov, Benjy Friedmann, Snir Hordan et al.3.00
[abs]Leaner transformers can easily learn to clusterCharlotte Park, Kenneth Clarkson, Lior Horesh et al.3.00
[PDF]DoAtlas-1: A Causal Compilation Paradigm for Clinical AIYulong Li, Jianxu Chen, Xiwei Liu et al.3.00
[PDF]Probabilistic Tiny Recursive ModelAmin Sghaier, Ali Parviz, Alexia Jolicoeur-Martineau3.00
[abs]ESENSC: A Polynomial-Time Axiomatic Alternative to SHAPKazuhiro Hiraki, Shinichi Ishihara, Takumi Kongo et al.3.00
[PDF]Structural Rationale Distillation via Reasoning Space CompressionJialin Yang, Jiankun Wang, Jiajun Wu et al.2.25
[abs]Think about how AIs think about themselvesRaymond Douglas, Jan Kulveit, Ondřej Havlíček et al.
[PDF]ScrapeGraphAI-100k: Dataset for Schema-Constrained LLM GenerationWilliam Brach, Francesco Zuppichini, Lorenzo Padoan et al.
[abs]RASS: Risk-Audited Budget Selection for Compact NeRF Benchmark SubsetsAhmad AlMughrabi, Flavià Serret, Ricardo Marques et al.
[abs]CyberDualEval: Measuring Dual-Use Cyber Risks in Frontier Language ModelsMagnus Saebo, Francesco Piccoli, Maxwell Watson et al.

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

Privacy