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
[abs]FairSplit: Decomposing the Embedding Space for Fair ClassificationAndrii Shkabrii, Anna Beer, Ylli Sadikaj et al.4.67
[PDF]Predictive–Generative Drift Decomposition for Speech Enhancement and SeparationJulius Richter, Yoshiki Masuyama, Christoph Boeddeker et al.4.67
[abs]Unbounded Streaming Text-To-Speech with Prefixed Sliding Window AttentionThéodor Lemerle, Diego Torres Guarin, Téo Guichoux et al.4.67
[abs]StaDy: Factorizing the World into Static and Dynamic via Likelihood MatchingThomas Ressler-Antal, Frank Fundel, Malek Ben Alaya et al.4.67
[abs]VAMIRec: Value-Aware Memory Intervention for Continual RecommendationXudong Zhao, Xiaolong Xu, Haolong Xiang et al.4.67
[PDF]PPO in the Fisher-Rao geometryRazvan-Andrei Lascu, David Siska, Lukasz Szpruch4.67
[PDF]Mitigating Over-squashing without Rewiring: A Sheaf Effective Resistance PerspectiveAndré Ribeiro Guimarães, Germano Barcelos, Amauri Souza et al.4.67
[PDF]DegBins: Degradation-Driven Binning for Depth Super-ResolutionZhiqiang Yan, Zhengxue Wang, Jian Yang et al.4.67
[PDF]A Free Lunch in LLM Compression: Revisiting Retraining after PruningMoritz Wagner, Christophe Roux, Max Zimmer et al.4.67
[abs]Do Diffusion Models Learn to Generalize Basic Visual Skills?Amish Sethi, Boya Zeng, Wenhao Chai et al.4.67

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

Privacy