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 diffusion rating>=3sort:ratingnewestmost read
[abs]Differentiating Network Design Objectives for Balancing Cost and DistanceZishang Chen, Longhe Lin, Zhiyuan Julian Su et al.4.33
[abs]A Hierarchical World Model for DrivingSudhanshu Mittal, Arian Mousakhan, Silvio Galesso et al.4.33
[PDF]RelAgent: LLM Agents as Data Scientists for Relational LearningXingyue Huang, Louis Tichelman, Jinwoo Kim et al.4.33
[abs]Identifiable alignment of unpaired representationsStas Syrota, Albert Lopez i Serrano, Johanne Franck et al.4.33
[abs]Long Video Instructional Editing in the WildYiqi Lin, Guoqiang Liang, Ziyun Zeng et al.4.33
[PDF]Ares: Adaptive Reasoning Effort Selection for Efficient LLM AgentsJingbo Yang, Bairu Hou, Jiayun (Peter) Wang et al.4.33
[PDF]OpenSearch-VL: An Open Recipe for Frontier Multimodal Search AgentsShuang Chen, Kaituo Feng, Hangting Chen et al.4.33
[PDF]Min-Max Optimization Requires Exponentially Many QueriesMartino Bernasconi, Matteo Castiglioni, Andrea Celli et al.4.33
[PDF]Structured Transforms for Low-Overhead Quantization of Language ModelsDaria Cherniuk, Alexander Rudikov, Boris Kashin et al.4.33
[abs]On Communication-Efficient Training of Ensembles in Federated LearningValery Parfenov, Mikhail Aleksandrov, Daniil Medyakov et al.4.33
[abs]Residual Expertise Is Not Decision ValueNidhish Shah, Shaurjya Mandal, Asfandyar Azhar4.33

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

Privacy