Transformation-Invariant Learning and Theoretical Guarantees for OOD Generalizationby Omar Montasser, Han Shao, Emmanuel AbbeFirst submitted…
MDCure: A Scalable Pipeline for Multi-Document Instruction-Followingby Gabrielle Kaili-May Liu, Bowen Shi, Avi Caciularu, Idan…
Gradient-free training of recurrent neural networksby Erik Lien Bolager, Ana Cukarska, Iryna Burak, Zahra Monfared,…
ProTransformer: Robustify Transformers via Plug-and-Play Paradigmby Zhichao Hou, Weizhi Gao, Yuchen Shen, Feiyi Wang, Xiaorui…
Does equivariance matter at scale?by Johann Brehmer, Sönke Behrends, Pim de Haan, Taco CohenFirst submitted…
Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Tasksby Michael Matthews, Michael…
Improved convergence rate of kNN graph Laplaciansby Yixuan Tan, Xiuyuan ChengFirst submitted to arxiv on:…
Grounding by Trying: LLMs with Reinforcement Learning-Enhanced Retrievalby Sheryl Hsu, Omar Khattab, Chelsea Finn, Archit…
COMAL: A Convergent Meta-Algorithm for Aligning LLMs with General Preferencesby Yixin Liu, Argyris Oikonomou, Weiqiang…
Partial Channel Dependence with Channel Masks for Time Series Foundation Modelsby Seunghan Lee, Taeyoung Park,…