Auto-Intent: Automated Intent Discovery and Self-Exploration for Large Language Model Web Agentsby Jaekyeom Kim, Dong-Ki…
Meta-Learning Adaptable Foundation Modelsby Jacob L. Block, Sundararajan Srinivasan, Liam Collins, Aryan Mokhtari, Sanjay ShakkottaiFirst…
Flow-DPO: Improving LLM Mathematical Reasoning through Online Multi-Agent Learningby Yihe Deng, Paul MineiroFirst submitted to…
Where Do Large Learning Rates Lead Us?by Ildus Sadrtdinov, Maxim Kodryan, Eduard Pokonechny, Ekaterina Lobacheva,…
SceneGenAgent: Precise Industrial Scene Generation with Coding Agentby Xiao Xia, Dan Zhang, Zibo Liao, Zhenyu…
Generating Realistic Tabular Data with Large Language Modelsby Dang Nguyen, Sunil Gupta, Kien Do, Thin…
L3Ms – Lagrange Large Language Modelsby Guneet S. Dhillon, Xingjian Shi, Yee Whye Teh, Alex…
Personalized Federated Learning with Mixture of Models for Adaptive Prediction and Model Fine-Tuningby Pouya M.…
Reducing the Scope of Language Models with Circuit Breakersby David Yunis, Siyu Huo, Chulaka Gunasekara,…
UFT: Unifying Fine-Tuning of SFT and RLHF/DPO/UNA through a Generalized Implicit Reward Functionby Zhichao Wang,…