by Yuchen Mao Papers
2 papers found
Conference
AgentTrek: Agent Trajectory Synthesis via Guiding Replay with Web Tutorials
Yiheng Xu, Dunjie Lu, Zhennan Shen et al.
ICLR 2025arXiv:2412.09605
54
citations
Sharpness-Aware Minimization Efficiently Selects Flatter Minima Late In Training
Zhanpeng Zhou, Mingze Wang, Yuchen Mao et al.
ICLR 2025arXiv:2410.10373
11
citations