Hang Gao
Hang Gao is an assistant professor at the Institute of Software, Chinese Academy of Sciences, where he has held the position since 2024 after completing his PhD there. His research focuses on machine learning, graph learning, and causal learning, with recent work appearing at venues such as AAAI 2025. He has published on topics including heterogeneous graph representation learning via large language models and causal inference in graph neural networks, and has contributed to research on trajectory-level credit aliasing in vision-language-action reinforcement learning.
“We characterize and formulate trajectory-level credit aliasing in outcome-driven VLA reinforcement learning, where rollouts with different stage progress can receive the same final-outcome advantage, causing successful preceding actions and later failed actions to be updated with the same advantage.”
Source→AI-extracted from podcast / newsletter / paper summaries. May contain errors.