Published several papers including 'Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction' (ICML 2025), 'AgentTrek: Agent Trajectory Synthesis via Guiding Replay with Web Tutorials' (ICLR 2025 Spotlight), 'Lemur: Harmonizing Natural Language and Code for Language Agents' (ICLR 2024 Spotlight), and more; received PaperDigest Most Influential Papers and ICBS 2024 Frontiers of Science Award.
Research Experience
Contributed to multiple research projects such as Qwen3 Coder, Qwen2.5-VL, Aguvis, AgentTrek, and Lemur, serving as a core contributor in these projects.
Education
Third-year PhD Student at the University of Hong Kong
Background
Research interests include advancing AI from digital workflow automation to fully autonomous agents. Research directions span across building models that can interpret diverse digital interfaces, designing and training agents that operate efficiently through command-line and API-based interfaces, and pushing the frontier of agents that can interact in human-designed GUI environments.