I am currently a Ph.D. student at The Hong Kong Polytechnic University. Previously, I obtained my MSc from Dalian University of Technology under the supervision of Prof. Huchuan Lu. My research focuses on Large Language Models, Multimodal GUI Agents, and Diffusion Models for Video Generation.

My recent research interests include:

• Multimodal GUI Agents: InfiGUIAgent, InfiGUI-R1, InfiGUI-G1 - advancing GUI automation from reactive actors to deliberative reasoners.
• Large Language Models: Curse of Depth, Mix-LN, Outlier-weighted Layerwise Sampling - improving LLM training and fine-tuning.
• Diffusion Models for Generation: TrackDiffusion, MoTrans, DreamMix - controllable video and image generation.
• Autonomous Driving: Corner case evaluation and trajectory generation.