I am a third-year Ph.D. Candidate in the Robotics Perception and Learning Lab (RIPL) at Georgia Institute of Technology advised by Prof. Zsolt Kira. Previously, I was fortunate to work with Prof. Hongteng Xu in Structured Data Science Lab (SDSL) at Renmin University of China. My research aims to improve the generalizability of foundation models, especially vision–language models. I am particularly interested in robust fine-tuning, reasoning, and vision–language–action models.

News

• [2025.04] I received the CVPR 2025 Travel Support Award, thanks! See you in Nashville!
• [2025.04] I passed my Qualifying Exam and officially become a Ph.D. Candidate!
• [2025.02] Our paper “FRAMES-VQA: Benchmarking Fine-Tuning Robustness across Multi-Modal Shifts in Visual Question Answering” was accepted by CVPR 2025!
• [2025.01] Our paper “Directional Gradient Projection for Robust Fine-tuning of Foundation Models” was accepted by ICLR 2025!
• [2024.09] Our paper “Rethinking Weight Decay for Robust Fine-Tuning of Foundation Models” was accepted by NeurIPS 2024.
• [2023.08] I joined Georgia Institute of Technology for the Machine Learning PhD Program!
• [2023.06] I graduated from the School of Statistics at Renmin University of China with a Bachelor’s degree in Science!
• [2023.02] I became a research intern at Microsoft Research AI4Science.