Hey there! I'm a first-year PhD student in Computer Science at University of Illinois
Urbana-Champaign
(UIUC), working
with Prof.
Yue Guo and Prof. Heng Ji.
I work on Multimodality (Language, Vision) and Agents.
My recent research focuses on agentic AI,
grounded
multi-modal reasoning, and controllable multi-modal generation.
Previously, I did my Master at University of California, Los Angeles (UCLA),
where I worked with Prof.
Nanyun
Peng,Prof.
Kai-Wei
Chang and Prof. Yiwei
Wang.
Before that, I got my B.S.in Computer Science and Data Science (double
major) at Purdue University.
My long-term research vision is to build a multisensory assistant capable of reasoning across
modalities and
continuously acquiring new skills and knowledge to adapt to diverse, evolving contexts in real time. I
believe in
Adaptive Intelligence—the ability of intelligent systems to invent, learn, and generalize
beyond their training
distribution.
Driven by both curiosity and social responsibility, I have also worked on AI applications for human
health
and social good, exploring how intelligent systems can meaningfully benefit the next generation.
My current research focuses on enhancing agents (e.g. language agent, visual agent, embodied agent,
etc.) with the learning-on-the-job capability: long-horizon run-time learning for
adaptive
multimodal agents that update their knowledge and behavior from in-situ feedback and new context.
My recent works mainly span across two directions:
