Hi 👋 ~

About Me

I am a junior student at Zhejiang University, pursuing a Bachelor of Computer Science and Technology with an honors degree from Chu Kochen Honors College. I expect to receive my degree in June, 2026.

I am fortunate to be a research intern at Nanyang Technological University (NTU) advised by Prof. Mengmi Zhang. And in future I will be a research intern at Berkeley AI Research (BAIR) lab, UC Berkeley, advised by Xudong Wang and Prof. Trevor Darrell.

My research interests lie in the Computer Vision and Generative Model. Specifically, I’m currently interested in Controllable Text-to-Image Generation, Multi-modal Alignment.

My Ultimate goal is to build a model that can Make Everybody be his/her Own Artist Easily. If you have any idea or want to discuss/collaboration, feel free to contact me!

Publication

See in my publication list here.

Projects

• Author of Iterative Editing Mode in MIGC: Multi-Instance Generation Controller for Text-to-Image Synthesis.

Miscellaneous

I’m an ACGN lover QAQ so I’m enthusiastic about the Image, Video, Music and Vocal Generation, especially the model which have a good controllability.

Previously, I’ve also been a member of the ZJU ACM/ICPC team, and I’ve reached a rating of 2478 on Codeforces. You can check my old blog here. There are some old articles about my competitive programming experience :(.