I am a third-year Ph.D. student at UCSD, advised by Dr. Zhuowen Tu. I have been working on generative models, especially controllability (BDM, Omni-ControlNet, SemLayer), image (Science-T2I, OverLayBench, OverLay++), and video (VideoNSA, LIFT, RECAP-Forcing). I'm now also interested in visual agents (EditAgent & ongoing!) and agentic robotics (ongoing!). For more details, check out my Research Notes.
I was a Research Intern at Adobe in 2026 Summer, working with Dr. Mingze Xu, Dr. Tianyu Wang, Dr. Jiteng Mu, and Dr. Jialu Li; at Adobe in 2025 Summer, working with Dr. Zhaowen Wang and Dr. Li-Yi Wei, Dr. Nanxuan Zhao, and Dr. Cuong Nguyen; and at NYU Courant in 2024 Fall, working with Dr. Saining Xie. During my undergraduate, I was fortunate to work with Dr. Xiangnan He.
RECAP-Forcing: REtaining Content APpearances for Long Video Generation
Preprint 2026
  Website   PDF   Code
SemLayer: Semantic Generative Segmentation and Layer Reconstruction for Abstract Icons
CVPR 2026
  Website   PDF   Code
OverLayBench: A Benchmark for Layout-to-Image Generation with Dense Overlaps
NeurIPS 2025
  Website   PDF   Code
Omni-ControlNet: Dual-stage Integration for Conditional Image Generation
CVPRW 2024
  Website   PDF   Code