Papers published in ICLR'24, ICLR'23, NeurIPS'22, NeurIPS'24, EMNLP'24, ACL'23, CVPR'25, CVPR'24, ECCV'24, ICML'25, NEJM AI'24, npj Digital Medicine'19, etc.; selected as one of the Rising Stars in Data Science; participated in CVPR 2025 Doctoral Consortium; organized multiple workshops such as DCVLR: Data Curation for Vision Language Reasoning challenge, DataWorld Workshop, XAI4CV Workshop, etc.
Research Experience
Currently a postdoctoral scholar at Stanford University, working with Professors Serena Yeung-Levy, Ludwig Schmidt, and Emma Lundberg. Previously, received Ph.D. from Stanford University.
Education
Ph.D. in Computer Science from Stanford University, advisors include Professors Serena Yeung-Levy, Ludwig Schmidt, Tatsunori Hashimoto, Emma Lundberg, and John Cioffi; B.E. in Computer Science from Tsinghua University.
Background
Multimodal Machine Learning & Science Applications, currently a postdoctoral scholar at Stanford University. Research interests include embedding-based multimodal foundation models, generative multimodal foundation models, agentic/compounding systems, and generative models for science.