Publications: MEXA (EMNLP25), SeViLA (NeurIPS23), CREMA (ICLR25), etc.; Awards: SciVideoBench won the best benchmark paper award at ICCV 2025 KnowledgeMR workshop; Projects: Involved in various research on multimodal reasoning, visual editing/generative methods, and multimodal representation/feature engineering.
Research Experience
Internships: MIT-IBM Watson AI Lab (2021), Amazon (2023), Adobe Research (2024), Google DeepMind (2025).
Education
Ph.D.: University of North Carolina at Chapel Hill, Computer Science, Advisor: Prof. Mohit Bansal; B.S.: Shanghai Jiao Tong University.
Background
Research Interests: Multimodal AI, exploring how to enable AI models to perceive and understand the world in a way similar to or beyond humans. Professional Field: Computer Science. Brief Introduction: Currently a fourth-year Ph.D. student at the University of North Carolina at Chapel Hill, advised by Prof. Mohit Bansal.