Publications: 'Video Understanding with Large Language Models: A Survey' (TCSVT, 2025), 'MMPerspective: Do MLLMs Understand Perspective? A Comprehensive Benchmark for Perspective Perception, Reasoning, and Robustness' (NeurIPS, 2025).
Research Experience
Interned at Amazon, ByteDance, and Tencent.
Education
B.Eng. from SUSTech in 2023, supervised by Prof. Feng Zheng; Currently pursuing a Ph.D. at the University of Rochester, advised by Prof. Chenliang Xu.
Background
Research Interests: Video Understanding, Large Language Models; Field: Computer Vision; Bio: She is a Ph.D. student at the University of Rochester, advised by Prof. Chenliang Xu.