Papers published: 'VCA: Video Curious Agent for Long Video Understanding' (ICCV 2025), 'Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens' (arXiv, 2025), etc.
Research Experience
Summer internship at Samsung in Mountain View, California, 2025; started PhD journey at UMass Amherst in September 2024.
Education
PhD: University of Massachusetts Amherst, supervised by Prof. Chuang Gan and Prof. Hao Zhang; Master's degree: Tsinghua University in Computer Science, mentored by Prof. Yang Liu and Prof. Peng Li; Bachelor's degree: School of Economics and Management at Tsinghua University.
Background
Research interests: embodied intelligence and multi-modal foundation models; currently focusing on building lifelong embodied agents executable in real-world environments.
Miscellany
Contact information includes email, CV link, and social media accounts.