I am a Ph.D. student in Computer Science at Iowa State University, advised by Prof. Yang Li. I received my M.S. and B.Eng. in Computer Science from Zhejiang University, where I worked with Prof. Zhou Zhao.
My research centers on efficient multimodal models, with broader interests in computer vision and multimodal learning. My long-term goal is to build AI systems that perceive and understand the physical world reliably and efficiently.
arXiv · 2026
Training-free video token compression that removes global redundancy while preserving temporal coherence, including at token retention ratios as low as 1%.
IEEE TPAMI · 2026
Context-rich object representations and explicit identifiers unify 3D grounding, captioning, and spatial reasoning without task-specific fine-tuning.
CVPR · 2025
A large-scale simulated manipulation dataset and a grounding-aware robot policy that uses object masks to turn vision-language priors into actions.
NeurIPS · 2024
Object identifiers connect point clouds and multi-view images to language for 3D grounding, captioning, and question answering. Ranked first on ScanRefer and Scan2Cap in September 2024.
NAACL · 2025
Chat-3D · published version
NeurIPS Datasets and Benchmarks · 2024
Research Engineer · Shanghai, China
Research Intern · Shanghai, China
Mentors: Dr. Yilun Chen and Dr. Jiangmiao Pang
Research Intern · Beijing, China
Mentor: Dr. Tong Shen
Ph.D. in Computer Science · Advisor: Prof. Yang Li
M.S. in Computer Science · Advisor: Prof. Zhou Zhao
B.Eng. in Computer Science
Conference Reviewer: ICML, ICLR, NeurIPS, CVPR, ECCV, ICRA, AAAI
Journal Reviewer: TMLR, TIP, RA-L
