🏀Ph.D. candidate
Zhejiang University
About Me
Yefei He is a final-year Ph.D. candidate at Zhejiang University, supervised by Prof. Hong Zhou. He is also closely collaborated with Prof. Bohan Zhuang. His research focuses on developing efficient AI algorithms for computer vision and natural language processing tasks, striving to enhance AI’s practicality in real-world scenarios.
Interests
- RL for Visual Generation
- Efficient Visual Generation (Parallel Decoding, Quantization, Sparse Attention)
Education
PhD Electronic Information Technology
Zhejiang University
BSc Instrument Science
Zhejiang University
Recent Publications
(2025).
Neighboring Autoregressive Modeling for Efficient Visual Generation.
ICCV 2025.
(2024).
ZipAR: Accelerating Autoregressive Image Generation through Spatial Locality.
ICML 2025.
(2024).
ZipVL: Efficient Large Vision-Language Models with Dynamic Token Sparsification and KV Cache Compression.
ICCV 2025.
(2024).
ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification.
NeurIPS 2024.
(2024).
MiniCache: KV Cache Compression in Depth Dimension for Large Language Models.
NeurIPS 2024.