🏀Ph.D. candidate
Zhejiang University
About Me
Yefei He is a third-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
- Efficient Visual Generation
- Model Compression (especially Quantization & Binarization)
Education
PhD Electronic Information Technology
Zhejiang University
BSc Instrument Science
Zhejiang University
Recent Publications
(2024).
ZipAR: Accelerating Autoregressive Image Generation through Spatial Locality.
arXiv preprint arXiv:2412.04062.
(2024).
ZipVL: Efficient Large Vision-Language Models with Dynamic Token Sparsification and KV Cache Compression.
arXiv preprint arXiv:2410.08584.
(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.
(2023).
EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Models.
ICLR 2024 (spotlight).