Search

Tour
News
People
Publications

Hong Zhou

Latest

ZipAR: Accelerating Auto-regressive Image Generation through Spatial Locality
ZipVL: Efficient Large Vision-Language Models with Dynamic Token Sparsification
EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Models
ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification
Bivit: Extremely compressed binary vision transformers
PTQD: Accurate Post-Training Quantization for Diffusion Models

© 2025 ZIP Lab. Designed and Developed by Weijie Wang. This work is licensed under CC BY NC ND 4.0

Published with Hugo Blox Builder — the free, open source website builder that empowers creators.

Cite