Zhikai Li

4

Papers

31

Total Citations

Papers (4)

A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMs

K-Sort Arena: Efficient and Reliable Benchmarking for Generative Models via K-wise Human Preferences

CacheQuant: Comprehensively Accelerated Diffusion Models

Unsupervised Learning for Class Distribution Mismatch