Author

Zhen Zhao

University of Sydney

h-index 16 Homepage View on Semantic Scholar

We have 1 of 37 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Jul 2026

SigLIP-HD by Fine-to-Coarse Supervision

This work studies an interesting problem: how to achieve fine visual perception under lower cost without larger images, and builds this framework on the advanced SigLIP 2 model, which consistently delivers stronger results than the baseline model, especially on OCR-related tasks.

Lihe Yang, Zhen Zhao, Hengshuang Zhao · 0 citations