Author

Zhongshu Chen

h-index 5 View on Semantic Scholar

We have 1 of 23 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.

Jul 2026

U-shaped Multi-granularity Learning for Vision-Language Models

UPrompt is proposed, a U-shaped multi-granularity prompt learning framework for vision-language models that constructs parallel multi-granularity representations in both visual and textual modalities and maintains competitive performance with minimal overhead and matching PSRC with 1/3 cost.

Biao Chen, Yunqian Yu, Xiang-Xu Zhao et al. · arXiv.org · 0 citations