Author

Jiayang Yu

View on Semantic Scholar

1 paper indexed here

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 Aug 2026

RAGOCR: Optical Compression of Retrieval-Augmented Text via Visual Representation

This work introduces RAGOCR, a novel framework that compresses retrieved documents into compact visual representations conditioned on the input query, and introduces a query-aware dynamic resolution mechanism that adaptively allocates visual granularity based on each document's estimated relevance and complexity.

Jia-Yang Yu, Jialun Zhong, Lei Zou · 0 citations