activity
20232026
most citedChinese Text Recognition with A Pre-Trained CLIP-Like Model Through Image-IDS Aligning

4 citations · 10 across the 25 of their papers we have counts for

collaborators
Showing cs.CLShow all

1 paper · 1 filter

cs.CL2026

SAGE: From Direct Answering to Evidence-Grounded Inference for Chinese Ancient Document Understanding

Yuchuan Wu, Xuan Luo, Yinglian Zhu +3

Chinese ancient document understanding demands complex visual, linguistic, and historical reasoning. Current Large Vision-Language Models (LVLMs) typically rely on an opaque, singl…