2 papers
cs.CV2026
From Retrieval to Recognition:How Vision--Language Models Become OCR Specialists
Yuanxiang Huangfu, Hanmeng Zhong, Linqing Chen +1
Does a general vision--language model acquire specialized OCR ability by developing a new reading circuit or by reusing an existing mechanism? We address this question in the setti…
cs.CV2025
Role-SynthCLIP: A Role Play Driven Diverse Synthetic Data Approach
Yuanxiang Huangfu, Chaochao Wang, Weilei Wang
The effectiveness of Contrastive Language-Image Pre-training (CLIP) models critically depends on the semantic diversity and quality of their training data. However, while existing…