SOURCE-LINKED INTELLIGENCE

From Retrieval to Recognition:How Vision--Language Models Become OCR Specialists

arXiv · AI, language, vision and robotics · article · Sep 18, 2026 · UTC

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 setting of full-sequence OCR, rather than local-answer retrieval. Using an evidence-grounded protocol with held-out causal interventions, we identify sparse and stable OCR-head sets in GLM-OCR, MinerU2.5, and PaddleOCR-VL-1.6. We then investigate the mechanistic origin of these OCR heads by comparing them with independently identified textual retrieval/copy heads in general VLMs. Across two general VLMs, visual OCR heads

Read original source ↗ Open in workspace

recordType

paper

region

Global