GutenOCR: A Grounded Vision-Language Front-End for Documents Paper • 2601.14490 • Published 13 days ago • 36
GutenOCR: A Grounded Vision-Language Front-End for Documents Paper • 2601.14490 • Published 13 days ago • 36 • 7
OCR Collection Data and models for optical character recognition • 6 items • Updated 12 days ago • 4
view post Post 1498 Lacking vllm support for Transformers v5, frustrating only me? See translation 👀 4 4 + Reply