arXiv

OCRVerse: Towards Holistic OCR in End-to-End Vision-Language Models

Yufeng Zhong, Lei Chen, Xuanle Zhao

Jan 30, 2026·05:43·

00:00

05:43

Holistic OCRText-centric OCRVision-centric OCROCRVerseData EngineeringTwo-stage SFT-RL Training

Turn any paper into a podcast

ResearchPod turns research papers into podcasts you can actually follow.