DocTron-hub

DocTron-Formula. Python

VinciCoder. Python

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

Chart-R1. Chart-R1: Chain-of-Thought Supervision and Reinforcement for Advanced Chart Reasoner

FD-RL. [CVPR 2026] Reading or Reasoning? Format Decoupled Reinforcement Learning for Document OCR

MSRL. [ICLR 2026] Breaking the SFT Plateau: Multimodal Structured Reinforcement Learning for Chart-to-Code Generation