Breaking the SFT Plateau: Multimodal Structured Reinforcement Learning for Chart-to-Code Generation
DocTron
DocTron
AI & ML interests
None yet
Organizations
models 9
DocTron/OCRVerse
5B • Updated • 40 • 5
DocTron/FD-RL
5B • Updated • 22 • 1
DocTron/OCRVerse-code
4B • Updated • 7
DocTron/OCRVerse-text
4B • Updated • 7
DocTron/MSRL
8B • Updated • 21 • 1
DocTron/MSRL-SFT
8B • Updated • 11 • 1
DocTron/DocTron-Formula
8B • Updated • 33 • 3
DocTron/Chart-R1
8B • Updated • 32 • 2
DocTron/Chart-COT
8B • Updated • 11 • 1
datasets 0
None public yet