Disentangling Perception and Reasoning in Multimodal LLMs via Reward Design

arXiv:2601.00215 · cs.CV, cs.CL · Submitted 2026-01-01 · Read on arXiv

cs.CV, cs.CL

Submitted: 2026-01-01

Updated: 2026-10-31

Code: https://github.com/hiyouga/EasyR1

Terminology

Sources

Related papers