MoDoMoDo: Multi-Domain Data Mixtures for Multimodal LLM Reinforcement Learning

Yiqing Liang, Jielin Qiu, Wenhao Ding +7

Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a powerful paradigm for post-training large language models (LLMs), achieving state-of-the-art perform…