Modomodо Multimodal Rl

Optimize data mixtures across diverse vision-language domains when applying RL with verifiable rewards to multimodal LLMs, balancing task-specific performance with generalization.

adu2021 Updated 7 repo stars

File contents

adu2021/skillxiv commit 4d35d39748

Frequently asked questions

npx get-skill add adu2021/modomod-multimodal-rl