Infi-MMR: Curriculum-based Unlocking Multimodal Reasoning via Phased Reinforcement Learning in Multimodal Small Language Models

Published in Under Review, 2025

This manuscript studies curriculum-based reinforcement learning for multimodal reasoning in compact multimodal models.

Recommended citation: Zeyu Liu*, Yuhang Liu*, Guanghao Zhu, Congkai Xie, Zhen Li, Jianbo Yuan, Xinyao Wang, Qing Li, Shing-Chi Cheung, Shengyu Zhang, Fei Wu, Hongxia Yang. Infi-MMR: Curriculum-based Unlocking Multimodal Reasoning via Phased Reinforcement Learning in Multimodal Small Language Models. Under review, 2025.
Download Paper

Direct Link