M$^3$R-Bench: A Unified Benchmark for Evidence-Grounded Multimodal Metaphor Understanding
M$^3$R-Reasoner is proposed, which combines curriculum-based reasoning supervision with task-aware reinforcement learning to align model reasoning with metaphor interpretation and improves Visual Evidence and Sentiment Justification scores over GPT-5.
Hongye Jiang, Jun-Nan Zhu, Jing-Wang Huang et al.
· 0 citations