Mind What Matters for Reasoning: Aligning Cross-Modal Attention via Selective Probability Mass Concentration
SPMC, a training framework that identifies grounding-responsive heads and selectively regularizes their text-to-image attention, demonstrates that targeted guidance of sparse and implicit visual evidence pathways can directly improve multimodal reasoning.
Jia-Qi Deng, Zong-Han Wu, Zhan Heng et al.
· 0 citations