Preprint
Aug 2026
Motion-as-Prompt: Enhancing Motion Reasoning in Multimodal Large Language Models via Motion-Guided Cross-Frame Visual Prompting
MaP provides a simple and effective solution for enhancing motion-centric video reasoning without model training or architectural modification, and consistently improves average motion-reasoning accuracy.
Xikai Sun, Kebin Liu, Haotian Wang et al.
· 0 citations