Preprint
Sep 2026
VR-JEPA: Learning Contrastive-State Latent Guidance for Generation-based Video Reasoning
Reasoning through video generation offers a promising path toward visual intelligence by modeling latent visual states and their dynamics. However, current video generation models often lack explicit guidance on how these states should evolve, leaving generated trajectories prone to physical and structural inconsistenc...
Ze-Hua Ma, Kun Xiang, Yun-Shuang Nie et al.
· 0 citations