AI RESEARCH
SARA: Semantically Adaptive Relational Alignment for Video Diffusion Models
arXiv CS.CV
•
ArXi:2605.07800v1 Announce Type: new Recent video diffusion models (VDMs) synthesize visually convincing clips, yet still drop entities, mis-bind attributes, and weaken the interactions specified in the prompt. Representation-alignment objectives such as VideoREPA and MoAlign improve fine-grained text following by distilling spatio-temporal token relations from a frozen visual foundation model, but their pairwise supervision budget is allocated by visual or motion cues rather than by how relevant each pair is to the prompt.