Institution

Om AI Lab

Open-source AI research group focused on multimodal and vision-language models, known for the OmAgent and OmDet projects.

Vision Foundation Models · Zhejiang University

VLM vs Video Generation: Which Pretraining Wins at Spatial Intelligence?

A frozen-feature probe pits VLMs against video-generation models on spatial tasks. VLMs win semantics (92.08 mAP vs 69.89), video models win geometry (0.527 camera AUC vs 0.330), and a naive concat of the two beats both.