MagicVideo generates 256x256 text-conditioned video clips via latent diffusion with a custom 3D U-Net, achieving roughly 64 times lower compute than prior video diffusion models.
Frozen clip models are efficient video learners
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2verdicts
UNVERDICTED 2representative citing papers
Video foundation models encode intuitive physics knowledge that is strongest in V-JEPA at intermediate-to-late layers and depends on pretraining type and probe design.
citing papers explorer
-
MagicVideo: Efficient Video Generation With Latent Diffusion Models
MagicVideo generates 256x256 text-conditioned video clips via latent diffusion with a custom 3D U-Net, achieving roughly 64 times lower compute than prior video diffusion models.
-
Do Video Foundation Models Understand Intuitive Physics? A Layerwise Probing Analysis
Video foundation models encode intuitive physics knowledge that is strongest in V-JEPA at intermediate-to-late layers and depends on pretraining type and probe design.