Video diffusion transformers follow scaling laws, and tuning learning rate and batch size per model and data size makes those laws precise enough to predict loss and optimal model size at larger scales.
Panda-70m: Captioning 70m videos with multiple cross-modality teachers
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Towards Precise Scaling Laws for Video Diffusion Transformers
Video diffusion transformers follow scaling laws, and tuning learning rate and batch size per model and data size makes those laws precise enough to predict loss and optimal model size at larger scales.