A 5B Hydra/attention hybrid diffusion model matches Transformer quality for 2K images and 360p video while running faster at long token counts.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Pushing the Boundaries of State Space Models for Image and Video Generation
A 5B Hydra/attention hybrid diffusion model matches Transformer quality for 2K images and 360p video while running faster at long token counts.