Episode Details

Back to Episodes

SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Diffusion Transformers

Published 4 months, 2 weeks ago
Description
A 2.6B-parameter open-source world model that generates coherent 720p, minute-long videos with precise 6-DoF camera control on a single GPU using a Hybrid Linear Diffusion Transformer + Gated DeltaNet for long-context efficiency. Targets controllable physics simulation.
Listen Now

Love PodBriefly?

If you like Podbriefly.com, please consider donating to support the ongoing development.

Support Us