Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence
-
Updated
Jul 10, 2026 - Python
Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence
Selective fused FP8 checkpoint + ComfyUI runtime for LingBot-Video Dense 1.3B. Measured 1.27x in a local one-step RTX 5080 sampler smoke test; T2V, TI2V, experimental FLF.
Add a description, image, and links to the lingbot-video topic page so that developers can more easily learn about it.
To associate your repository with the lingbot-video topic, visit your repo's landing page and select "manage topics."