inclusionAI (Ruoyu Wang et al.) · Streaming Video Renderer

Code World Model 2.0: Towards Infinite Controllable Video Generation

Introduces Invoker-Render, a video renderer pairing a bidirectional creation model with a causal four-step streaming model, conditioned on structural proxies, an appearance reference and language. It is trained on an aligned corpus of about 200 hours and uses a new training method, Progressive Forcing (ProForcing), to limit drift during streaming. The authors report consistent gains over recent streaming baselines and stable 30-minute racing rollouts. Licence and code availability are not stated on the page.

Open the source ↗

Similar Video & Animation releases

Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.