Etiquetas: GWM-1

Runway announced its new GWM-1 "world model" technology, asserting it can maintain coherent output for minutes at a time. The company framed the model as a step toward unifying diverse domains and action spaces under a single base system. While highlighting potential uses in film, television, advertising, robotics, physics and life‑science research, Runway also disclosed a partnership with CoreWeave that will employ Nvidia GB300 NVL72 racks for training and inference. The move positions Runway in a competitive AI arena where larger tech firms also pursue similar capabilities. Leer más

Runway has introduced its inaugural world model, GWM-1, a video‑centric AI system that predicts pixels frame by frame to simulate physics, geometry and lighting. The launch includes three specialized variants—GWM‑Worlds for interactive scenes, GWM‑Robotics for synthetic data generation, and GWM‑Avatars for realistic human simulations. In parallel, the company upgraded its Gen 4.5 video model with native audio, dialogue editing and multi‑shot generation, allowing users to create longer, cohesive videos with consistent characters and background sound. Both innovations are now accessible to paid subscribers, with an SDK slated for robotics partners. Leer más