NVIDIA Cosmos Labs unveils WAMs and VLAs for robot learning
NVIDIAAI · x · 2026-08-14
NVIDIA AI announced that Cosmos Labs has introduced WAMs (World Action Models) and VLAs (Vision-Language-Action models) for robot learning. Details are not provided in the tweet, but this marks a significant move in embodied AI.
More from Embodied
- Google Demos 3-Agent Team Autonomously Training Robotics Models with Gemini 3.7 Flash — koraykv · 2026-08-14
- Raspberry Pi Journaling Device with Dedicated Screen and Keyboard, Plus Claude Chat Client — tom_doerr · 2026-08-14
- Open Data Pool Goes Live for Embodied AI — const_reborn · 2026-08-14
- Walden Robotics Opens New SF HQ, Hiring Across Multimodal, RL and Hardware Roles — adnothing · 2026-08-14
- Uber Teams Up with Wayve and Nissan to Bring Robotaxis to Tokyo by 2026 — alexgkendall · 2026-08-14
- LDA-1B: A 1B Robot Foundation Model Trained on 30k Hours of Embodied Data — chris_j_paxton · 2026-08-13