NVIDIA to Explore World Action Models and the Evolution of Robot Foundation Models

MonaJalal_ · x · 2026-08-08

NVIDIA's robotics team announced a livestream for August 13 to discuss the next generation of robotics technology following Vision-Language-Action (VLA) models.

The session will focus on World Action Models (WAMs), VLAs, and hybrid robot foundation models. Researchers will also demonstrate how the NVIDIA Cosmos 3 framework natively represents action alongside video to advance embodied AI.

Original post →

More from Embodied

Embodied channel →