Tag: World action model

Dyna 2.1 aims at whole shifts, measured by time between interventions

Dyna Robotics has shown a semi-humanoid on a wheeled base and pitched it around MTBI — mean time between human interventions. It claims 200 units an hour in a warehouse and 22 minutes per hotel room.

Dyna-2: a million hours of human video gives robots zero-shot skill

Dyna Robotics unveiled Dyna-2 — a world-action model trained on over a million hours of human video that the company says demonstrates the first human-to-robot scaling law.

NVIDIA Cosmos 3 Launches as World Action Model to Replace VLA Paradigm

NVIDIA unveiled Cosmos 3 at GTC Taipei -- an open-weights physical AI model with native robotic action generation. The model displaces the VLA paradigm in favor of WAM, ranking first on four open leaderboards.

NVIDIA Maps Robotics' Future on the LLM Evolution Path

NVIDIA's Jim Fan at AI Ascent 2026 outlined a detailed robotics development roadmap based on replicating four stages of large language model evolution — from pre-training to autonomous research.

ShengShu unveils Motubrain: one AI brain for every robot platform

ShengShu Technology has unveiled Motubrain, a World Action Model that unifies video generation, world modeling, and action control in a single Mixture-of-Transformers architecture. Backed by a $293M Series B from Alibaba Cloud, the model tops RoboTwin 2.0 with 96% success across 50 randomized tasks.

AGIBOT ogłasza Genie Envisioner 2.0: modele świata stają się symulatorem fizyki