Quanta AI Labs

NVIDIA · Open World Action Model

GR00T 2

NVIDIA is introducing GR00T 2 at CoRL, described as an open frontier world action model built on NVIDIA Cosmos and trained on robot and human data, including 100,000 hours of open egocentric human data. The page reports 71% average success across 50 tasks with one demonstration per task, rising to 95% with five, and says the model ranks in the top three on several VLA and world action model benchmarks. The release is accompanied by Isaac Lab 3.0, which adds agent-assisted environment setup and a reinforcement post-training library for models such as GR00T.

Open the source ↗

Similar Agents & Automation releases

  • Toward the Era of Agentic Embodied Intelligence

    Chao Liang, Ke Chen, Fengxiaoxiao Li, Shibo Huang, Yufeng Sun, Zhaokai Yin, Jianhuan Lai, Haozhe Feng (AutoLab) · Agentic Robot Control · Week 47, 2026

  • FLEX

    MIT and New York University researchers (led by Andreea Bobu, MIT) · LLM Robot Planning · Week 47, 2026

  • Open-HumanScale

    Juncheng Ma et al. (DAGroup-PKU) · Human-video robot pretraining · Week 47, 2026

  • UQ-DAAAM

    MIT (Luca Carlone's group; co-lead authors Harry Zhang and Nicolas Gorlo) · Uncertain Robot Memory · Week 46, 2026

  • Zero-real Agent Policy (ZAP)

    Luma AI (Benjamin Pikus, Daniel Saunders, Mircea Mironenco and co-authors) · Sim-trained robot agent · Week 46, 2026

  • DreamX: Video Diffusion Model is a Universal Latent Action Learner

    KAIST and NVIDIA (Jisoo Kim, Chaehyun Kim et al.; Seungryong Kim) · Latent action learner · Week 46, 2026

More from NVIDIA

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