GitSeonjeap
English

Sign in

Reading needs no sign-in. Sign in to write posts or comments, or to recommend and report, in the community.

By signing in you agree to the notices below. Community rules · Privacy notice

Keep browsing without signing in

← News

Industry

NVIDIA Releases GR00T 2 Robot World Action Model and Isaac Lab 3.0

Posted As of

NVIDIA introduced GR00T 2, an open model based on Cosmos, timed to CoRL. All performance figures are NVIDIA's own tests, and no information on the license or weights has been confirmed.

What happened

Based on the official NVIDIA blog announcement.

  • GR00T 2 is an open frontier world action model built on NVIDIA Cosmos, trained on robot and human data. This includes 100,000 hours (official) of NVIDIA's open-source first-person perspective data.
  • NVIDIA claims it ranks in the top 3 across all VLA and world action model categories on the RoboCasa365, RoboLab, RoboDojo, and MolmoSpaces benchmarks.
  • A developer forum post states that the combination of Isaac Lab 3.0 and Newton delivers up to 2.5x training throughput (official) on a dexterous manipulation benchmark.
  • AlphaNIST reports a simulation training success rate of over 98% (official) across 20 assembly tasks, and says it uses about 39x less GPU time (official) than individual policies.

Our take

The direct impact on local AI users is small; this is closer to news in the robotics and physical AI field. All figures come from NVIDIA's own tests. We could not confirm the model card, license, or whether weights are public from the primary page, so it is still unknown whether the model can actually be downloaded and used.

Sources and related posts

More in Industry

  1. Google Unveils Two New Systems, TPU 8tx and TPU 8i Max (blog.google)

    Google announced TPU 8tx, focused on security, and TPU 8i Max, built for large-context workloads. Reports differ on pricing and launch timing, so neither can be confirmed.

    Industry| |2 sources |Our take included
  2. Nvidia Claims Vera CPU Beats x86 on Agent Efficiency in 100MW Data Center Comparison (blogs.nvidia.com)

    Nvidia claimed in an official blog post that its Vera CPU delivers higher agent throughput per watt than x86 CPUs in a 100MW data center comparison. The figures come from Nvidia and its partners, and there is no independent verification.

    Industry| |1 sources |Our take included
  3. Nvidia Board Launches Independent Probe After Reports on Foreign Intelligence Targeting of Jensen Huang (nvidianews.nvidia.com)

    Nvidia's board said it is starting an independent investigation in connection with reports that CEO Jensen Huang was targeted by foreign intelligence activities. The board says it has no reason to believe national security or company confidential information was compromised.

    Industry| |1 sources |Our take included

All news