shipfeedAI news, curated daily

18:05:52 CET
29 JUN18:05:52shipfeed
pull to refreshlast sync
Just in — 30 new
§ models · storyline

How Cosmos 3 Helps Physical AI Think Before It Acts

NVIDIA releases Cosmos 3, an open world foundation model combining vision reasoning, multimodal generation and action prediction for robots, autonomous vehicles and vision AI agents.

Jun 1 · · primary fetch2 sourcesupdated Jun 1 ·

The new, open NVIDIA world foundation model brings vision reasoning, multimodal generation and action prediction together to help robots, autonomous vehicles and vision AI agents think before acting in the real world.

read full article on blogs.nvidia.com
§ sources2 publications · timeline below
  1. blogs.nvidia.comHow Cosmos 3 Helps Physical AI Think Before It Actsprimary
  2. huggingface.coWelcome NVIDIA Cosmos 3: The First Open Omni-model for Physical AI Reasoning and Action

§ how this story moved

  1. primaryHugging Face — Blog publishes the launch post.
  2. NVIDIA — AI Blog picks up coverage.