Physical AI
NVIDIA’s Cosmos platform supports adapting pretrained world models for physical-AI applications. Its released tools cover video processing, tokenization, world models, and post-training examples.
Why it matters
Research about physical systems needs evidence for each downstream use. A generated scene alone does not establish reliable robot behavior.
Relationships
acts throughAgent → Physical AIfeeds back toPhysical AI → Digital twininformsSim-to-real → Physical AI
Related models
WFM within aserdargun.com
WFM is a research atlas in the physical AI layer of the AI Learning System. Read the sources here, explore prediction and action in WML, then follow asset records, evidence, and human oversight in ITL.
These links describe a learning path. The applications run independently; they do not imply shared telemetry or automatic control. ITL examples are synthetic teaching records.