How World Foundation Models Will Advance Physical AI With NVIDIA’s Ming-Yu Liu - Ep. 240
NVIDIA AI Podcast
World Models vs. LLMs/Generative Video
- World models differ from LLMs by focusing on generating simulations, often in video form, based on physics and real-world understanding, rather than text descriptions.
- Generative video models can serve various purposes, including creative ones.
- World models, as a subset of video foundation models, concentrate on simulating future outcomes based on current observations and actor intentions.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
