NVIDIA's Ming-Yu Liu on open models, world models, and the future of physical AI
Practical AI · rss · 2026-10-01
On the Practical AI podcast, Ming-Yu Liu, VP of NVIDIA's Cosmos Lab, discusses how AI is moving beyond the cloud into robots and vehicles: why open models matter for physical AI innovation, how world models help AI understand and simulate the physical world, and what it takes to build increasingly capable physical AI systems.
More from Embodied
- Personalized AI, personalized bugs: Dots users report wildly different flaws — ChrisGPT · 2026-10-01
- A 40-gram autonomous drone hunts mosquitoes by acoustic signature and sonar — TinfoilTricorn · 2026-10-01
- Google DeepMind Tokyo hiring senior research engineer for gaming AI agents — heiga_zen · 2026-10-01
- 5 robotics accounts that are '6 months ahead': Jim Fan, Physical Intelligence founders lead the list — RemiCadene · 2026-10-01
- DyRAD: radar novel view synthesis for dynamic driving scenes, recovering 90.7% vs 26.9% baseline — Technion · 2026-10-01
- VLA reinforcement learning updates are low-rank and concentrate in overlooked Timestep Modules — HOLILAB · 2026-10-01