How a Voice Agent Learns the Rhythm of Conversation — Shawn Wen
Oct 1, 2026 - 01:10:09
Radio and PodcastLive Radio & Podcasts
Technology
How Physical AI Learns Across Language, Video and Action — Ming-Yu Liu
The car making a left turn at the start of this episode was never filmed. Cosmos 3 generated it. Ming-Yu Liu, who leads the Cosmos research at NVIDIA, explains how one model can describe a video, generate one, and produc...
Related Episodes
Continue listening to more episodes from Machine Learning Street Talk.
Who Checks a Proof No Human Can Read? — Leo de Moura
Sep 30, 2026 - 01:14:19
When AI Research Starts Moving Faster Than Human Research - Zhengyao Jiang
Sep 26, 2026 - 00:43:42
How Deep Learning Finally Cracked Messy Tables - Frank Hutter
Sep 23, 2026 - 01:53:12
Why Scaling Prediction Cannot Create Intelligence - Alexander Mattick
Sep 21, 2026 - 02:14:20
Speech Recognition Is Not a Solved Problem — Pavan Muddireddy
Sep 14, 2026 - 01:42:22
How Replication Could Teach Machines What Good Science Looks Like — Edward Hughes
Sep 11, 2026 - 02:01:53
AI 2040: Plan A report - Daniel Kokotajlo & Thomas Larsen
Sep 8, 2026 - 01:29:46