"Generalist Robot Learning in the Era of Foundation Models" – Ankit Goyal, Talks at TTIC
“Foundations of Generalist Robot Learning in the Era of Foundation Models” Ankit Goyal, NVIDIA Originally recorded on March 5, 2026, at TTIC. In this talk, Ankit Goyal outlines a research agenda for building generalist robots capable of handling diverse tasks and environments using foundation models. He presents approaches for enabling foundation models to generate actions, process 3D inputs from 2D representations, and integrate with specialized robotic systems, highlighting hierarchical designs that combine generalization with structure for real-world deployment. Timestamps: 00:00 Introduction 00:50 Talk begins No Q&A #Robotics #RobotLearning #FoundationModels #AI #MachineLearning #EmbodiedAI #3DVision #Autonomy #Research #TTIC

▶︎
Robotics' End Game: Nvidia's Jim Fan

▶︎
"Moving Away from Probabilities" – Nati Srebro, Research at TTIC

▶︎
Progress made on AI-powered humanoid robots | 60 Minutes

▶︎
Prof. Sergey Levine: Robotic Foundation Models

▶︎
Andrey Rudenko - Prediction, planning and interaction methods for a mobile robot in dynamic scenes

▶︎
The Future of Humanoid Robotics | Jonathan Hurst | TEDxPortland

▶︎
MIT 6.S191: AI for Science

▶︎
VINMOTION INTELLIGENCE PIONEERS SEMINAR #2 | Synthetic Data for Robot Learning - Dr. Fan Shi

▶︎
Why The Russian Accent Terrifies Everyone

▶︎
Rise of the Humanoids: Inside China’s Robot Awakening

▶︎
Google DeepMind robotics lab tour with Hannah Fry

▶︎
The World's Most Important Machine
![Yann LeCun's $1B Bet Against LLMs [Part 1]](https://i.ytimg.com/vi/kYkIdXwW2AE/hqdefault.jpg?sqp=-oaymwEjCNACELwBSFryq4qpAxUIARUAAAAAGAElAADIQj0AgKJDeAE=&rs=AOn4CLDbV4izF3i-wxevCVIn7FJjoy1vlA)
▶︎
Yann LeCun's $1B Bet Against LLMs [Part 1]

▶︎
The Uncomfortable Truth About AI “Reasoning” | World Science Festival

▶︎
FULL DISCUSSION: Google's Demis Hassabis, Anthropic's Dario Amodei Debate the World After AGI | AI1G

▶︎
This is not the AI we were promised | The Royal Society

▶︎
How ASML Makes Chips Faster With Its New $400 Million High NA Machine

▶︎
Why Building AI Data Centres Isn’t Working Anymore

▶︎
