Show Notes
When The Jetsons imagined life in 2062, Rosie the robot maid seemed like pure science fiction. Today, chatbots can answer questions, analyze data and even crack jokes. But they still can't load the dishwasher.
In this episode of Building 32, MIT CSAIL associate professor Vincent Sitzmann explains why building AI that understands and interacts with the physical world is a fundamentally different challenge. Sitzmann explains why today's AI still struggles with seemingly simple physical tasks and how researchers are teaching machines to see, predict, and interact with the world around them.
In this episode: 00:00 - Intro 03:50 - From electrical engineering to computer science 05:05 - What is computer vision? 08:32 - Limitations of computer vision 09:41 - How do we fix the limitations of computer vision? 12:41 - Why can’t LLMs solve computer vision? 18:31 - How robots can learn like babies 20:57 - The future of robots in homes 23:59 - Continual learning and exploration 27:25 - Outro
Episode Resources: 😃Learn more about Vincent Sitzmann: https://www.vincentsitzmann.com/ 🎥And the Scene Representation Group: https://scenerepresentations.org/ 📖Read the Nature article Karen referenced: https://bit.ly/45NzH7q
🤖Watch the Jetsons and meet Rosie: https://bit.ly/4bzEHjB
Building 32 episodes, meet the host, and more: csail.mit.edu/podcast
Connect with CSAIL Alliances: On our site: cap.csail.mit.edu/about-us/meet-our-team On LinkedIn: linkedin.com/company/mit-csail
#MIT #CSAIL #Building32 #ArtificialIntelligence #Robotics #TechInnovation #FutureOfAI #Podcast
More from Building 32 from MIT CSAIL Alliances
Yael Tauman Kalai is a computer scientist who doesn’t code. Instead, this MIT CSAIL professor uses mathematics and cryptography to tackle some of computing’s biggest security questions: How can we know if a message is secure or if an LLM answer is correct? What does it mean to know anything when it comes to computation and trust?
What if the future of sustainable construction looked less like traditional building and more like knitting?
Long before smartphones, social media, or ChatGPT, researchers at MIT Computer Science and Artificial Intelligence Laboratory (CSAIL) helped lay the groundwork for the modern internet. In this episode of Building 32, MIT CSAIL senior research scientist, internet pioneer and former Chief Protocol Architect David Clark reflects on those early days and explains how a network designed to connect computers became a force that reshaped society.
MIT has a new podcast. Announcing Building 32, from MIT CSAIL Alliances.
Professor Armando Solar-Lezama, MIT CSAIL Associate Director, says there are currently three camps in AI discourse: the utopian thinkers, the alarmists, and the skeptics. And all of them are wrong. Plus, hear his thoughts on AI Agents, neurosymbolic programming, vibe coding, and more.