Generally Intelligent cover image

Episode 28: Sergey Levine, UC Berkeley, on the bottlenecks to generalization in reinforcement learning, why simulation is doomed to succeed, and how to pick good research problems

Generally Intelligent

00:00

Is There a Future for Vision Language Models?

There's a lot of interesting work going on in this area right now. I think one of the things that good visual language models allow you to do is kind of not worry about the language. So much because if you have good visual goal models, then you can plug them in with vision language models. The visual language model almost acts like a front end for interfacing these non linguistic robotic controllers with language.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app