
Episode 16: Yilun Du, MIT, on energy-based models, implicit functions, and modularity
Generally Intelligent
00:00
Are There Any Arians Wha, You're Really Excited to See Them Develop?
Len Biast: I think the current performances, like, pretty far away from what you can do was just hard coating stuff. One thing that might be pretty promising is combining some of these perception base deep learning approaches with boti pipe line to get more generalized manipulation. And i think that's a very interesting direction to go. He says he doesn't care too much about what other people say about his research because ther're always going to be a lot of people who really dislike it. But in the end, maybe it doesn't matter that much if no one reads most papers anyway.
Transcript
Play full episode