Skip to yearly menu bar Skip to main content


Invited Talk
in
Workshop: Text, camera, action! Frontiers in controllable video generation

Ashley Edwards - Learning actions, policies, rewards, and environments from videos alone

Ashley Edwards

[ ]
Sat 27 Jul 1:30 a.m. PDT — 2:10 a.m. PDT

Abstract:

In the past year we have seen a leap in the capabilities of video generation models. It is no surprise that this could be considered the next frontier — videos encompass much of the world we live in and learning from this data could get us ever closer to more generalist agents. However, video generation only scratches the surface of what we can learn from such data. In this talk, I will discuss a few different works that further investigate how we can infer actions, rewards, policies, and even environments from videos alone.

Chat is not available.