[Theory] [TTIC Talks] 2/27 Talks at TTIC: Amir Bar, Meta AI (FAIR)

[Brandie Jones via Theory]

*When:*        Thursday, February 27th at *10AM CT*


*Where:       *Talk will be given *live, in-person* at

                       TTIC, 6045 S. Kenwood Avenue

                       5th Floor, Room 530


*Virtually:*  via Panopto (livestream
<https://uchicago.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=c995b509-ab19-4289-a39a-b28801157495>
)


*Who: *         Amir Bar, Meta AI (FAIR)

*Title:*        Towards Real-World Models
*Abstract: *Current artificial intelligence systems can synthesize images,
solve math problems, and write code. Despite these advances, they still
struggle with basic tasks that humans and animals perform effortlessly. One
potential idea why humans and animals can perform basic tasks well, is
because they have a predictive world model that integrates perception,
reasoning, and planning capabilities—can we build such a model in a
bottom-up fashion from sensorimotor data and primarily visual observations?

In this talk, I will propose a path toward building such a world model. I
will introduce Visual Prompting, a new paradigm that unifies many computer
vision tasks and can readily adapt pretrained models to novel tasks without
fine-tuning. Building on this, I will present an extension to planning
using generative world models—showing that action-conditioned video models
can act as simulators of the environment that support real-world
decision-making, with a case study in visual navigation. Finally, I will
discuss future directions for scaling up the capabilities of world models
and the challenges we face to enable their real-world deployment.

*Short Bio*: Amir Bar is a Postdoctoral Researcher at Meta AI (FAIR),
working on self-supervised learning with Yann LeCun. Previously, Amir
completed his PhD at Tel Aviv University and was a Visiting PhD student at
Berkeley AI Research, advised by Amir Globerson and Trevor Darrell. His
work on video models won the Ego4D CVPR 2022 PNR challenge. Amir began his
PhD following the acquisition of the startup Zebra Medical Vision where he
led the AI team and developed multiple FDA-approved algorithms currently in
clinical use worldwide.

*Host: **Greg Shakhnarovich* <greg at ttic.edu>

-- 
*Brandie Jones *
*Executive **Administrative Assistant*
Toyota Technological Institute
6045 S. Kenwood Avenue
Chicago, IL  60637
www.ttic.edu
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/theory/attachments/20250220/be54c85d/attachment.html>