[Theory] 12/15 TTIC Colloquium: Yonatan Belinkov, Technion

[Mary Marre via Theory]

*When:*        Monday, December 15, 2025 at* 11:30** am CT *

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

                   TTIC, 6045 S. Kenwood Avenue

                   5th Floor, Room 530


*Virtually:*  * via Panopto
<https://uchicago.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=94da4e03-67ec-4089-b48d-b3ae010ff34b>*



*Who: *         Yonatan Belinkov, Technion



*Title: *Toward Scalable and Actionable Interpretability

*Abstract:* Interpretability research has made many interesting discoveries
about how language models and other deep learning models operate. However,
despite this progress, interpretability has remained behind recent advances
in how language models are used in practice. In this talk, I will describe
some of our recent interpretability work, starting with scientific insights
about the kind of algorithms that may be employed by language models. I
will then describe several case studies where interpretability insights
informed solutions for known problems: overcoming the modality gap in
vision-language models and removing undesired information from trained
models. If time permits, I will also share initial results on
interpretability of protein language models. I will end by suggesting
directions for making interpretability research more scalable and
actionable.

*Bio:* Yonatan Belinkov is an Assistant Professor at the Technion. He is a
former Azrieli Faculty Fellow and was a Mind Brain and Behavior
Postdoctoral Fellow at Harvard University. Prior to that, he received his
PhD from MIT. He is spending the current academic year at the Kempner
Institute at Harvard University thinking about issues of interpretability,
controllability, multi-agent communication, and AI for science.

*Host: **Karen Livescu* <klivescu at ttic.edu>




Mary C. Marre
Faculty Administrative Support
*Toyota Technological Institute*
*6045 S. Kenwood Avenue, Rm 517*
*Chicago, IL  60637*
*773-834-1757*
*mmarre at ttic.edu <mmarre at ttic.edu>*
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/theory/attachments/20251209/38edec3f/attachment.html>