Siebel School Speakers Calendar

View Full Calendar

Through the Looking Glass: Semantic Analysis of Neural Networks

Event Type
Lecture
Sponsor
Darko Marinov
Location
Siebel Center 201 N Goodwin Ave- Room 3102
Virtual
Join online
Date
Sep 16, 2025   5:00 pm  
Speaker
Corina Păsăreanu
Contact
Samantha Webster
E-Mail
swebster@illinois.edu
Phone
217-300-0846
Views
63

Who: Corina Păsăreanu (https://www.andrew.cmu.edu/user/pcorina), Carnegie Mellon University, USA

Abstract: Neural networks are known for their lack of transparency, making them difficult to understand and analyze. In this talk, we explore methods designed to interpret, formally analyze, and even shape the internal representations of neural networks using human-understandable abstractions. We review recent techniques including the use of vision-language models to investigate perception modules, the application of probing and steering vectors to identify vulnerabilities in code models, and an axiomatic approach for validating mechanistic interpretation of transformer models.

link for robots only