Understanding and using the embedding spaces of large generative models
IEEE Information Theory Society Distinguished Lecture
November 21, 2025
11:00 AM - 12:00 PM
Location
Lecture Center C4
Address
802 S. Halsted St., Chicago, IL 60607
Calendar
Download iCal FileUnderstanding and using the embedding spaces of large generative models
Presenter: Anand Sarwate, Rutgers University
Abstract: Training massive ML/AI models on massive amounts of data supposedly creates latent representations or features that are “universal” in the sense that the large model acts as a feature extractor that maps inputs into an embedding space. In this talk I will discuss recent empirical work that looks at embeddings for generative models. In particular, I will describe an approach that uses a third model as a “microscope” to uncover differences between two other models. Simple methods on the embedding space of the “microscope” model show that outputs of different models are distinguishable, which potentially opens the door to several applications. Time permitting, I will describe other insights about embedding spaces.
Speaker bio: Anand D. Sarwate is currently a professor of electrical and computer engineering at Rutgers University. Prior to joining Rutgers he was a research assistant professor at Toyota Technical Institute-Chicago and a postdoc at the ITA Center at UCSD. He received undergraduate degrees in mathematics and electrical engineering from MIT (2002) and a PhD from UC Berkeley (2008). His research interests include information theory, machine learning, signal processing, optimization, and privacy and security. Dr. Sarwate is a Distinguished Lecturer of the IEEE Information Theory Society for 2024--2025 and is on the Board of Governors of the IEEE Information Theory Society.
Faculty host: Natasha Devroye, devroye@uic.edu
Date posted
Nov 18, 2025
Date updated
Nov 20, 2025