EP11: JEPA with Randall Balestriero
Update: 2025-10-28
Description
In this episode we talk with Randall Balestriero, an assistant professor at Brown University. We discuss the potential and challenges of Joint Embedding Predictive Architectures (JEPA). We explore the concept of JEPA, which aims to learn good data representations without reconstruction-based learning. We talk about the importance of understanding and compressing irrelevant details, the role of prediction tasks, and the challenges of preventing collapse.
Comments
In Channel
Download from Google Play
Download from App Store
United States00:00
00:00
1.0x
