Toward a Theoretical Understanding of Self-Supervised Learning in the Foundation Model Era
- 👤 Speaker: Yisen Wang 🔗 Website
- 📅 Date & Time: Wednesday 28 January 2026, 17:00 - 18:00
- 📍 Venue: Computer Laboratory, William Gates Building, Room FW26
Abstract
Self-supervised learning (SSL) has become the cornerstone of modern foundation models, enabling them to learn powerful representations from vast amounts of unlabeled data. By designing auxiliary tasks on raw inputs, SSL removes the reliance on human-provided labels and underpins the pretraining–finetuning paradigm that has reshaped machine learning beyond the traditional empirical risk minimization framework. Despite its remarkable empirical success, its theoretical foundations remain relatively underexplored. This gap raises fundamental questions about when and why SSL works, and what governs its generalization and robustness. In this talk, I will introduce representative SSL methodologies widely used in foundation models, and then present a series of our recent works on the theoretical understanding of SSL , with a particular focus on contrastive learning, masked autoencoders and autoregressive learning.
Series This talk is part of the Foundation AI series.
Included in Lists
- All Talks (aka the CURE list)
- Artificial Intelligence Research Group Talks (Computer Laboratory)
- bld31
- Cambridge Centre for Data-Driven Discovery (C2D3)
- Cambridge Forum of Science and Humanities
- Cambridge Language Sciences
- Cambridge talks
- Chris Davis' list
- Computer Laboratory, William Gates Building, Room FW26
- Department of Computer Science and Technology talks and seminars
- Guy Emerson's list
- Hanchen DaDaDash
- Interested Talks
- Martin's interesting talks
- ndk22's list
- ob366-ai4er
- PhD related
- rp587
- School of Technology
- Speech Seminars
- Trust & Technology Initiative - interesting events
- yk373's list
- yk449
Note: Ex-directory lists are not shown.
![[Talks.cam]](/static/images/talkslogosmall.gif)



Wednesday 28 January 2026, 17:00-18:00