-
The Implicit Geometry of Deep Representations: Insights From Log-Bilinear Softmax Models
On November 21, 2025 at 11:00 am till 12:00 pm E18-304Christos Thrampoulidis, University of British Columbia
-
Private statistical estimation via robustness and stability
On November 14, 2025 at 11:00 am till 12:00 pm E18-304Sewoong Oh, University of Washington
-
Back to the future – data efficient language modeling
On November 7, 2025 at 11:00 am till 12:00 pm E18-304Tatsunori Hashimoto, Stanford University
-
Attention Sinks: A ‘Catch, Tag, Release’ Mechanism for Embeddings
On October 31, 2025 at 11:00 am till 12:00 pm E18-304Vardan Papyan, University of Toronto
-
Learning to Price Electricity for Optimal Demand Response
On October 24, 2025 at 11:00 am till 12:00 pm E18-304Stefan Wager, Stanford University
-
Hard-Constrained Neural Networks
On October 17, 2025 at 11:00 am till 12:00 pm E18-304Navid Azizan, MIT
-
Do Large Language Models (Really) Need Statistical Foundations?
On October 10, 2025 at 11:00 am till 12:00 pm E18-304Weijie Su, University of Pennsylvania
-
Transformers Learn Generalizable Chain-of-Thought Reasoning via Gradient Descent
On October 3, 2025 at 11:00 am till 12:00 pm E18-304Yuejie Chi, Yale University
-
TBD
On September 19, 2025 at 11:00 am till 12:00 pm E18-304Benjamin Recht, University of California – Berkeley
