Surbhi Goel, University of Pennsylvania Abstract: Understanding how different components of the machine learning pipeline—spanning data composition, architectural choices, and optimization dynamics—shape model behavior remains a fundamental challenge. In this talk, I will argue that synthetic tasks, which enable precise control over data distribution and task complexity, serve as powerful testbeds for analyzing and attributing […]

Claire Boyer, Université Paris-Saclay Abstract: Attention-based models, such as Transformer, excel across various tasks but lack a comprehensive theoretical understanding, especially regarding token-wise sparsity and internal linear representations. To address this gap, we introduce the single-location regression task, where only one token in a sequence determines the output, and its position is a latent random […]

Michael W. Mahoney, ICSI, LBNL, and Department of Statistics, UC Berkeley Abstract: The remarkable successes of ChatGPT in natural language processing (NLP) and related developments in computer vision (CV) motivate the question of what foundation models would look like and what new advances they would enable, when built on the rich, diverse, multimodal data that […]