3

Latent Structure of Affective Representations in Large Language Models
This work studies the geometry of affective representations in large language models as a setting where latent structure can be …
B. Choi, M. Weber
Preprint PDF Project
Towards distillation guarantees under algorithmic alignment for combinatorial optimization
Distillation can transfer knowledge from a large source model into a smaller model better suited for deployment, but theoretical …
T. Le, M. Weber
Preprint PDF Project
Iso-Riemannian Optimization on Learned Data Manifolds
High-dimensional datasets often concentrate near low-dimensional learned manifolds, but optimizing directly on such learned geometric …
W. Diepeveen, M. Weber
Preprint PDF Project
Uncovering Developmental Lineages from Single-cell Data with Contrastive Poincaré Maps
Single-cell RNA-sequencing (scRNA-seq) enables the study of hierarchical and branching patterns in organismic development at high …
N. Bhasker, H. Chung, L. Boucherie, V. Kim, S. Speidel, M. Weber
Preprint PDF Project
Computing Brascamp-Lieb Constants through the lens of Thompson Geometry
This paper studies algorithms for efficiently computing Brascamp-Lieb constants, a task that has recently received much interest. In …
M. Weber, S. Sra
Preprint Project