4 papers
LinguaMap: Which Layers of LLMs Speak Your Language and How to Tune Them?
J. Ben Tamo, Daniel Carlander-Reuterfelt, Jonathan Rubin +3
Despite multilingual pretraining, large language models often struggle with non-English tasks, particularly in language control, the ability to respond in the intended language. We…
Limits of message passing for node classification: How class-bottlenecks restrict signal-to-noise ratio
Jonathan Rubin, Sahil Loomba, Nick S. Jones
Message passing neural networks (MPNNs) are powerful models for node classification but suffer from performance limitations under heterophily (low same-class connectivity) and stru…
Higher diameters of Cayley digraphs
G. C. Magda, J. Rubin, S. Streipert +3
Higher diameters of Cayley digraphs are defined and studied.
Enriched model categories in equivariant contexts
Bertrand Guillou, J. P. May, Jonathan Rubin
We give a general framework of equivariant model category theory. Our groups G, called Hopf groups, are suitably defined group objects in any well-behaved symmetric monoidal catego…