3 papers
cs.LG2026
A Unifying View of Attention Sinks: Two Algorithms, Two Solutions
Lukas Fesser, Mozes Jacobs, Thomas Fel +2
When attention concentrates on a single token, a sink, what is the model actually computing? Attention sinks are ubiquitous in softmax transformers, yet this shared visual signatur…
cs.LG2026
Kuramoto Orientation Diffusion Models
Yue Song, T. Anderson Keller, Sevan Brodjian +4
Orientation-rich images, such as fingerprints and textures, often exhibit coherent angular directional patterns that are challenging to model using standard generative approaches b…
cs.LG2025
Flow Equivariant Recurrent Neural Networks
T. Anderson Keller
Data arrives at our senses as a continuous stream, smoothly transforming from one instant to the next. These smooth transformations can be viewed as continuous symmetries of the en…