5 citations · 6 across the 5 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
A Unifying View of Attention Sinks: From Mechanisms to Architectural Interventions
Lukas Fesser, Lukas Fesser*, Mozes Jacobs* +5
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.LG2023★ 5 cited
HyperSINDy: Deep Generative Modeling of Nonlinear Stochastic Governing Equations
Mozes Jacobs, Bingni W. Brunton, Steven L. Brunton +2
The discovery of governing differential equations from data is an open frontier in machine learning. The sparse identification of nonlinear dynamics (SINDy) \citep{brunton_discover…