1 citations · 3 across the 11 of their papers we have counts for
Showing 2026Show all
3 papers · 1 filter
cs.LG2026
The Residual Stream's Effective Depth
Barak Gahtan, Ido Galil, Alex M. Bronstein
We introduce \emph{effective depth} ($\Deff$), a scalar diagnostic that treats the layer-wise residual stream of a transformer as a discrete-time process, measures how representati…
cs.LG2026
Invertible Query-Key Coupling Composes with Attention Mechanisms
Barak Gahtan, Alex M. Bronstein
Scaled dot-product attention forms its queries and keys as independent linear projections, so the two never interact before the dot product that scores them. We study coupled query…
cs.CE2026
Differentiable Randers-Finsler Eikonal Solvers
Barak Gahtan, Jacob Shpund, Alex M. Bronstein
Fast and differentiable solvers for anisotropic and asymmetric distance fields are a key primitive in geometry processing, enabling gradient-based optimization over metrics, drift…