1 citations · 2 across the 11 of their papers we have counts for
6 papers · 1 filter
Inducing Fourier Geometry: A Smoothness Prior Imposes Approximate Translation Equivariance in Multimodal Stellar Embeddings
Ilay Kamai, Alex M. Bronstein, Hagai B. Perets
Learned representations often contain geometric structure induced by symmetries in the underlying data. We ask whether a known continuous parameter space can instead be used to \em…
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…
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…
Effective Sample Size and Generalization Bounds for Temporal Networks
Barak Gahtan, Alex M. Bronstein
Learning from time series is fundamentally different from learning from i.i.d.\ data: temporal dependence can make long sequences effectively information-poor, yet standard evaluat…
Estimating the Number of HTTP/3 Responses in QUIC Using Deep Learning
Barak Gahtan, Robert J. Shahla, Reuven Cohen +1
QUIC, a new and increasingly used transport protocol, enhances TCP by offering improved security, performance, and stream multiplexing. These features, however, also impose challen…
WearableMil: An End-to-End Framework for Military Activity Recognition and Performance Monitoring
Barak Gahtan, Shany Funk, Einat Kodesh +3
Musculoskeletal injuries during military training significantly impact readiness, making prevention through activity monitoring crucial. While Human Activity Recognition (HAR) usin…