8 papers
L-SR1: Learned Symmetric-Rank-One Preconditioning
Gal Lifshitz, Shahar Zuler, Ori Fouks +1
End-to-end deep learning has achieved impressive results but often relies on large labeled datasets, exhibits limited generalization to unseen scenarios, and incurs substantial com…
Catastrophic Forgetting is Low-Rank: A Function-Space Theory for Continual Adaptation
Ido Nitzan Hidekel, Dan Raviv
Catastrophic forgetting in continual adaptation is usually studied through parameter drift, replay, or distillation, but these views do not identify which output-space directions a…
Harnessing Selective State Space Models to Enhance Semianalytical Design of Fabrication-Ready Multilayered Huygens' Metasurfaces: Part II - Generative Inverse Design (MetaMamba)
Natanel Nissan, Sherman W. Marcus, Dan Raviv +2
We present a generative framework for inverse design of five-layer transmissive Huygens' metasurfaces (HMSs), addressing a longstanding challenge in achieving full-phase, high-effi…
Harnessing Selective State Space Models to Enhance Semianalytical Design of Fabrication-Ready Multilayered Huygens' Metasurfaces: Part I - Field-based Semianalytical Synthesis
Sherman W. Marcus, Natanel Nissan, Vinay K. Killamsetty +4
Planar metasurfaces can profoundly control electromagnetic scattering. At microwave frequencies, such devices are typically implemented using multilayer cascades of patterned metal…
SONAR: Spectral-Contrastive Audio Residuals for Generalizable Deepfake Detection
Ido Nitzan Hidekel, Ido Nitzan HIdekel, Gal lifshitz +2
Deepfake (DF) audio detectors still struggle to generalize to out of distribution inputs. A central reason is spectral bias, the tendency of neural networks to learn low-frequency…
Systole-Conditioned Generative Cardiac Motion
Shahar Zuler, Gal Lifshitz, Hadar Averbuch-Elor +1
Accurate motion estimation in cardiac computed tomography (CT) imaging is critical for assessing cardiac function and surgical planning. Data-driven methods have become the standar…