activity
20222025
most citedDeep Signatures -- Learning Invariants of Planar Curves

2 citations · 2 across the 2 of their papers we have counts for

collaborators

5 papers

cs.CV2025

Learning Eigenstructures of Unstructured Data Manifolds

Roy Velich, Arkadi Piven, David Bensaïd +3

We introduce a novel framework that directly learns a spectral basis for shape and manifold analysis from unstructured data, eliminating the need for traditional operator selection…

cs.AI2025

SingLoRA: Low Rank Adaptation Using a Single Matrix

David Bensaïd, Noam Rotstein, Roy Velich +2

Low-Rank Adaptation (LoRA) has significantly advanced parameter-efficient fine-tuning of large pretrained models. LoRA augments the pre-trained weights of a model by adding the pro…

cs.CV2025

Neural Descriptors: Self-Supervised Learning of Robust Local Surface Descriptors Using Polynomial Patches

Gal Yona, Roy Velich, Ron Kimmel +1

Classical shape descriptors such as Heat Kernel Signature (HKS), Wave Kernel Signature (WKS), and Signature of Histograms of OrienTations (SHOT), while widely used in shape analysi…

cs.CV2024

Pathways on the Image Manifold: Image Editing via Video Generation

Noam Rotstein, Gal Yona, Daniel Silver +3

Recent advances in image editing, driven by image diffusion models, have shown remarkable progress. However, significant challenges remain, as these models often struggle to follow…

cs.CV20222 cited

Deep Signatures -- Learning Invariants of Planar Curves

Roy Velich, Ron Kimmel

We propose a learning paradigm for numerical approximation of differential invariants of planar curves. Deep neural-networks' (DNNs) universal approximation properties are utilized…