collaborators

10 papers

cs.CV2026

LoRSA: Toward Generalizable Parameter-Efficient Fine-Tuning for Biomedical Downstream Tasks

Saed Moradi, Benyamin Ghojogh, M. Hadi Sepanj +2

Parameter-efficient fine-tuning enables the adaptation of vision foundation models to biomedical tasks under limited computational resources, but a single low-rank update can const…

stat.ML2026

Data Evolution by Wittgenstein's Rule Following

Aydin Ghojogh, Benyamin Ghojogh

This paper introduces Wittgenstein's Rule Following (WRF) data evolution, a framework in philomatics for evolving or generating a new dataset from a sequence of previously observed…

cs.LG2026

Self-Supervised Learning by Curvature Alignment

Benyamin Ghojogh, M. Hadi Sepanj, Paul Fieguth

Self-supervised learning (SSL) has recently advanced through non-contrastive methods that couple an invariance term with variance, covariance, or redundancy-reduction penalties. Wh…

math.DG2026

Foundations of Riemannian Geometry for Riemannian Optimization: A Monograph with Detailed Derivations

Benyamin Ghojogh

Riemannian geometry provides the fundamental framework for optimization on nonlinear spaces such as matrix manifolds, which arise in machine learning, signal processing, and roboti…

stat.ML2026

Kernel VICReg for Self-Supervised Learning in Reproducing Kernel Hilbert Space

M. Hadi Sepanj, Benyamin Ghojogh, Saed Moradi +1

Self-supervised learning (SSL) has emerged as a powerful paradigm for representation learning by optimizing geometric objectives, such as invariance to augmentations, variance pres…

math.RA2026

Similarity Algebra: A Framework for Approximate Algebraic and Lie Structures with Collapse to Classical Algebra

Benyamin Ghojogh, Golbahar Amanpour

Classical algebraic structures require exact satisfaction of their defining axioms. We propose similarity algebra, a framework extending algebraic and Lie structures to settings wh…