activity
20242026
collaborators

8 papers

eess.IV2026

BreastMammo and DenseMammo: Benchmarks for Mammography Domain Generalization

Hongyi Pan, Gorkem Durak, Halil Ertugrul Aktas +18

Breast density classification is a critical component of breast cancer risk assessment, yet AI models often struggle to generalize across clinical sites due to vendor-specific acqu…

cs.CV2026

HamVision: Hamiltonian Dynamics as Inductive Bias for Medical Image Analysis

Mohamed A Mabrok

We present HamVision, a framework for medical image analysis that uses the damped harmonic oscillator, a fundamental building block of signal processing, as a structured inductive…

cs.LG2026

Latent Semantic Manifolds in Large Language Models

Mohamed A. Mabrok

Large Language Models (LLMs) perform internal computations in continuous vector spaces yet produce discrete tokens -- a fundamental mismatch whose geometric consequences remain poo…

cs.LG2025

Controllability Analysis of State Space-based Language Model

Mohamed Mabrok, Yalda Zafari

State-space models (SSMs), particularly Mamba, have become powerful architectures for sequence modeling, yet their internal dynamics remain poorly understood compared to attention-…

cs.CV2025

X-VMamba: Explainable Vision Mamba

Mohamed A. Mabrok, Yalda Zafari

State Space Models (SSMs), particularly the Mamba architecture, have recently emerged as powerful alternatives to Transformers for sequence modeling, offering linear computational…

eess.IV2025

MammoClean: Toward Reproducible and Bias-Aware AI in Mammography through Dataset Harmonization

Yalda Zafari, Hongyi Pan, Gorkem Durak +3

The development of clinically reliable artificial intelligence (AI) systems for mammography is hindered by profound heterogeneity in data quality, metadata standards, and populatio…