Manuscript · 2026
Vision-language models for digital pathology
Evaluation of computational pathology vision-language foundation model for few-shot histopathology classification with adapting modules
Amirmohammad
(Amir) Mohammadi.
PhD from Texas A&M University
I develop methods that help AI models adapt to new settings with stronger performance and lower computational costs. My work spans parameter-efficient fine-tuning, physics-informed modeling, and model evaluation, including settings with limited labeled data and noisy signals. I apply these approaches to digital health, computer vision, acoustics, and sensing.
Publications
Research highlights
IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · 2026
Distribution-aware foundation-model adaptation
Distribution-aware adaptation of pretrained Transformers for passive and active sonar classification by developing and integrating a learnable histogram module.
IEEE Sensors Journal · 2022
Integrated wearable sensor for mental stress detection
An integrated wearable sensing platform, connecting low-power circuitry, physiological measurements, and supervised stress classification.