Computational pathology
Exploring foundation and vision-language models for computational pathology, with an emphasis on understanding their predictions.
Research
Explainable & robust AI
Studying how explainability algorithms reveal model behavior, and how adversarial attacks expose vulnerabilities in learned predictions.
Graph learning
Using graph-based multi-task learning for fault detection and event diagnosis in smart grids.
Selected work
Publications
Journal2027
CThoughtPathNet: Expert-Guided Vision–Language Reasoning for Few-Shot Cancer Subtyping in Whole-Slide Pathology
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) JournalUnder review
Expert-guided vision–language reasoning for few-shot cancer subtyping in whole-slide pathology.
Conference2026
INVEX: Label-Free Pathology Foundation Model Ranking via Invariance and Expressiveness
IEEE International Conference on Big Data (IEEE BigData) ConferenceAccepted
Ranking pathology foundation models without labels using invariance and expressiveness.
Conference2027
MOSAIC: Towards a Universal Latent Space for Computational Pathology Foundation Models
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) ConferenceAccepted
Exploring a universal latent space for computational pathology foundation models.