3 papers
cs.LG2026
Concept frustration: Aligning human concepts and machine representations
Enrico Parisini, Christopher J. Soelistyo, Ahab Isaac +2
Aligning human-interpretable concepts with the internal representations learned by modern machine learning systems remains a central challenge for interpretable AI. We introduce a…
cs.LG2026
Leakage and Interpretability in Concept-Based Models
Enrico Parisini, Tapabrata Chakraborti, Chris Harbron +2
Concept-based Models aim to improve interpretability by predicting high-level intermediate concepts, representing a promising approach for deployment in high-risk scenarios. Howeve…
cs.CV2026
Generating crossmodal gene expression from cancer histopathology improves multimodal AI predictions
Samiran Dey, Christopher R. S. Banerji, Partha Basuchowdhuri +3
Emerging research has highlighted that artificial intelligence-based multimodal fusion of digital pathology and transcriptomic features can improve cancer diagnosis (grading/subtyp…