3 papers
cs.LG2026
LatentVerse: A Framework for Understanding Shared and Modality-Specific Information in Multimodal Latent Representations
Majd Alafrange, Samuel Friedman, John Kitonyo +2
Latent embeddings have become a central data abstraction in modern machine learning, especially in biomedicine, where foundation models are increasingly used to encode multimodal d…
cs.AI2026
Protecting patient privacy in clinical foundation models: Technical and legal perspectives
Sana Tonekaboni, Lena Stempfle, Sasha Ronaghi +4
Clinical foundation models trained on large-scale patient data are increasingly used for decision support, screening, and public health. As deployment expands, privacy risk increas…
cs.CL2026
Clinically Grounded Privacy Evaluation of Medical LMs
Sasha Ronaghi, Sana Tonekaboni, Lena Stempfle +6
Medical language models (LMs) can memorize and reproduce protected health information, but privacy evaluations often focus on recovery of training text rather than disclosure under…