Parvin Mousavi

Instruction tuning degrades the latent moral geometry of LLMs, even though distribution-driven steering vectors can naturally mirror human value topologies to enable coherent cross-value generalization.

Learning surgical concepts directly from noisy intraoperative data could revolutionize how we assess surgical margins in real-time.

Multi-view analysis of μUS data can dramatically enhance prostate cancer detection, outperforming traditional methods and expert assessments.