collaborators

16 papers

cs.CV2026

Self-supervision drives representational convergence in medical foundation models more than clinical supervision

Soroosh Tayebi Arasteh, Sebastian Ziegelmayer, Mahshad Lotfinia +4

Medical image encoders from different groups are increasingly treated as interchangeable, on the assumption that scale and clinical supervision concentrate their representations on…

cs.LG2026

CANDOR: Chance-Calibrated Discordance in Frozen Foundation Encoders

Soroosh Tayebi Arasteh, Sven Nebelung, Daniel Truhn

Frozen encoders are chosen by how well a lightweight head reads a finding from their features, not whether the geometry separates it. Nearest-neighbor discordance does, but with un…

cs.CL2026

The strength of clinical evidence is recoverable from language model representations but not from their stated grades

Soroosh Tayebi Arasteh

Large language models (LLMs) increasingly summarize clinical evidence, where a claim's weight depends on how strongly it is supported. Yet these models convey confidence poorly, an…

cs.CV2026

Vision-language models for chest radiography do not always need the image

Mahshad Lotfinia, Sebastian Ziegelmayer, Lisa Adams +3

Medical vision-language models report strong chest radiograph accuracy, and this is increasingly read as evidence that they use the image. That inference is unsafe: a model exploit…

cs.CV2026

Cross-modal linkage risk in clinical vision-language models

Soroosh Tayebi Arasteh, Mahshad Lotfinia, Sven Nebelung +1

Vision-language models (VLMs) trained on paired chest radiographs and radiology reports learn a shared embedding space that can preserve instance-level image-report correspondence.…

eess.AS2026

Perceptual implications of automatic anonymization in pathological speech

Soroosh Tayebi Arasteh, Saba Afza, Tri-Thien Nguyen +11

Automatic anonymization is increasingly used to enable ethical sharing of clinical speech, yet its perceptual and clinical consequences remain undercharacterized. We present a huma…