4 papers
Answer or Defer? Testing VLMs' Stated Confidence on Brain MRI
Amir Sabbaghziarani, Parsa Ghazvinian, Sepehr Salem +1
Vision-language models (VLMs) could support medical-image interpretation, but their use requires deciding which interpretations to accept and which images to refer to a clinician.…
Label Agreement Does Not Measure Authorization
Amir Sabbaghziarani, Bradley Thomas Baker, Theodore J. LaGrow +1
Many groups now delegate label ontology and metadata harmonization to agentic LLM pipelines. We built one and audited it. Our aggregate scores looked healthy, but the pipeline kept…
FlexSplat: Flexible Feed-Forward 3D Gaussian Splatting without Point Cloud Correspondence
Amir Sabbaghziarani, Hanting Ye, Maria Gorlatova +1
We present FlexSplat, a feed-forward framework for novel view synthesis (NVS) from uncalibrated, object-centric multi-view image collections. A recent line of query-based methods r…
Confident but Unreliable: A Behavioral Safety Audit of Vision-Language Models on Brain MRI
Amir Sabbaghziarani, Mohammadsajad Abavisani, Sergey Plis
Vision-language models (VLMs), including medical specialists, are increasingly proposed for medical imaging, yet their stated confidence is rarely evaluated separately from correct…