AI researcher · Palo Alto
I work in radiology AI to help radiologists save time.
Lead or senior author in Nature, Nature Medicine, Nature Biomedical Engineering, ACL, EMNLP, NeurIPS and ICLR.
Long-form reading notes on radiology AI papers, with a focus on report generation.
A MICCAI 2025 study swaps the LLM, the projector, the tuning method and the input size of a 3D CT report generator trained on 1,287 scans. No change to the model adds more than 0.006 GREEN, while canned “normal” sentences add 0.078. What that says about small-data training, and about the metric.
The report-generation side of Merlin, the abdominal CT foundation model published in Nature: 490 visual tokens, one linear adapter and a LoRA-tuned language model writing one organ section at a time, what the scores show, and why the released dataset matters more.
The report-generation side of NVIDIA’s NV-Reason-CT: all 13,824 visual tokens, radiologist-guided reasoning data and GRPO on finding lists, and what its CT-RATE, Merlin and RAD-ChestCT comparisons can and can’t support.
