Congrats @Cross_JL & @Shawnwahi on presenting our work on leveraging SOTA #LLMs to extract CMR indications showing that in terms of accuracy: 1) commercial > open source, 2) general > medical pretrained, 3) with reasoning being similar to non reasoning models @AHAScience#AHA25
Introducing BrainLM 🧠🤖the first foundation model for #fMRI analysis trained on 6,700 hours of brain activity data! Fine-tune for specialized tasks or leverage zero-shot inference capabilities!
@WuTsaiYale@YaleCompsci@YaleCBB@YaleMed
https://t.co/MUobqXULfb