1) Preference Fine-Tuning for Factuality in Chest X-Ray Interpretation Models Without Human Feedback presents a practical recipe for improving and scaling expert human quality report generation in high-stakes domains: using LLM-as-Judge for preference tuning in radiology report

New European Spine J study introducing novel method for 3D analysis of lumbar paraspinal intramuscular fat. Method may deliver key insights into the interplay between #muscle #health and #lowbackpain. doi.org/10.1007/s00586… Stanford Pain Medicine NeuroPoly

So proud of the release of the GREEN metric. See what you can do when you merge medical AI research and open-sourceness. 26,000 downloads on 🤗 Hugging Face and counting. 🟥 EMNLP proceedings: aclanthology.org/2024.findings-… 🤗 Dataset: huggingface.co/datasets/Stanf… 🤗 Models:

If you are at #NeurIPS2024, don't miss a chance to chat with Maya Varma on how to mitigate spurious correlations found in VLMs!

Inspired by a few of my conversations with Akshay Chaudhari I decided to spend my winter break redesigning the stock Health app with an AI focused approach starting with clinical records. The goal here was to help patients get a deeper understanding of their own records

The most powerful agent, interpreting X-rays is opensource🤗

Does everything seem like a foundation model these days? We tried to add some rigor and definitions to help with the process! Kudos to Magda Paschali for leading this work, which is now published in Radiology.

A fine-tuned, open-source LLM (Mistral-7B) extracted clinical history from imaging orders, showing strong agreement with radiologists & rivaling GPT-4 Turbo. Dive into the findings: Magda Paschali Akshay Chaudhari @stanfordradiology @stanfordaide #AI #Radiology pubs.rsna.org/doi/10.1148/ra…