🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

BREAKING NEWS The Royal Swedish Academy of Sciences has decided to award the 2024 #NobelPrize in Physics to John J. Hopfield and Geoffrey E. Hinton “for foundational discoveries and inventions that enable machine learning with artificial neural networks.”

New meta-analysis: Moderate agreement among 146 thoracic radiologists on ILD diagnosis (k=0.61), lower for specific HRCT features (k=0.56). Radiology Radiology: Cardiothoracic Imaging Don't stress over differing reports! 😄 pubs.rsna.org/doi/full/10.11…

Our latest work improves chest x-ray report generation with LLM alignment tools! We build a scalable preference fine-tuning pipeline to improve automated metrics + expert rad. win rates—all WITHOUT any radiologist feedback. Preference alignment w/o needing human preference. 1/3

A Johns Hopkins University study found that measuring 162 quality metrics cost >$5 mil. Our team at UC San Diego Health, led by Drs. Aaron Boussina and Shamim Nemati, found that LLMs are a great way to scale quality measurement - needed for a learning health system. Paper: ai.nejm.org/stoken/default…

The internet has been progressively diluted with AI-generated slop. Are medical records headed for the same fate? 🧵 I just published a perspective in NEJM with Adam Rodman and Arjun Manrai on why rushing AI into medical documentation could be a mistake.

not there yet 🤷‍♂️

absolute superstar lineup, can highly recommend this team! see 🧵 for ways to join them.

Speaker at #RSNA24 says that online “grand challenge” competitions are the equivalent of clinical trials for medical #AI. I think these competitions have a lot of value, but I don’t think they can in any way take the place of true clinical trials.

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:

🦙 LLama 3.3 70B is already plugged to 🤗 Hugging Face paper-central to chat with any research papers, powered by Hyperbolic. Try it out: huggingface.co/spaces/hugging…

(1/4) Excited to share RaVL, which is appearing this week at #NeurIPS2024! RaVL discovers and mitigates spurious correlations in fine-tuned vision-language models (VLMs). 📄 Paper: arxiv.org/abs/2411.04097 💻 GitHub: github.com/Stanford-AIMI/…

Join us tomorrow for the session "Future Frontiers in Health AI: Emerging Technologies and Innovations" on the second day of #AIPlusHealth24 #Radiology Stanford AIMI

The future may be painful and confusing for vast swaths of the laptop striver class.

internal medicine residency

Curious how large language models fit into radiology? 💬🧠 In this article, Curt Langlotz, Akshay Chaudhari and team break down what radiologists need to know, from limitations to smart prompting to fine-tuning tips. A must-read guide! #Radiology #AI pubs.rsna.org/doi/10.1148/ra…

💥 We unveil our paper accepted at the #ACL2025 Main Conference: Automated Structured Report Generation Let's revisit automated radiology report generation for CXR. Free-form reports make it hard for AI systems to learn accurate generation, and even harder to evaluate. 🧵👇

what's crazy about all of these top AI researchers making 10-100m dollars is that literally every single one of them is a Dota 2 player. like all of them. if you played Dota 2, there is a good chance that you were in a lobby with them or me