🚨 Just published in @Nature_NPJ Artificial Intelligence! 💡 Speech data can be as sensitive as images. ✅ We successfully applied DP to DL training on medical speech data ⚖️ Utility tradeoff remains high, but fairness behavior is more complex 🔍

Are you ready for web-scale pre-training with RL ? 🚀 🔥 New paper: RLP : Reinforcement Learning Pre‑training We flip the usual recipe for reasoning LLMs: instead of saving RL for post‑training, we bring exploration into pretraining. Core idea: treat chain‑of‑thought as an

📢 New #preprint: Agentic LLMs improve retrieval-based radiology QA 🧠 Our #agentic #RAG framework lets #LLMs iteratively retrieve & synthesize evidence. ✅ 25 models analyzed (500M→670B) 📈 Accuracy ↑ in mid/small models 🤖 Hallucinations ↓ ~9% 📖

We're proud to welcome the journal's 2025-2027 Trainee Editorial Board! Learn more about these talented individuals: https://t.co/Pekb0y3uNv

#RadioRAG introduces real-time data retrieval to support the accuracy & factuality of LLMs in radiologic diagnosis https://t.co/9o8PLjuwNY @starasteh @DanielTruhn @laim_uka #retrieval #Radiopaedia #radiology

„PhD-Level“ Intelligence GPT5 still fails the „first do A, then B(A)“ test. A PhD student in Germany clearly does have such capabilities. GPT unfortunately, not. I don’t feel the AGI today.

🚨 Just published in @Radiology_AI! #RadioRAG: Online Retrieval–Augmented Generation for #Radiology QA 💡Goes beyond static #LLMs by integrating live data from @Radiopaedia 🔓Open-source code & datasets! 📖 https://t.co/7NIMyA5T0w #AI #RAG #ChatGPT #LangChain #Mistral #Llama3

RadioRAG retrieves context-specific information from #Radiopaedia in real-time https://t.co/9o8PLjuwNY @starasteh @DanielTruhn @laim_uka #RAG #LLM #RadioRAG

RadioRAG retrieves context-specific information from #Radiopaedia in real-time https://t.co/9o8PLjuwNY @starasteh @DanielTruhn @laim_uka #LLMs #radiology #AI

#LLMs using radiology retrieval-augmented generation (RadioRAG) showed variable performance in answering case-based radiology questions https://t.co/9o8PLjuwNY @starasteh @DanielTruhn @laim_uka #Radiopaedia #radiology #AI

#RadioRAG shows potential to improve LLM accuracy in radiology question answering by integrating real-time domain-specific data https://t.co/9o8PLjuwNY @SNM_MI #SNMMI25 #NucMed #MolRad #radiology

Just crossed 1,000 citations on Google Scholar! Huge thanks to everyone I've collaborated with and learned from along the way, couldn’t have done it without you! https://t.co/MZCa5eYQXR

#ThrowbackThursday – @starasteh @GKaissis @DanielTruhn investigate differential privacy and analyze its impact on #AI model performance (Jan 2024) https://t.co/L10NEa2Xjz #ML #MachineLearning #ArtificialIntelligence

The Treasure Trove Hidden in Plain Sight: The Utility of GPT-4 in Chest Radiograph Evaluation | Radiology This study evaluates the potential of OpenAI’s GPT-4 with Advanced Data Analysis (ADA) to help radiologists analyze large medical datasets. The researchers tested GPT-4’s

🚀 New Publication Alert in @RSNA @radiology_rsna ! 🚀 How good are #LLMs like #GPT4 at statistics? Our latest study explores how #GPT4 assists with basic to advanced stats and machine learning 🩺📊 and where it gets the concepts wrong! ☹ Full article:

OpenAI’s GPT-4 with Advanced Data Analysis performed basic statistical analyses and built ML-based models to evaluate a chest radiography dataset, performing similarly to its manually crafted counterpart. @laim_uka @starasteh @DanielTruhn @naebbi22 https://t.co/vQ8PW4yYKc

🚨Overwhelmed with daily tasks as a #radiologist? No time to learn #AI development to simplify your work? #LLMs like #GPT4 can autonomously assist—no programming knowledge needed! Our latest @radiology_rsna paper shows how:

It is impressive to see how quickly AI is being used in medicine. The German magazine "Der SPIEGEL" recently reported on how LLMs will be used to make diagnoses in the future. It is important to note that, despite all the challenges surrounding modern AI (hallucinations), the

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

This year’s #NobelPrize laureates in chemistry have revealed proteins’ secrets through computing and artificial intelligence. Chemists have long dreamed of fully understanding and mastering the chemical tools of life – proteins. This dream is now within reach. 2024 chemistry