Welcome to stop by our poster! Ziyang is presenting at #85 at #KDD2024.

🎉 Extremely honored that our paper "A Preliminary Study of o1 in Medicine: Are We Getting Closer to an AI Doctor?" has been selected as the medical AI paper of the week! 🏆 Huge thanks to Open Life Science AI 🔍 Key Highlights: - Benchmarking OpenAI’s o1(-preview) on 37 medical

Thrilled to unveil our⚡️Lightning Talks⚡️ for Michigan AI Symposium! Join us to hear from: Zanë ([email protected]) (Harvard University) Hejie Cui Hejie Cui, Aishwarya Mandyam Aishwarya Mandyam (Stanford University) Gabe Margolis Gabe Margolis (MIT CSAIL) Ilija Radosavovic Ilija Radosavovic, Qianqian Wang (UC Berkeley)

Excited to present two papers at #NeurIPS 2024 this week! Stop by our posters if you're interested in LLMs, graphs, or health AI! I'm looking forward to reconnecting with familiar faces and meeting new friends! 🍻

🎉 We're thrilled to announce the general release of three de-identified, longitudinal EHR datasets from Stanford Medicine—now freely available for non-commercial research-use worldwide! 🚀 Read our HAI blog post for more details: hai.stanford.edu/news/advancing… 𝗗𝗮𝘁𝗮𝘀𝗲𝘁

We build 𝗠𝗲𝗱𝗛𝗘𝗟𝗠✨: a comprehensive benchmark evaluating AI on realistic clinical tasks that healthcare professionals perform daily instead of just medical exams.👩‍⚕️⚕️ • Stanford HAI Blog: hai.stanford.edu/news/holistic-… • Leaderboard: crfm.stanford.edu/helm/medhelm/l…

Introducing TIMER⌛️: a temporal instruction modeling and evaluation framework for longitudinal clinical records! 🏥📈 TIMER tackles challenges in processing longitudinal medical records—including temporal reasoning, multi-visit synthesis, and patient trajectory analysis. It

Excited to share our latest benchmark: CLIMB, where we built a solid data foundation for multimodal clinical models. With 4.51M patient samples, totaling 19.01 TB of data across 13 domains, it's currently the largest public clinical benchmark! Paper: arxiv.org/abs/2503.07667 Code:

As artificial intelligence pervades health and medicine, Stanford Medicine researchers have developed a new evaluation framework to help scientists determine which type of algorithms are best suited for health care. scopeblog.stanford.edu/2025/04/08/ai-…

🎉 Excited to present our #ICLR2025 work—leveraging future medical outcomes to improve pretraining for prognostic vision models. 🖼️ "Time-to-Event Pretraining for 3D Medical Imaging" 👉 Hall 3+2B #23 📍 Sat 26 Apr, 10 AM–12:30 PM 🔗 iclr.cc/virtual/2025/p…

Excited to present this work at ICLR's SynthData Workshop on Sunday April 27! Come through from 11:30-12:30 @ Peridot 202-203 to talk anything synthetic data for post-training, benchmarking, and AI for healthcare in general.

Congrats! [email protected]

🔥 New paper at #ICML2025 (Oral)! “Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation” We introduce CSR – fast, sparse, adaptive. ✅ No retraining ✅ Better accuracy ✅ Flexible inference 🎤 Oral: Wed 3:45PM @ West Hall C 🖼 Poster: #E-1705, 4:30–7PM 📄

Thanks everyone for the interest in our work! 🧗🏻

The paper introduces WebCoach, a memory tool that helps web agents remember past browsing sessions and avoid repeating mistakes. With a 38B open source model, WebCoach raises success from 47% to 61%, and tests on 643 live tasks show that this cross session memory from the

Can we make Web Agents stop repeating the same mistakes? Yes, with Cross-Session Memory. 🧠 We present WebCoach: 💾 Learns from experience (no retraining needed). ✨ Model-agnostic framework. 🚀 +14% gain on WebVoyager (47% -> 61% with a 38B model), comparable with GPT-4o