RT @Zhang_Yu_hui: 🧬 What if we could build a virtual cell to predict how it responds to drugs or genetic perturbations?. Super excited to i….

RT @AkliluJosiah2: There’s growing excitement around VLMs and their potential to transform surgery🏥—but where exactly are we on the path to….

Join millions who have switched to Grok.

Shout out to my stellar first co-authors @minwsun and @jmhb0 for leading this effort, as well as the incredible team of computer scientists, statisticians,  biologists, and clinicians that made this possible: @jnirsch.Christopher Polzak, @Zhang_Yu_hui, @cliangyu_, Jeffrey Gu,.

Earlier this year, we released the BIOMEDICA dataset, featuring 24 million unique image caption pairs and 30 million image references derived from open-source biomedical literature. It's been great to see the community engaging with it—we're currently seeing around 6K downloads

Introducing video differencing, a new task for detecting differences between video frames. Notably, even the most advanced Video LLMs struggle with this challenge, underscoring the long road ahead!.

RT @kevinywu: Which LLMs work best for medical queries? 🩺✨ Introducing MedArena 🏥—the first chatbot arena just for clinicians ⚕️!. 👩‍⚕️👨‍⚕️….

Check out our new work accepted to ICLR 2025. We introduce time-to-event (TTE) pretraining to leverage temporal supervision from longitudinal EHR data and estimate the risk of future events. By scaling to 225M clinical events, we achieve SOTA prognostic performance!.

RT @XiaohanWang96: 🚀 Introducing Temporal Preference Optimization (TPO) – a video-centric post-training framework that enhances temporal gr….

Work done at.@StanfordAILab.

[10/10. @cliangyu_,@jnirsch, Jeffrey Gu, Ivan Lopez,.@AkliluJosiah2, Austin Katzer, Collin Chiu, Anita Rau,.@XiaohanWang96,@Zhang_Yu_hui, Alfred Song,.@robtibshirani,@yeung_levy.

[9/10] Shout out to my stellar first co-authors. @minwsun and @jmhb0 for leading this effort, as well as the incredible team of computer scientists, statisticians, biologists, and clinicians that made this possible:.

[8/10]. While our models offer state-of-the-art performance, all evaluations indicate that there is still significant room for improvement. We release all our contributions under a permissive license to facilitate broader use and further development.

[7/10] 💡 We demonstrate the utility and accessibility of our resource by training BMC-CLIP, a suite of CLIP-style models continuously pre-trained on our dataset using different training recipes via streaming.

[6/10]. 🎯 We demonstrate the utility and accessibility of our resource by training BMC-CLIP, a suite of CLIP-style models continuously pre-trained on our dataset using different training recipes via streaming.

[5/10]. 💵 Our archive is hosted in HuggingFace, enabling streaming. Eliminating the need to download 3.9 TB of data locally in order to use BIOMEDICA.

[4/10]. ⚡Our archive is serialized as a webdataset. Providing 3x-10x higher I/O rates when compared to random access memory (decreasing GPU idle time).

[3/10]. 🗄️Rather than pre-filtering to specific domains, we provide ~10x more metadata and expert-derived annotations at various granularities. Subsequently, we offer a pipeline to use these metadata and filter on demand, accommodating to different interests in the community.

[2/10]. Our framework produces a comprehensive archive with over 24M unique image-text pairs, including image-captions, image-references, full metadata, and human derived annotations from over 6M articles, that can be freely used by the community for model training.

Biomedical datasets are often confined to specific domains, missing valuable insights from adjacent fields. To bridge this gap, we present BIOMEDICA: an open-source framework to extract and serialize PMC-OA. 📄Paper: .🌐Website:

RT @Zhang_Yu_hui: 🔍 Vision language models are getting better - but how do we evaluate them reliably? Introducing AutoConverter: transformi….