📣 We are excited and thrilled to announce APOLLO, a healthcare system-scale multimodal temporal foundation model for virtual patient representations. Trained on 25 billion clinical events from 7.2 million patients across 33 years and 28 modalities, APOLLO learns a unified atlas of medicine. Turning labs, notes, pathology images, medications, and diagnoses into coherent, computable longitudinal trajectories. APOLLO is disease-agnostic by design, a single model that learns the shared structure underlying human health and disease across every specialty, modality, and stage of care. The possibilities are enormous: earlier risk prediction, treatment response modeling, clinical trial matching, biomarker discovery, and a new generation of agentic systems built on rich patient representations. Read the pre-print: arxiv.org/pdf/2604.18570 Read our blog post about the work: linkedin.com/pulse/apollo-mu… 👏 🎉Huge congratulations to Andrew Zhang , @TongDing99, Sophia J. Wagner, and the rest of the team.

Tokenizing a patient's health arc. Our new @TheLancet essay just published @AI4Pathology and I review the implications of 5 AI large recent health models, which includes prediction (and prevention) many years out thelancet.com/journals/lance…

The people behind the science. Couldn’t ask for a better team.

Congratulations to Luca Weishaupt on a fantastic PhD defense and on becoming the fifth PhD student to graduate from our group. A wonderful milestone, very proud of Luca and excited to see what comes next!

Happy 4th of July! 🇺🇸 Celebrating our ideals of freedom, unity, & opportunity that bind us all. To our service members, veterans & first responders who safeguard our freedoms, thank you for your dedication. Wishing everyone a safe, joyful Independence Day! #FourthOfJuly

For medical information, general AI frontier models (Google, OpenAI, Anthropic) outperformed specialized @openevidence and @UpToDate as assessed by 12 US clinicians, randomized and blinded to which model and extensive testing/benchmarks. This was not anticipated. @NatureMedicine nature.com/articles/s41591-0…

Please join us on June 3rd in Room 607 for the #CVPR2026 Foundation Models for Medical Vision (FMV) workshop! Four world-leading keynote speakers, @jnkath, @AI4Pathology, @hoifungpoon, and @pranavrajpurkar will share cutting-edge AI models across oncology, pathology, virtual patients, and agentic systems. Plus: winners of our medical image foundation model challenges will give highlights on their solutions. 🔗 fmv-cvpr26workshop.github.io… @yuyinzhou_cs @vishalm_patel @BoWang87 @CVPR

At #CVPR2026 @CVPR this week? Join the 1st Med-Reasoner Workshop Thurs June 4 · 1:00–6:00 PM MDT · Room 110 med-reasoner.github.io/cvpr2… @nouhadziri @JiaWu_PhD @Ale9806_ @hoifungpoon @AI4Pathology @iScienceLuvr @yeung_levy @MariaXenoch

Be part of the Hallmarks of cancer legacy. Join our distinguished keynote speakers Johanna Joyce @Joycelab & Faisal Mahmood @AI4Pathology in Sitges, Spain, November 1–3, 2026. Abstract deadline: June 26, 2026 🔗hubs.li/Q04h5Zwj0 @CellPressEvents #CSHallmarks2026

Be part of the Hallmarks of cancer legacy. Join our distinguished keynote speakers Johanna Joyce @Joycelab & Faisal Mahmood @AI4Pathology in Sitges, Spain, November 1–3, 2026. Abstract deadline: June 26, 2026 🔗hubs.li/Q04h4SSz0 @CellPressEvents #CSHallmarks2026

🎉 🎊 Congratulations to our superstar @anurag_vaidya7 on successfully defending his PhD at @mit_hst! 🎓 During his PhD Anurag led an extraordinary body of work spanning multimodal outcome prediction (SurvPath, CVPR 2024), a landmark audit of demographic bias in computational pathology (Nature Medicine, 2024), and multiple foundation models that have pushed the field forward: MADELEINE (ECCV 2025), THREADS (Nature Cancer, 2026, to appear), and KRONOS. A unifying idea behind much of this work: biology is a powerful learning signal. It has been a privilege to advise @anurag_vaidya7 and to watch him grow into an independent scientist. Proud of all he has accomplished, and excited for what comes next.

Harvard Students’ AI Usage: Requires new educational formats pronto. HT @NAchristakis thecrimson.com/article/2026/…

Wonderful planark talks from @moofaca and @AI4Pathology

If you're at #ICLR2026, come see very cool work from our superstar @Daniel__Shao. In MIL for computational pathology, the per-patch linear projection is the binding constraint. MAMMOTH replaces it with a multi-head soft MoE of low-rank experts at matched parameter count, and the effect dominates aggregator choice: swapping the projection matters more than swapping the MIL architecture. 📍 Poster session: 10:30 am – 1 pm BRT at Pavilion 4, P4 #5105 📄 Paper: arxiv.org/abs/2603.22198 💻 Code: github.com/mahmoodlab/MAMMOT… 🔗 OpenReview: openreview.net/forum?id=S5Io… Read the blog post: lnkd.in/eyV4WWzj

Jakob Nikolas Kather chaired today's #AACR26 Plenary Session on "The AI Revolution in Cancer Research," featuring Jure Leskovec, Bo Wang, Suchi Saria, and Faisal Mahmood. @jnkath @jure @BoWang87 @suchisaria @AI4Pathology

At #AACR26, Faisal Mahmood, PhD (@AI4Pathology @harvardmed) provides insights on multimodal, generative, and agentic AI for oncology.

Excited to kick off an action-packed week at #AACR2026 showcasing our work on multimodal whole patient foundation models, 3D spatial transcriptomics and much more. I’m honored to deliver a plenary talk tomorrow: April 20, 9:29AM – “Multimodal, generative, and agentic AI for oncology” Here’s where else you can find our team: Today (April 19, 2:00–5:00 PM) • *33: “A healthcare system scale multimodal whole patient temporal foundation model” – led by Andrew Zhang @TongDing99 Sophia J. Wagner • *77: “AI-driven 3D spatial transcriptomics for 3D tumor microenvironment mapping in prostate adenocarcinoma” – led by @Criis_perez99 @GreatAndrew90 April 21 • 9:00 AM–12:00 PM: *4163 – “A general-purpose AI foundation model for spatial proteomics” – led by @GreatAndrew90 @anurag_vaidya7 joint work with @SizunJ • 2:00–5:00 PM: *5469 – “Data-efficient morphological deep learning for fine-grained Gleason grading based on AI-triaged 3D pathology” – led by Renao Yan joint work with Jonathan Liu #AACR2026 #AIinCancer #ComputationalPathology #SpatialBiology #MultimodalAI #CancerResearch

Better than reviewer #2 in large scale AI-Assisted Peer Review: The AAAI-26 AI Review Pilot arxiv.org/abs/2604.13940