You can find me on Bluesky 🦋! https://t.co/MRInWA68Mc

If we want AI agents to support Molecular Tumor Boards, we need benchmarks that capture real multimodal, longitudinal patient journeys. We introduce MTBBench (NeurIPS 2025 D&B track, Poster #1710) to evaluate AI agents in multimodal, sequential clinical decision-making settings.

Super important new benchmark is proposed here. MTBBench, creates the first test that actually checks whether an AI can handle real cancer cases that unfold over time with many data types, just like a molecular tumor board would. MTBBench builds a realistic cancer decision

MTBBench: A Multimodal Sequential Clinical Decision-Making Benchmark in Oncology Going beyond the standard single-turn multiple choice benchmarks, this paper introduces a multimodal longitudinal agentic benchmark that simulates tumor boards, where oncologists review patient

Some news from the lab & collabs: - Med-PRM (medical reasoning with guideline-verified process reward models) received an 𝐨𝐫𝐚𝐥 𝐩𝐫𝐞𝐬𝐞𝐧𝐭𝐚𝐭𝐢𝐨𝐧 at 𝐄𝐌𝐍𝐋𝐏! https://t.co/PupsVqqbPT - SMMILE got accepted to 𝐍𝐞𝐮𝐫𝐈𝐏𝐒 2025 (D&B track)

⌨️ 😇 Drafting for NeurIPS? Submit to #ICML2025 workshop on Scaling Up Intervention Models (SIM) too! Let’s enjoy some fun science in Vancouver this July. 🌞🌳 🗓️Workshop submission due on May 20 AOE 🔗More info: https://t.co/fyY4f22SJl

Excited to share that our work “Test-time view selection for multi-modal decision making” will be presented as an Oral at MLGenX, ICLR 2025 (27/04 9:15 am)!

🔥 Our workshop will take place in less than a week! In the meantime, check out the full schedule on our website and the strong lineup of invited speakers and panelists 💪 Looking forward to seeing you there!

What if AI could advance cell biology the way it did for protein folding? 🧬 In this video podcast, Head of Science @StephenQuake & EPFL’s @_bunnech join @EricTopol to discuss the virtual cell, a moonshot for digital biology. Watch:

Researchers have developed a deep learning protein language model, ESM3, that enables programmable protein design. Learn more in this week's issue of Science: https://t.co/PndjVQWjT5

I’m excited to co-host the new #AIxBio conference alongside @Avsecz, @ferruz_noelia, @pdhsu, @BenLehner, @ml19, @deboramarks, @p_tingying, @CarolineUhlerat at @wellcomegenome/ @sangerinstitute! We’ll focus on modellingz and designing DNA, RNA, proteins, and cells, as well as

I spoke with @Nature about the transformative potential of foundation models for biology—particularly in personalized medicine and clinical diagnostics. Take a look at the technologies to watch in 2025. An exciting year ahead in AI, biology and medicine! https://t.co/Zco6Utc1qS

📄Read the full paper: https://t.co/ghxNIo2Pni Would love to hear your thoughts! Feel free to reach out with questions.

This was a fantastic collaboration between researchers at @EPFL, the @EPFL_AI_Center, the @Unispital_USZ, and @UZH_en with co-authors @gabrigut , Andreas Wicki, Kiril Vasilev and @pariset_matteo! This is just the beginning - we’re excited of what is coming next!

🔎How? VirTues is built on a novel vision transformer architecture that efficiently processes high-dimensional data and flexible numbers of input channels while maintaining biological interpretability.

💡Why now? Spatial proteomics has just been announced ‘Method of the Year’ by @naturemethods due to its critical role in #clinical #diagnostics and #computational #pathology. VirTues is the first AI model that can handle the complexity and unique requirements of multiplex images

• Handle varying combinations of hundreds of protein markers without retraining. • Provide interpretable insights from molecular to tissue scales through its multi-scale design and novel attention. • Support clinical decisions through case retrieval and the creation.

🧬Our work tackles a key challenge in precision medicine: making sense of highly multiplexed tissue imaging data that captures dozens of molecular markers simultaneously. VirTues can: • Generate zero-shot virtual tissue representations across cancer types and diseases.

Led by PhD students @wencksternjo and @eeshaan_jain, we introduce the Virtual Tissues platform (VirTues), a foundation model framework for analyzing complex tissue architectures.

✨Excited to share our work on “AI-powered virtual tissues from spatial proteomics for clinical diagnostics and biomedical discovery” ( https://t.co/ghxNIo2Pni), building on our vision paper in @CellCellPress on multi-scale, multi-modal foundation models ( https://t.co/4Yf6w2oRlY).

We’re thrilled to welcome Charlotte Bunne (@_bunnech ), assistant professor at @EPFL, to our https://t.co/VXWIUz2RbS / NCT Data Science Seminar series on January 23rd at 4 pm in Heidelberg for a hybrid event. Join us for an engaging and inspiring session!