You can find me on Bluesky 🦋!.

RT @JiaqiZhangVic: ⌨️ 😇 Drafting for NeurIPS? Submit to #ICML2025 workshop on Scaling Up Intervention Models (SIM) too!. Let’s enjoy some f….

RT @eeshaan_jain: Excited to share that our work “Test-time view selection for multi-modal decision making” will be presented as an Oral at….

RT @ai4na_workshop: 🔥 Our workshop will take place in less than a week! In the meantime, check out the full schedule on our website and the….

RT @ChanZuckerberg: What if AI could advance cell biology the way it did for protein folding? 🧬 In this video podcast, Head of Science @Ste….

RT @ScienceMagazine: Researchers have developed a deep learning protein language model, ESM3, that enables programmable protein design. Le….

RT @mo_lotfollahi: I’m excited to co-host the new #AIxBio conference alongside @Avsecz, @ferruz_noelia, @pdhsu, @BenLehner, @ml19, @deboram….

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!.

📄Read the full paper: 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” (, building on our vision paper in @CellCellPress on multi-scale, multi-modal foundation models (.

RT @CarTLueth: We’re thrilled to welcome Charlotte Bunne (@_bunnech ), assistant professor at @EPFL, to our / NCT D….

RT @KristinaUlicna: Exciting news! 🚀 The Learning Meaningful Representations of Life (#LMRL 🌟) workshop is returning at #ICLR2025! 🎉.On 27t….

RT @CellPressNews: Out now in @CellCellPress! How to build the virtual cell with artificial intelligence: Priorities and opportunities. @P….

RT @cziscience: We recently shared a hub for AI-powered cell models with tools for researchers. In @CellPressNews today: Our vision for AI….

Now out in @CellCellPress! Stay tuned for exciting work coming out of my lab soon!. Aaand we are #hiring #PhD students @EPFL. Deadline is December 15. Check out our lab webpage for more information.