🔥Telegram İfşa

💡Diffsurv: Differentiable sorting for censored time-to-event data 👏Great work from AI-Enabled Healthcare Systems CDT at UCL The UCL Institute of Health Informatics colleagues Andre Vauvelle Spiros Denaxas 🦆 🧑‍🏫 ICLR 2026 Time Series Representation Learning 4 Health @ICLR openreview.net/forum?id=29-Zs…

Echo chambers in the honeybee dance communication! We automatically detected 100K waggle phases of dancing bees and found a fascinating aspect of how bees organize their colony space. A thread.

Over the past few months, @gogothorr and I have been heads down building Pheiron . Our platform extracts disease markers from biomedical data to aim right: identifying the right targets for diseases and the right populations for clinical trials. This is personal to us:

Ten months ago, we launched the Vesuvius Challenge to solve the ancient problem of the Herculaneum Papyri, a library of scrolls that were flash-fried by the eruption of Mount Vesuvius in 79 AD. Today we are overjoyed to announce that our crazy project has succeeded. After 2000

Amazing work from YoussefNader!

Does removing unsupported facts in the training or prompting data effectively reduce hallucinations? We tested this for GPT-4 & Llama 2 for generating patient summaries. W/ Shannon Shen, Florian Gierse, Monica Agrawal, David Sontag, Xiaoyi Jiang arxiv.org/abs/2402.15422 1/7

Thrilled to share our Nature Biotechnology paper “Multistate and functional protein design using RoseTTAFold sequence space diffusion” nature.com/articles/s4158….

How does DeepSeek compare with other LLMs for clinical diagnosis and treatment plan—125 patient case benchmarks, not real world medicine nature.com/articles/s4159…

Current multimodal single-cell integration methods act as black boxes, lacking meaningful interpretability. We introduce NetworkVI, a VAE that performs integration via gene-gene interactions and the Gene Ontology for biologically grounded analysis. biorxiv.org/content/10.110…

NetworkVI is a group effort by Julius Upmeier zu Belzen, Luis Herrmann, Khue Nguyen, supervised by Fabian Theis & Benjamin Wild & Roland Eils at Charité - Universitätsmedizin Berlin and Helmholtz Munich | @HelmholtzMunich. Code: github.com/LArnoldt/netwo… Preprint: biorxiv.org/content/10.110… 🧠 Open-source & ready to use!

🚨 Machine Learning for Health (ML4H) is back and better than ever! 🌴 Join us in San Diego on December 1–2, 2025, right before NeurIPS Conference! 📢 Call for Papers is LIVE → ahli.cc/ml4h/call-for-… ⏳ Deadline: Sept 8 — don’t miss it! 🔁 RT and follow ML4H for updates!

NeurIPS is pleased to officially endorse EurIPS, an independently-organized meeting taking place in Copenhagen this year, which will offer researchers an opportunity to additionally present their accepted NeurIPS work in Europe, concurrently with NeurIPS. Read more in our blog