Look at our paper on generalizable perturbation modeling via Optimal Transport, now featured on the cover of #NatureMachineIntelligence!

Faculté de biologie et de médecine@fbm-unil.bsky.social · 3mo ago

A new #AI method for predicting how #cells will #respond to #treatments 💡 What if we could #predict how cells would react to a new drug even before testing it in the laboratory? A radically different and promising approach now on the cover of @natmachintell.nature.com 👉 www.unil.ch/news/en/1782...

🚀 #NatureMachineIntelligence 🚀 Conditional Monge Gap: a lightweight method for generalizable Optimal Transport across perturbations. Works well on unseen drugs, doses & time points. <1M params! Paper: ibm.biz/conditional-monge-gap Code: ibm.biz/conditional-monge-gap-code @marianna-raps.bsky.social

Conditional Monge Gap enables generalizable single-cell perturbation modelling - Nature Machine Intelligence

Driessen et al. present a conditional optimal transport method that can model the distribution shift between perturbed and unperturbed cell transcriptomes and that can generalize to unseen contexts.

ibm.biz

@jannisblrn.bsky.social wrote a very nice teaser about our Neurips paper Quantum Doubly Stochastic Transformers (spotlight). Our co-authors Filip and Kahn will present it in San Diego, and Jannis in EurIPS. You can find links to the paper, video, and poster below: www.linkedin.com/posts/jannis...

#transformers #neurips #eurips #ibmresearch | Jannis Born

𝗡𝗲𝘂𝗿𝗜𝗣𝗦 𝘀𝗽𝗼𝘁𝗹𝗶𝗴𝗵𝘁 for our work on "𝗤𝘂𝗮𝗻𝘁𝘂𝗺 𝗗𝗼𝘂𝗯𝗹𝘆 𝗦𝘁𝗼𝗰𝗵𝗮𝘀𝘁𝗶𝗰 𝗧𝗿𝗮𝗻𝘀𝗳𝗼𝗿𝗺𝗲𝗿𝘀" 🔦 𝘊𝘢𝘯 𝘱𝘳𝘪𝘯𝘤𝘪𝘱𝘭𝘦𝘴 𝘧𝘳𝘰𝘮 𝘲𝘶𝘢𝘯𝘵𝘶𝘮 𝘤𝘰𝘮𝘱𝘶𝘵𝘪𝘯𝘨 𝘣𝘦 𝘣𝘭𝘦𝘯𝘥𝘦𝘥 𝘪𝘯𝘵𝘰 𝘵𝘩𝘦 𝘮𝘰𝘴𝘵 𝘱𝘰𝘸𝘦𝘳𝘧𝘶𝘭 𝘔𝘓 𝘮𝘰𝘥𝘦𝘭𝘴? 🤔 𝗧𝗵𝗲 𝗽𝗿𝗼𝗯𝗹𝗲𝗺 𝗶𝗻 #𝗧𝗿𝗮𝗻𝘀𝗳𝗼𝗿𝗺𝗲𝗿𝘀: Transf...

linkedin.com

🤓 Open position at IBM Research Zurich! Passionate about AI for maths & curious about Quantum Computing? Join our team & help to shape the future of computing! We are offering internships & master theses. If you are looking for a PhD, please apply to the same ad! 👉 www.zurich.ibm.com/careers/2025...

After several years of usage by the open-source community, our paperscraper package finally has its own Docs available: jannisborn.github.io/paperscraper/ Use #paperscraper for publication keyword search, download PDFs, extract citation statistics and many more! 🚀

Check out our workflow for AI-driven molecular design. We’ve successfully validated this experimentally already (papers coming soon)!

Fragment-Screen@fragment-screen.bsky.social · last yr.

Fragment-Screen partner #IBMResearch has developed an open-source workflow for AI-informed molecular design! Find out more about the workflow here and how it will help facilitate fragment-based drug discovery (FBDD) fragmentscreen.org/open-source-... @eu-openscreen.bsky.social

1/ New paper out in @commsbio.nature.com, led by @marinv.bsky.social: doi.org/10.1038/s420...! Across several past studies, we showed how newborns' degraded vision may benefit human development and inspire more robust deep networks. We have referred to this as Adaptive Initial Degradations (AID).

Potential role of developmental experience in the emergence of the parvo-magno distinction - Communications Biology

Developmentally-driven computational modeling study suggests that early sensory experience shapes distinct neuronal response properties in the visual system, providing a potential account of the emerg...

doi.org

#ICML Why are LLMs so powerful but still suck at math? 🤔 A key problem is cross-entropy loss: It is nominal-scale, so tokens are unordered. That makes sense for words, but not for numbers. For a "5" label, predicting “6” or “9” gives the same loss 😱 Yes, it's crazy! No, nobody has fixed this yet! ⬇️

🚨 Our new paper: Conditional Optimal Transport generalizes well to unseen drugs. Big step forward, thanks to conditional Monge Gap! Even better: conditional models often beat local, non-conditional ones. arxiv.org/abs/2504.08328. Code public! Thanks to all co-authors @marianna-raps.bsky.social

Towards generalizable single-cell perturbation modeling via the Conditional Monge Gap

Learning the response of single-cells to various treatments offers great potential to enable targeted therapies. In this context, neural optimal transport (OT) has emerged as a principled methodologic...

arxiv.org

Our next journal club meeting will be discussing "A Computational Investigation of Inventive Spelling and the 'Lesen durch Schreiben' Method" by @jannisblrn.bsky.social et al. on 23 Jan 2025, 11am - 12pm (GMT+1). Join us by emailing us at gewonn.contact.us@gmail.com, and stay tuned for more news!

If you're @neuripsconf.bsky.social and into #OptimalTransport & bio, dont miss on Alice Driessen's spotlight talk on #ConditionalMongeGap for modeling CAR Response. Today #AIDrugX workshop! Positive results on OOD perturbations -> accurate gene expression prediction. Paper: ibm.biz/carot-pre

A new loss improves math capabilities in language models! The loss is model-agnostic and only requires to know which tokens represent numbers. No computational overhead but better performance. Poster today @NeurIPS - MathAI Workshop! Thx to collaborators from TUM AI! Paper: arxiv.org/abs/2411.02083

Can we iteratively design small molecules with desired target properties, simply by sending messages on Slack? YES! Super excited to give a live demo on🤖dZiner🧪 during the SPOTLIGHT 🔦 talk at #AI4Mat #NeurIPS2024! Preprint: lnkd.in/e-24AEHC Code: lnkd.in/egF4hGCg