🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Happy to announce that our preprint is out! What makes the effect of protein mutations difficult to predict? biorxiv.org/content/10.110…

I have 3 open postdoc positions in my group. Machine learning and AI to topics varying from inverse molecular design, optimization of near-term quantum computer algorithms to multi-scale simulations of electron transport. All project are exciting collabs. see thread for links:

Check out our new DNA LM benchmark paper on arXiv. Here is an excellent summary by shared first author Felix Teufel. We encourage you to check out the repository.

[1/7] 🎉Our paper Time-lagged Information Bottleneck (T-IB) is in #ICLR2024! Kudos to Bas Veeling Ryota Tomioka Patrick Forré & MSR AI4Science! 📄arxiv.org/abs/2309.07200 T-IB maps complex dynamics to simple latent spaces for super fast, highly accurate simulations!

We have now released the denoising diffusion model codebase! It includes: 🏋️ Pretrained models ✅ Easy sampling and evaluation 💻 Full model and training scripts Check out our repository here: github.com/microsoft/two-…

Are you fitting high-dimensional Gaussian Processes? Remember to include a good prior for your lengthscales. It's essential for guiding your optimization. Here's a blogpost about when and why GP regression fails to fit in high dimensions: miguelgondu.com/blogposts/2024…

📢Internship position Genmab 🏃One week left to apply! Come join our team if you're an NL-based Master's student eager to use ML for antibody design & discovery 💻🔬 #biotechinternships #proteinengineering #datasciencecareer #JoinGenmab #Utrecht linkedin.com/jobs/view/3873…

I am excited to share our #ACL2024 main paper, "What Languages are Easy to Language-Model? A Perspective from Learning Probabilistic Regular Languages". 📖 Link: arxiv.org/abs/2406.04289

New blogpost alert! miguelgondu.com/blogposts/2024… I've been trying to map the field of high-dimensional Bayesian optimization. Here's a brief introduction, and the blogposts that follow will dive deeper and provide code examples.

A Gaussian Process regression model built on top of protein language model embeddings and inverse folding models makes accurate predictions with calibrated uncertainties. Wouter Boomsma

Trying out Bluesky! 🦋 You can find me there under the same handle: bsky.app/profile/artsma…