Check out our paper with Vincent, AMBOSS ⚡, and Vikash Singh, where we use Machine Learning to predict edge balances in the Lightning Network, a layer 2 solution to enhance Bitcoin payment scalability and reliability ⚡ arxiv.org/abs/2405.12087

🎉📢 VantAI will be at #icml2024! We'll be co-hosting the AI x Bio/Chem social of the week together with our friends from Microsoft Research AI4Science and Relation. Come join us in Vienna after the ML4LMS workshop on 📆 Friday July 26th 📆 for an evening of fun, networking, great

Heading to ICML next week and looking for recommendations on interesting papers in ML x Bio, Diffusion Models, and GNNs to look for during the poster sessions. Any tips?

"Do we really need to drop items with missing modalities in #multimodal #recsys?" Not at all! Our short paper at #CIKM2024 ACM CIKM 2024 proposes untrained #graph propagation to impute missing modalities as a **preprocessing** stage 🚀 w/ Emanuele Rossi Claudio Pomo Fragkiskos Malliaros Tommaso Di Noia

The lack of large, high-quality datasets and robust evaluation is holding back ML in Drug Discovery. Today, we are excited to release Pinder (Protein-Protein) and Plinder (Protein-Ligand) to help bridge this gap and drive meaningful progress 🧬

 --> 🧬

Pre-print and code of our #CIKM2024 ACM CIKM 2024 paper "Do We Really Need to Drop Items with Missing Modalities in Multimodal Recommendation?" (w/ Emanuele Rossi Claudio Pomo Tommaso Di Noia Fragkiskos Malliaros) are now available! * Pre-print: arxiv.org/abs/2408.11767 * Code: github.com/sisinflab/Grap…

If next week you'll be in Barcelona for KDD and would like to chat about MLxBio, Generative Models or GNNs, please reach out 🧬 I won't be at the conference but live at walking distance!

Andrej Karpathy We're solely focused on scaling payments to enable a frictionless economy in a decentralized way, just like the internet itself. In our search, we found that the Lightning Network on Bitcoin is the only tech that enables this today by using payment channels. We're working on

#AITHYRA is born! 🎉 OeAW is founding a new institute at the intersection of #AI & #biomedicine – the AITHYRA Institute. Meet the new founding director and DeepMind Professor of Artificial Intelligence Michael Bronstein. Watch now ➡️youtu.be/pTA6DPQpxfo #boehringeringelheimstiftung

Excited to announce Boltz-1: the first fully open-source AlphaFold3-level model!

🚀 Don't miss this week's talk with Jeremy Wohlwend and Gabriele Corso where they will talk about their new model Boltz-1. 🗓️Friday - 4pm CET / 10am ET

I'm very late to the party, but you can now follow me on the 🦋 app at bsky.app/profile/emaros… ✨

We are excited to announce the first alpha release of 💥 peppr - package for evaluation of predicted poses 💥 an open source framework for structural model evaluation Find out more at peppr.vant.ai built on Biotite, peppr dramatically simplifies evaluation

Excited to unveil Boltz-2, our new model capable not only of predicting structures but also binding affinities! Boltz-2 is the first AI model to approach the performance of FEP simulations while being more than 1000x faster! All open-sourced under MIT license! A thread… 🤗🚀