Alejandro Dobles

Excited to share Pearl from Genesis Molecular AI (yes, we've updated our name!): the first co-folding model to clearly surpass AlphaFold 3 on protein-ligand structure prediction. Unlike LLMs that train on vast public data, drug discovery AI faces fundamental data scarcity. Our 3D foundation model – #pearlAI – solves this with physics-based synthetic data generation and an innovative, controllable, architecture that leverages equivariant neural networks and an improved ability to leverage 3D templates as structural priors for in-context learning. Pearl is already deployed on live programs. Grateful to our incredible team and @NVIDIA for this collaboration. Read more: genesis.ml/news/introduci…

💠 Stanford Graph Learning Workshop 2024! Join leaders from academia and industry to explore the latest in Machine Learning and AI. Topics include Relational domains, Foundation Models, Agents and more. Save the date: Tuesday, Nov 5, 2024, 09:00 - 18:00 PT. The event will be held at Stanford University and live-streamed online. Register and/or submit a talk/poster: snap.stanford.edu/graphlearning-…

Excited to share that RelBench: Relational Deep Learning Benchmark paper was accepted to NeurIPS. Summarizing the study in one picture 📷 relbench.stanford.edu

🚀 Announcing RelBench: an open benchmark for deep learning on relational databases! RelBench is the foundational infrastructure for research in Relational Deep Learning (RDL), which brings modern AI to structured data. RelBench has databases, tasks, loaders, evaluators, and leaderboards to catalyze research in the field! Key features: 🌍 7 datasets spanning diverse domains: e-commerce, social, medical, and sports. 🧩 30 carefully curated predictive tasks: including entity classification/regression and recommendation. 📊 Wide data size range: ranging from 74K to 41M rows, 15 to 140 columns, 3 to 15 tables. ⏳ Wide time spans: from 2 weeks to 55 years of training data. 🏅 Comprehensive benchmarks: SOTA tabular learning and GNN baselines for every task. 🔥We hired a data scientist with 5 years of industry experience to solve RelBench tasks using traditional machine learning (feature engineering, model training). The RDL outperforms the data scientist in accuracy while reducing the time/code by 20x (12.3 hors -> 0.5 hours) !!! 🤯 Learn more: 🌐 Website: relbench.stanford.edu 📄 Paper: arxiv.org/abs/2407.20060 💻GitHub: github.com/snap-stanford/… Follow @RelBench for the latest updates Shoutout to the amazing team: @Josh_d_robinson @_rishabhranjan_ @weihua916 @KexinHuang5 @jiaqihan99 @adobles96 @rusty1s @janericlenssen @yiwenyuan98 @zechengzh @xhe1997 @Kumo_ai_team @PyG_Team @StanfordAILab