We’re excited to welcome Petar Veličković to the OxML speaker lineup. Petar is a Senior Staff Research Scientist at Google DeepMind, and a Lecturer at University of Cambridge. His research focuses on neural algorithmic reasoning, graph representation learning, and geometric deep learning, with the goal of improving out-of-distribution generalisation in AI systems. He is widely known as the first author of Graph Attention Networks (GAT) and Deep Graph Infomax, with research that has impacted areas ranging from Google Maps travel-time prediction to mathematical discovery, football tactics, and competitive programming. Join us to hear insights from one of the leading researchers shaping the future of graph and geometric deep learning. Register Now: oxfordml.school #OxML #GraphAttentionNetworks #GraphRepresentationLearning #RepLearning #GeometricDeepLearning @PetarV_93 @GoogleDeepMind @Cambridge_Uni

What does the OxML experience look like? A week of learning, building, and connecting with some of the brightest minds in AI. From cutting-edge lectures and hands-on sessions to poster presentations, networking, and conversations that continue long after the programme ends — OxML brings together a truly global community passionate about machine learning, generative AI, health, and intelligent systems. Whether you are a researcher, engineer, founder, clinician, or student, OxML is designed to help you deepen your knowledge, explore real-world applications, and meet collaborators from around the world. Join us this July at the University of Oxford and be part of the next generation of AI innovation. Register now — spots are limited. oxfordml.school. #OxML #AICommunity #MLHealth #RepLearning #GenerativeAI #AI

📣 MLx Representation Learning & Generative AI lecture update: 📍On Causal Discovery and the Extrapolation of Causal Effects by Prof Ricardo Silva from UCL 🗓 15–18 July | Mathematical Institute, Oxford 🌐 oxfordml.school Revisit how causal effect learning predicts how the world responds to an agent’s actions using off-policy data, while causal discovery seeks to uncover the underlying structure that makes such extrapolation possible. The lecture also explores how outcomes from past actions across different environments can be used to calibrate causal discovery, making these predictions more reliable. Registrations are now open! #OxML2026 #CausalEffects #RepLearning #AIAgent

Join us TODAY (Aug 1st 2024) for this week's robot learning seminar, in which Léopold Maytié from @UT3PaulSabatier will present his talk titled "First Steps of a Global Workspace Model in the RL and Robotics world". See you there! YouTube.com/@MontrealRobotic… #rl #replearning

replearning

"He's my supporting elm and I his vine"- Britten, Canticle I 'My Beloved is Mine', op. 40 #replearning

This has been my summer so far. Well worth it though #replearning :)