ABOUT

I am a Departmental Lecturer (Assistant Professor) in Machine Learning at the Department of Computer Science and a Lecturer in Computer Science at Jesus College, University of Oxford, where I lead the Oxford AI for Science Lab.

I work on probabilistic machine learning, with particular focus on generative modeling, probabilistic programming, deep learning, and simulation-based inference.

Previously I was a postdoc with Frank Wood, working on probabilistic programming. Before Oxford, I was a postdoc with Barak Pearlmutter at the Brain and Computation Lab, National University of Ireland Maynooth, where I specialized in automatic differentiation in higher-order functional languages, and nesting of forward and reverse differentiation. I did my PhD at Universitat Autònoma de Barcelona, where my supervisor was Ramon Lopez de Mantaras at the Artificial Intelligence Research Institute (IIIA/CSIC), working on computational analogy, commonsense reasoning, and graph-based evolutionary algorithms. Before this, I received a MSc degree from Chalmers University of Technology, where I was working on artificial life and computational physics in the Complex Adaptive Systems program.

I am also a member of the Torr Vision Group (TVG) at the Department of Engineering Science and the Oxford Applied and Theoretical Machine Learning Group (OATML). I am a Research Member of the Common Room at Kellogg College, and a member of the European Lab for Learning and Intelligent Systems (ELLIS) Oxford Unit. Previously I was a research consultant for Microsoft Research Cambridge. I am involved in NASA and ESA Frontier Development Lab programs as faculty and member of the AI Technical Committee.

RESEARCH GROUP

• Oxford AI for Science Lab

NEWS

• Jan 2025. Co-organizing the Languages for Inference (LAFI) workshop at POPL 2025
• Dec 2024. Co-organizing the seventh Machine Learning and the Physical Sciences workshop at NeurIPS 2024
• May 2024. Our paper “Managing extreme AI risks amid rapid progress” is published in Science
• May 2024. Serving as Area Chair in the AISTATS 2024 conference
• Dec 2023. Co-organizing the sixth Machine Learning and the Physical Sciences workshop at NeurIPS 2023
• Oct 2023. Our work on managing AI risks is featured by the TIME Magazine and on the front page of The Guardian.
• Aug 2023. Appointed to the Royal Society’s International Exchanges Committee
• Jun 2023. Co-organizing the residential program on Differentiable and Probabilistic Programming for Fundamental Physics at the Munich Institute for Astro-, Particle and BioPhysics, Germany and co-organizing the topical workshop “The Road to Differentiable and Probabilistic Programming in Fundamental Physics” at the Max Planck Institute for Extraterrestrial Physics

More news

• Jun 2023. Serving on the Helmholtz Association evaluation panel for Data Science in Hamburg - Helmholtz Graduate School for the Structure of Matter DASHH, Hamburg, Germany
• Mar 2023. Serving as Area Chair in the AISTATS 2023 conference
• Dec 2022. Co-organizing the fifth Machine Learning and the Physical Sciences workshop at NeurIPS 2022
• Aug 2022. Our paper "Exploring the Limits of Synthetic Creation of Solar EUV Images via Image-to-Image Translation" is accepted to the Astrophysical Journal
• Jun 2022. Invited talk at Collège de France, Paris, France
• Feb 2022. Invited talk at the NSF AI Planning Institute for Data Discovery in Physics, Carnegie Mellon University, Pittsburgh, PA, US
• Jan 2022. Papers accepted at AISTATS and ICLR
• Dec 2021. Invited talk at the Bayesian Deep Learning workshop, co-organizing the fourth Machine Learning and the Physical Sciences workshop, and we have our paper "Domain Invariant Representation Learning with Domain Density Transformations" accepted at the Conference on Neural Information Processing Systems (NeurIPS) 2021
• Jun 2021. A machine learning model I worked on is launched to space from Cape Canaveral on a SpaceX Falcon 9 rocket! Official news at University of Oxford, Department of Engineering Science and Department of Computer Science
• Mar 2021. Two journal papers accepted: "Towards Global Flood Mapping Onboard Low Cost Satellites with Machine Learning" (Scientific Reports), on deploying ML onboard ESA satellites and "Multi-Channel Auto-Calibration for the Atmospheric Imaging Assembly Using Machine Learning" (Astronomy and Astrophysics), on using ML to calibrate NASA Solar Dynamics Observatory instruments
• Dec 2020. Co-organizing the third Machine Learning and the Physical Sciences workshop, and we have our paper "Black-Box Optimization with Local Generative Surrogates" accepted at the Conference on Neural Information Processing Systems (NeurIPS) 2020
• Oct 2020. Panel member on Probabilistic Programming in the Field: Complex Simulators at PROBPROG 2020, MIT, Cambridge, MA, US
• Oct 2020. I joined Oxford Applied and Theoretical Machine Learning Group (OATML)
• Sep 2020. Invited talk at Stanford Linear Accelerator, Menlo Park, CA, US
• Aug 2020. Organizing committee of Lockheed Martin Workshop on Machine Learning For Space Sciences, Committee on Space Research (COSPAR 2020) Scientific Assembly, Sydney, Australia (postponed to Jan 2021)
• Jul 2020. Invited talk at ML-HEP Summer Scool 2020, EPFL, Lausanne, Switzerland
• Jun 2020. Invited talk at the Nordic Probabilistic AI School, Trondheim, Norway (postponed to 2021)
• Jan 2020. Invited talk at the AI & Physics Track, Applied Machine Learning Days, EPFL, Lausanne, Switzerland
• Dec 2019. Our paper Efficient Probabilistic Inference in the Quest for Physics Beyond the Standard Model is accepted at the Conference on Neural Information Processing Systems (NeurIPS) 2019, Vancouver, Canada
• Dec 2019. Co-organizing two workshops, Machine Learning and the Physical Sciences and Program Transformations for Machine Learning at the Conference on Neural Information Processing Systems (NeurIPS) 2019, Vancouver, Canada
• Nov 2019. Our paper "etalumis" selected as Best Paper finalist at the Supercomputing Conference (SC19)
• Oct 2019. Invited talk at the Interpretable Learning in Physical Sciences workshop at the Institute for Pure & Applied Mathematics (IPAM), UCLA, Los Angeles, CA, US
• Aug 2019. Invited talk at the Hammers & Nails 2019: Machine Learning Meets Astro & Particle Physics workshop at Weizmann Institute of Science, Rehovot, Israel
• Jun 2019. I'm mentoring heliophysics challenges at NASA FDL, NASA Ames and SETI Institute; and Earth observation for disaster response challenge at ESA FDL, European Space Agency and University of Oxford
• Jun 2019. Selected as a top 5% reviewer for ICML 2019.
• May 2019. Papers accepted at the Astronomical Journal, ICML workshops on AI for Social Good and Automated Machine Learning
• Apr 2019. Invited talk at the Advanced Workshop on Accelerating the Search for Dark Matter with Machine Learning, International Centre for Theoretical Physics, Trieste, Italy
• Mar 2019. Invited keynote talk at the International Workshop on Advanced Computing and Analysis Techniques in Physics Research, Saas Fee, Switzerland
• Feb 2019. I joined Torr Vision Group
• Oct 2018. Serving on the program committee of the Languages for Inference workshop at POPL 2019, Lisbon, Portugal
• Sep 2018. Giving two lectures on automatic differentiation at the University of British Columbia, Vancouver, BC, Canada
• Jul 2018. I'm mentoring an astrobiology challenge at the NASA Frontier Development Lab at SETI Institute and NASA Ames, Mountain View, CA, US
• Jul 2018. Invited talk at NERSC, Lawrence Berkeley National Lab, Berkeley, CA, US
• Apr 2018. Our hypergradient descent paper is accepted to the International Conference on Learning Representations (ICLR) 2018, Vancouver, Canada
• Feb 2018. I joined the AI Technical Committee of the NASA Frontier Development Lab and FDL Europe with the European Space Agency
• Dec 2017. Co-organizing the Deep Learning for Physical Sciences workshop at the Conference on Neural Information Processing Systems (NIPS) 2017, Long Beach, CA, US
• Dec 2017. Invited talk at the Autodiff Workshop at the Conference on Neural Information Processing Systems (NIPS) 2017, Long Beach, CA, US
• Sep 2017. DARPA Data-Driven Discovery of Models (D3M) Meeting, Washington, DC, US
• Sep 2017. CSCS-ICS-DADSi Summer School: Accelerating Data Science with HPC, Swiss National Supercomputing Centre, Lugano, Switzerland
• Jul 2017. Hammers & Nails - Machine Learning & HEP workshop, Weizmann Institute of Science, Rehovot, Israel
• Jul 2017. NASA Frontier Development Lab 2017, SETI Institute & NASA Ames Research Center, Mountain View, CA, US
• Apr 2017. International Conference on Artificial Intelligence and Statistics (AISTATS), Fort Lauderdale, FL, US
• Jan 2017. DARPA Probabilistic Programming for Advancing Machine Learning (PPAML) PI Meeting, Washington, DC, US
• Dec 2016. Conference on Neural Information Processing Systems (NIPS), Barcelona, Spain
• Sep 2016. International Conference on Algorithmic Differentiation, Christ Church, Oxford, UK
• May 2016. F# Technology Creators Workshop, Microsoft Research Cambridge, Cambridge, UK
• Apr 2016. Functional Londoners Meetup, London, UK
• Apr 2016. I joined the group of Frank Wood in Oxford
• Feb 2016. Alan Turing Institute Probabilistic Programming Workshop, London, UK
• Sep 2015. Gaussian Process Summer School 2015, University of Sheffield, Sheffield, UK
• Aug 2015. Deep Learning Summer School 2015, Université de Montréal, Montreal, Canada
• Jul 2015. ICML Workshop on Machine Learning Open Source Software (MLOSS), Lille, France
• Jun 2015. MRI/fMRI Theory & Practical Course, Trinity College Institute of Neuroscience, Dublin, Ireland
• Jun 2014. ICML 2014 Workshop on Automatic Machine Learning, Beijing, China

CONNECTIONS

• I have an Erdős number of 3. :)
• My academic genealogy, based on the Mathematics Genealogy Project.