Johann Brehmer 2014-2023
- NeurIPS (poster): Geometric Algebra Transformer
- NeurIPS (poster): EDGI: Equivariant Diffusion for Planning with Embodied Agents
- ELLIS Symposium on Large Language and Foundation Models (invited): In search of structure in the age of scale
- Guest lecture in Deep Learning 2, Universiteit van Amsterdam, Netherlands (invited): From causality to compression: AI Research at Qualcomm
- Climate informatics seminar, TU Berlin, Germany (invited): Causal representations and how to learn them
- Qualcomm Innovation Fellowship info session, online: Causal representations and how to learn them
- NeurIPS (poster): Weakly supervised causal representation learning (talk)
- Imperial College, London, UK (invited): Weakly supervised causal representation learning
- Computational Methods and Data Science Journal Club, Flatiron Institute, New York, USA: Weakly supervised causal representation learning
- Causality discussion group, online (invited): Weakly supervised causal representation learning
- RODEM Sinergia seminar, Switzerland (invited): Simulation-based inference: The likelihood is dead, long live the likelihood
- CMS machine learning journal club, CERN, Switzerland (invited): Simulation-based inference in particle physics and beyond
- AI Institute seminar, Carnegie Mellon University, USA (invited): Flows for simultaneous manifold learning and density estimation
- NeurIPS workshop on Machine Learning and the Physical Sciences (poster): Hierarchical clustering in particle physics through reinforcement learning
- NeurIPS (poster): Flows for simultaneous manifold learning and density estimation (talk)
- Theory seminar, JLab, USA (invited): How machine learning can help us get the most out of high-precision particle physics models
- Theory seminar, DESY Zeuthen and HU Berlin, Germany (invited): How machine learning can help us get the most out of high-precision particle physics models
- Job talk, Qualcomm AI Research, Amsterdam, Netherlands: How machine learning can help us get the most out of high-precision physics models
- Job talk, Bosch Center for AI, Renningen, Germany: How machine learning can help us get the most out of high-precision physics models
- ICML workshop on Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models (spotlight talk): NOTAGAN: Flows for the data manifold
- MLclub.net seminar (invited): Flows for simultaneous manifold learning and density estimation #notagan
- Physics x ML seminar, New York University, USA: NOTAGAN: Normalizing flows for simultaneous manifold learning and density estimation
- Dark Matter Working Group seminar, RIKEN, Japan: Mining for Dark Matter substructure: Learning from lenses without a likelihood
- Machine Learning for the LHC, Nagoya University, Japan (invited): The frontier of simulation-based inference
- Deep learning seminar, University of Bremen, Germany (invited): Normalizing flows and the likelihood ratio trick in particle physics
- NeurIPS workshop on Machine Learning and the Physical Sciences, Vancouver, Canada (poster): Mining gold: Improving simulation-based inference with latent information
- Seminar, INFN Padova, Italy (invited): Constraining effective field theories with machine learning
- Higgs and Effective Field Theory, Louvain-la-Neuve, Belgium (plenary, invited): Constraining effective field theories with machine learning
- Likelihood-free inference meeting, Flatiron institute, New York, USA: "Mining gold" from simulators to improve likelihood-free inference
- 19th International Workshop on Advanced Computing and Analysis Techniques in Physics Research, Saas-Fee, Switzerland (plenary, invited): Keynote: Constraining effective field theories with machine learning
- Dark universe seminar, Brandeis University, USA (invited): Bringing together simulations, physics insight, and machine learning to constrain new physics
- ITS/CHEP joint seminar, University of Oregon, USA (invited): Meticulous measurements with matrix elements and machine learning
- IAS Program on High Energy Physics, Hong Kong (plenary, invited): Constraining effective field theories with machine learning
- Moore-Sloan data science summit, Park City, USA: Mining gold from implicit models to improve likelihood-free inference
- IPPP seminar, Durham University, UK (invited): Learning to constrain new physics
- Pheno and vino seminar, University of Princeton, USA (invited): Learning to constrain new physics
- Elementary particle theory seminar, University of Maryland, USA (invited): Learning to constrain new physics
- Phenomeology seminar, Heidelberg University, Germany (invited): Learning to constrain new physics
- Theory seminar, Brookhaven National Laboratory, USA (invited): Constraining Effective Theories with Machine Learning
- Physics seminar, New York City College of Technology, USA (invited): Learning from the LHC, Effectively
- Phenomenology Symposium, Pittsburgh, USA: Better LHC Measurements Through Information Geometry
- Joint particle seminar, UC Irvine, USA (invited): Better Higgs Measurements Through Information Geometry
- Higgs Couplings, SLAC, USA: Higgs Physics with Information Geometry
- Phenomenology Symposium, Pittsburgh, USA: Pushing Higgs Effective Theory to its Limits
- Research unit meeting, Mainz, Germany: Pushing Higgs Effective Theory over the Edge
- Research unit meeting, Bonn, Germany: Symmetry Restored in Dibosons at the LHC?
- DESY Theory Workshop "Physics at the LHC and beyond", Hamburg, Germany: Symmetry Restored in Dibosons at the LHC?
- ATLAS Heidelberg retreat, Trifels, Germany: Polarized WW Scattering on the Higgs Pole