Antoine Dedieu

About me

I am a Senior Research Scientist at Google DeepMind. My current research is primarily focused on the AI for Science initiative—spanning domains such as chemistry and nuclear fusion— with the goal of enabling an AI-driven scientific revolution. Alongside this core focus, I have also contributed to several works on generative world models designed to help agents rapidly adapt to novel environments.

Prior to joining Google DeepMind, I spent 3.5 years at Vicarious (acquired by Alphabet), where I built an AI layer for robots. There, I designed an object detection pipeline used 1M+ times in production. My research focused on building novel generative probabilistic graphical models to solve challenging object-centric vision and navigation problems.

I hold a Master of Science from the MIT Operations Research Center, advised by Prof. Rahul Mazumder, and an MS in Applied Mathematics from Ecole Polytechnique. I am also a movie-fan, a sports addict, and a world-traveller. As an amateur photographer, I share my journeys on my website.

---

Conference articles

• AutoHarness: improving LLM agents by automatically synthesizing a code harness. [Preprint]
  Xinghua Lou, Miguel Lazaro-Gredilla, Antoine Dedieu, Carter Wendelken, Wolfgang Lehrach, Kevin P Murphy
• Code world models for general game playing. [Preprint]
  ICLR 2026. Wolfgang Lehrach, Daniel Hennes, Miguel Lazaro-Gredilla, Xinghua Lou, Carter Wendelken, Zun Li, Antoine Dedieu, Jordi Grau-Moya, Marc Lanctot, Atil Iscen, John Schultz, Marcus Chiam, Ian Gemp, Piotr Zielinski, Satinder Singh, Kevin P Murphy
• Improving Transformer World Models for Data-Efficient RL. [Preprint] [YouTube]
  Outstanding paper award at ICLR 2025 World Model Workshop
  ICML 2025. Antoine Dedieu*, Joseph Ortiz*, Xinghua Lou, Carter Wendelken, Wolfgang Lehrach, Swaroop Guntupalli, Miguel Lázaro-Gredilla, Kevin Murphy
• DMC-VB: A Benchmark for Representation Learning for Control with Visual Distractors. [Preprint] [Code]
  Neurips 2024. Antoine Dedieu*, Joseph Ortiz*, Wolfgang Lehrach, Swaroop Guntupalli, Carter Wendelken, Ahmad Humayun, Sivaramakrishnan Swaminathan, Guangyao Zhou, Miguel Lázaro-Gredilla, Kevin Murphy.
• Diffusion Model Predictive Control. [Preprint]
  TMLR 2025. Guangyao Zhou, Sivaramakrishnan Swaminathan, Rajkumar Vasudeva Raju, Swaroop Guntupalli, Wolfgang Lehrach, Joseph Ortiz, Antoine Dedieu, Miguel Lázaro-Gredilla, Kevin Murphy.
• Learning Cognitive Maps from Transformer Representations for Efficient Planning in Partially Observed Environments. [Preprint]
  ICML 2024. Antoine Dedieu, Wolfgang Lehrach, Guangyao Zhou, Dileep George, Miguel Lázaro-Gredilla.
• Schema-learning and rebinding as mechanisms of in-context learning and emergence. [Preprint]
  Neurips 2023, Spotlight. Sivaramakrishnan Swaminathan, Antoine Dedieu, Rajkumar Vasudeva Raju, Murray Shanahan, Miguel Lázaro-Gredilla, Dileep George.
• Learning noisy-OR Bayesian Networks with Max-Product Belief Propagation. [Preprint] [Code]
  ICML 2023. Antoine Dedieu, Guangyao Zhou, Dileep George, Miguel Lázaro-Gredilla.
• Graphical Models with Attention for Context-Specific Independence and an Application to Perceptual Grouping. [Preprint] [Code]
  Guangyao Zhou, Wolfgang Lehrach, Antoine Dedieu, Miguel Lázaro-Gredilla, Dileep George.
• Perturb-and-max-product: Sampling and learning in discrete energy-based models. [Preprint] [Code]
  Neurips 2021. Miguel Lázaro-Gredilla, Antoine Dedieu, Dileep George.
• Sample-Efficient L0-L2 Constrained Structure Learning of Sparse Ising Models. [Preprint] [Code]
  AAAI 2021. Antoine Dedieu, Miguel Lázaro-Gredilla, Dileep George.
• Query Training: Learning a Worse Model to Infer Better Marginals in Undirected Graphical Models with Hidden Variables. [Preprint] [Code]
  AAAI 2021. Miguel Lázaro-Gredilla, Wolfgang Lehrach, Nishad Gothoskar, Guangyao Zhou, Antoine Dedieu, Dileep George.
• Improved error rates for sparse (group) learning with Lipschitz loss functions. [Preprint]
  Antoine Dedieu.
• An error bound for Lasso and Group Lasso in high dimensions. [Preprint]
  Antoine Dedieu.
• Learning higher-order sequential structure with cloned HMMs. [Preprint]
  Antoine Dedieu, Nishad Gothoskar, Scott Swingle, Wolfgang Lehrach, Miguel Lázaro-Gredilla, Dileep George.
• Error bounds for sparse classifiers in high-dimensions. [Preprint]
  AiStats 2019. Antoine Dedieu.
• Hierarchical Modeling and Shrinkage for User Session Length Prediction in Media Streaming. [Preprint] [Code]
  CIKM 2018. Antoine Dedieu, Rahul Mazumder, Zhen Zhu, Hossein Vahabi.

Journal articles

• PGMax: Factor Graphs for Discrete Probabilistic Graphical Models and Loopy Belief Propagation in JAX. [Preprint] [Code]
  Journal of Machine Learning Research, 2025. Guangyao Zhou, Antoine Dedieu, Nishanth Kumar, Miguel Lázaro-Gredilla, Shrinu Kushagra, Dileep George.
• A detailed theory of thalamic and cortical microcircuits for predictive visual inference. [Preprint]
  Science Advances, 2025. Dileep George, Miguel Lázaro-Gredilla, Wolfgang Lehrach, Antoine Dedieu, Guangyao Zhou.
• Subset Selection with Shrinkage: Sparse Linear Modeling when the SNR is low. [Preprint] [Code]
  Operations Research, 2023. Rahul Mazumder, Peter Radchenko, Antoine Dedieu.
• Learning attention-controllable border-ownership for objectness inference and binding. [Preprint]
  Antoine Dedieu, Rajeev V. Rikhye, Miguel Lázaro-Gredilla, Dileep George.
• Solving L1-regularized SVMs and related linear programs: Revisiting the effectiveness of Column and Constraint Generation. [Preprint] [Code]
  Journal of Machine Learning Research, 2022. Antoine Dedieu, Rahul Mazumder, Haoyue Wang
• Learning Sparse Classifiers: Continuous and Mixed Integer Optimization Perspectives. [Preprint] [Code]
  Journal of Machine Learning Research, 2021. Antoine Dedieu, Hussein Hazimeh, Rahul Mazumder.
• Clone-structured graph representations enable flexible learning and vicarious evaluation of cognitive maps. [Preprint]
  Nature Communications, 2021. Dileep George, Rajeev Rikhye, Nishad Gothoskar, Swaroop Guntupalli, Antoine Dedieu, Miguel Lázaro-Gredilla.

Other software

• MEQ-JAX: Magnetic EQuilibrium Solver in JAX. [Code]
  David Pfau, Antoine Dedieu, Joel Jennings, Wolfgang Lehrach, Norman Casagrande, Matthias Lochbrunner, Tomek Nanowski, Craig Donner, Federico Felici.

Thesis

• Sparse learning: statistical and optimization perspectives.
  MIT Libraries. Antoine Dedieu.