Publications and Talks

Preprints

  1. Learning the Universe: Posterior Reliability of Neural Generative Models in High-Dimensional Field-Level Inference of Cosmic Initial Conditions
    L. Doeser, J. Jasche
    [https://arxiv.org/abs/2606.10023] (citations: 0)

  2. The Manticore Project II: Bayesian digital twins of cosmic structure across the SDSS and BOSS volumes
    S. McAlpine, J. Jasche, G. Lavaux, L. Doeser, A. Loureiro
    [https://arxiv.org/abs/2606.10020] (citations: 0)

Journal Articles

  1. Preparing for Rubin-LSST -- Detecting Brightest Cluster Galaxies with Machine Learning in the LSST DP0.2 simulation
    A. Chu, L. Doeser, S. Ding, J. Jasche
    [https://arxiv.org/abs/2503.15945] (citations: 0)

  2. Learning the Universe: Learning to Optimize Cosmic Initial Conditions with Non-Differentiable Structure Formation Models
    L. Doeser, M. Ata, J. Jasche
    [https://www.arxiv.org/abs/2502.13243] (citations: 8)

  3. Learning the Universe: 3 Gpc/h Tests of a Field Level N-body Simulation Emulator
    M.T. Scoggins, M. Ho, F. Villaescusa-Navarro, D. Jamieson, L. Doeser, G.L. Bryan
    [https://arxiv.org/abs/2409.02154] (citations: 1)

  4. COmoving Computer Acceleration (COCA): N-body simulations in an emulated frame of reference
    D. Bartlett, M. Chiarenza, L. Doeser, F. Leclercq
    [https://arxiv.org/abs/2409.02154] (citations: 10)

  5. Bayesian Inference of Initial Conditions from Non-Linear Cosmic Structures using Field-Level Emulators
    L. Doeser, D. Jamieson, S. Stopyra, G. Lavaux, F. Leclercq, J. Jasche
    [https://arxiv.org/abs/2312.09271] (citations: 34)

Conference Proceedings

  1. Invariant Sets for Integrators and Quadrotor Obstacle Avoidance
    L. Doeser, P. Nilsson, A. D. Ames, R. M. Murray
    Proceedings of the American Control Conference 2020, Denver, 1-3 July 2020. Publisher: IEEE [https://ieeexplore.ieee.org/abstract/document/9147872] (citations: 14)

Talks

  1. Multimodal Cosmology with a Hierarchical Spherical Transformer
    Symposium: CCA Pre-Doc, Flatiron Institute, New York, USA. May, 2026
  2. Towards Next-Generation Cosmic Digital Twins using Physics-Informed Priors and/or Neural Search Enginges
    Seminar: Cosmo Coffee: Department of Physics @ Massachusetts Institute of Technology (MIT), Massachusetts, USA. April, 2026
  3. Towards Next-Generation Cosmic Digital Twins with Deep Learning
    Seminar: Astro AI Lunch: Center for Astrophysics | Harvard & Smithsonian, Massachusetts, USA. April, 2026
  4. Learning to Optimize Cosmic Initial Conditions with Non-Differentiable Structure Formation Models
    Seminar: AI Lunch Discussion: The NSF AI Institute for Artificial Intelligence & Fundamental Interactions, Massachusetts, USA. April, 2026
  5. Neural Optimizers vs Neural Emulators at the Field-Level
    Seminar: Astronomy Department Pizza Lunch: Columbia University, New York, USA. April, 2026
  6. Learning to Optimize Cosmic Initial Conditions with Non-Differentiable Structure Formation Models
    Seminar: Astro-ML, Columbia University, New York, USA. April, 2026
  7. Cosmic Digital Twins of the Large-Scale Structure of Galaxies
    Group Meeting: Columbia University, New York, USA. April, 2026
  8. Field-level Inference of Initial Conditions with Stochastic Interpolants and Flows
    Collaboration Meeting: Simons Collaboration on Learning the Universe Spring Meeting, John Hopkins University, Baltimore, USA. March, 2026
  9. Field-level Inference of Cosmic Initial Conditions, and Digital Twins
    AstroxML Meeting, Computational Center for Astrophysics (CCA), Flatiron Institute, New York, USA. March, 2026
  10. Field-level reconstruction of LSS and cross-correlations with CMB
    Conference: New Synergies in Multi-Probe Cosmology, KITP, Santa Barbara, Califoria, USA. February, 2026
  11. Learning the Universe by Learning to Optimize Cosmic Initial Conditions with Non-Differentiable Simulators
    Conference: AI for Science Symposium, Royal Swedish Academy of Sciences, Stockholm, Sweden. Sep, 2025
  12. The Light Revealing our Universe
    Workshop: Tom Tits Experiment Science Center, Stockholm, Sweden. Aug, 2025
  13. Learning to Optimize Cosmic Initial Conditions with Non-Differentiable Structure Formation Models
    Conference: European Coalition for AI in Fundamental Physics, Sardinia, Italy. June, 2025
  14. Accelerating Cosmological Field-level Inference with Deep Learning
    Seminar: Statistics and Machine Learning, Princeton University, USA. March, 2025
  15. Accelerating Cosmological Simulations and Statistical Inference with Machine Learning
    OKC x Industry, Savantic AB HQ, Stockholm, Sweden. February, 2025
  16. Bayesian Inference of Initial Conditions from Non-Linear Cosmic Structures using Field-Level Emulators
    Working Group Meeting: Oskar Klein Centre, Cosmology and Gravity WG, Stockholm, Sweden. October, 2024
  17. Bayesian Inference of Initial Conditions from Non-Linear Cosmic Structures using Field-Level Emulators
    Conference: New Strategies for Extracting Information from Galaxy Surveys II, Sexten/Sesto, Italy. July, 2024
  18. Towards Robust Bayesian inference (ROBIN) using Physics-Informed Priors from Cosmological Simulations
    Conference: COSMO 2021 (Statistical Challenges for 21st Century Cosmology), Chania, Crete, Greece. May, 2024
  19. Bayesian Inference of Initial Conditions from Non-Linear Cosmic Structures using Field-Level Emulators
    Virtual Seminar: USM Galaxies and Lensing Seminar, Munich, Germany. May, 2024
  20. Bayesian Inference of Initial Conditions from Non-Linear Cosmic Structures using Field-Level Emulators
    Virtual Seminar: Astrophysics Group, Imperial College London, UK. January, 2024
  21. Bayesian Inference of Initial Conditions from Non-Linear Cosmic Structures using Field-Level Emulators
    Conference: Debating the Potential of Machine Learning in Astronomical Surveys #2, ML-IAP/CCA 2023, Paris, France. November, 2023
  22. Field-level Emulator in BORG
    Collaboration Meeting: Simons Foundation, Learning the Universe, New York, USA. September, 2023
  23. Machine Learning the Initial Conditions of the Universe within BORG
    Cosmology Lunch Talk: Oskar Klein Centre, Stockholm University, Sweden. May, 2023

Theses

  1. A Machine Learning Approach for Comprehending Cosmic Expansion
    L. Doeser
    Master Thesis in Engineering Physics (track: Theoretical Physics), KTH Royal Institute of Technology
    [https://kth.diva-portal.org/]

  2. Coupling of Light Into a Silicon-on-Silica Strip Waveguide
    L. Doeser, E. Rydving
    Bachelor Thesis in Engineering Physics, KTH Royal Institute of Technology
    [https://kth.diva-portal.org/]