The Atanackovic Lab

Welcome to the Atanackovic Lab at the University of Alberta! We are a research group focused on developing cutting-edge machine learning methods for understanding and modeling natural (physical) systems from data, with an emphasis on cellular and molecular systems.

Our research spans machine learning, generative modeling, causality, systems biology, single-cell biology, and protein & molecule design. We combine theoretical advances with practical applications to push the boundaries of what’s possible in computational biology and AI.

Interested in joining our lab? Explore our Research areas and learn how to Join Us for opportunities at the intersection of machine learning and biology.

Have questions or want to collaborate? Contact us.

Selected Publications

  1. m2m_tfm_v2.png
    Measure-to-measure Regression with Transformers
    Matthew Vandergrift , Martha White , Yury Polyanskiy , Philippe Rigollet , and Lazar Atanackovic
    2026
    arXiv
  2. boids_notebook_forecast.gif
    A Call to Lagrangian Action: Learning Population Mechanics from Temporal Snapshots
    Vincent Guan , Lazar Atanackovic, and Kirill Neklyudov
    International Conference on Machine Learning (ICML, Spotlight), 2026
    arXiv Code
  3. nm1_fig1.png
    Flow matching for generative modelling in bioinformatics and computational biology
    Alex Morehead* , Lazar Atanackovic*, Akshata Hegde* , Yanli Wang* , Frimpong Boadu* , Joel Selvaraj* , Alexander Tong , Aditi Krishnapriyan , and Jianlin Cheng
    Nature Machine Intelligence, 2026
    HTML Code
  4. curly.gif
    Curly Flow Matching for Learning Non-gradient Field Dynamics
    Katarina Petrović , Lazar Atanackovic, Viggo Moro , Kacper Kapusniak , Ismail Ilkan Ceylan , Michael M Bronstein , Joey Bose , and Alexander Tong
    Advances in Neural Information Processing Systems (NeurIPS), 2025
    arXiv Code
  5. structureflow.png
    Simulation-free Structure Learning for Stochastic Dynamics
    Noah El Rimawi-Fine* , Adam Stecklov* , Lucas Nelson , Mathieu Blanchette , Alexander Tong , Stephen Y Zhang , and Lazar Atanackovic
    arXiv preprint arXiv:2510.16656, 2025
    arXiv Code
  6. SD_examples.gif
    The Superposition of Diffusion Models Using the Itô Density Estimator
    Marta Skreta* , Lazar Atanackovic*, Avishek Joey Bose , Alexander Tong , and Kirill Neklyudov
    International Conference on Learning Representations (ICLR, Spotlight), 2025
    arXiv Code
  7. gif_mfm_letters_train_50.gif
    Meta Flow Matching: Integrating Vector Fields on the Wasserstein Manifold
    Lazar Atanackovic*, Xi Zhang* , Brandon Amos , Mathieu Blanchette , Leo J Lee , Yoshua Bengio , Alexander Tong , and Kirill Neklyudov
    International Conference on Learning Representations (ICLR), 2025
    arXiv Code
  8. gflownet_gen_preview.png
    Investigating Generalization Behaviours of Generative Flow Networks
    Lazar Atanackovic, and Emmanuel Bengio
    Transactions on Machine Learning Research (TMLR), 2025
    arXiv Code
  9. wlfs.png
    A Computational Framework for Solving Wasserstein Lagrangian Flows
    Kirill Neklyudov* , Rob Brekelmans* , Alexander Tong , Lazar Atanackovic, Qiang Liu , and Alireza Makhzani
    International Conference on Machine Learning (ICML), 2024
    arXiv Code
  10. sf2m.png
    Simulation-free Schrödinger Bridges via Score and Flow Matching
    Alexander Tong* , Nikolay Malkin* , Kilian Fatras* , Lazar Atanackovic, Yanlei Zhang , Guillaume Huguet , Guy Wolf , and Yoshua Bengio
    Artificial Intelligence and Statistics (AISTATS), 2024
    arXiv Code
  11. dyngfn.png
    DynGFN: Towards Bayesian Inference of Gene Regulatory Networks with GFlowNets
    Lazar Atanackovic*, Alexander Tong* , Bo Wang , Leo J Lee , Yoshua Bengio , and Jason Hartford
    Advances in Neural Information Processing Systems (NeurIPS), 2023
    arXiv Code

Software Packages