Lazar Atanackovic

I am a Ph.D. Candidate at the University of Toronto in The Department of Electrical & Computer Engineering and the Vector Institute.

laz_pic.jpg

I am a member of the Probabilistic and Statistical Inference Group supervised by Brendan Frey and co-supervised by Bo Wang. Previously, I was a research intern at Recursion Pharmaceuticals / Valence Labs, Deep Genomics, and Mila - Quebec AI Institute.

My research focuses on developing machine learning methods for deciphering and modelling complex dynamical systems from data, with a particular focus on computational biology and biological systems. My interests include generative modelling (flows and diffusion), dynamical systems, causality, single-cell biology, and proteins.

Feel free to contact me for collaborations or if you have any questions about my work!


News

Dec 07, 2024 I will be attending NeurIPS this year in Vancouver! :smile: Reach out if you want to meet and chat!

Selected Publications

  1. 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), 2025
  2. 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
  3. gflownet_gen_preview.png
    Investigating Generalization Behaviours of Generative Flow Networks
    Lazar Atanackovic, and Emmanuel Bengio
    ICML Workshop on Structured Probabilistic Inference & Generative Modeling [Oral], 2024
  4. 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
  5. 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
  6. 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

Talks


Repositories