Publications

For the most up to date list of publications see my Google Scholar

2025

  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, Spotlight), 2025
    arXiv Code
  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
    arXiv Code
  3. 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

2024

  1. 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
  2. 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

2023

  1. 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

2022

  1. ICML
    Robustness to adversarial gradients: A glimpse into the loss landscape of contrastive pre-training
    Philip Fradkin* , Lazar Atanackovic*, and Michael R Zhang*
    ICML Workshop on Pre-training: Perspectives, Pitfalls, and Paths Forward, 2022
  2. MLCB
    Energy-based Modelling for Single-cell Data Annotation
    Tianyi Liu , Philip Fradkin , Lazar Atanackovic, and Leo J Lee
    Machine Learning in Computational Biology (MLCB), 2022
    HTML
  3. concerto.png
    A Graph Neural Network Approach for Molecule Carcinogenicity Prediction
    Philip Fradkin , Adamo Young , Lazar Atanackovic, Brendan Frey , Leo J Lee , and Bo Wang
    Bioinformatics, 2022
    HTML

2020

  1. IEEE OCEANS
    Deep-Learning Based Ship-Radiated Noise Suppression for Underwater Acoustic OFDM Systems
    Lazar Atanackovic, Lutz Lampe , and Roee Diamant
    Global OCEANS IEEE/MTS, 2020
    HTML
  2. IEEE OCEANS
    Stochastic ship-radiated noise modelling via generative adversarial networks
    Lazar Atanackovic, Vala Vakilian , Dryden Wiebe , Lutz Lampe , and Roee Diamant
    Global OCEANS IEEE/MTS, 2020
    HTML

2019

  1. IEEE OCEANS
    Statistical shipping noise characterization and mitigation for underwater acoustic communications
    Lazar Atanackovic, Ruoyu Zhang , Lutz Lampe , and Roee Diamant
    OCEANS IEEE/MTS, 2019
    HTML
  2. IEEE Access
    Cable diagnostics with power line modems for smart grid monitoring
    Yinjia Huo , Gautham Prasad , Lazar Atanackovic, Lutz Lampe , and Victor CM Leung
    IEEE Access, 2019
    HTML

2018

  1. ISPLC
    Grid surveillance and diagnostics using power line communications
    Yinjia Huo , Gautham Prasad , Lazar Atanackovic, Lutz Lampe , and Victor CM Leung
    IEEE International Symposium on Power Line Communications and its Applications (ISPLC), 2018
    HTML