publications

2023

  1. NeurIPS
    Joint Bayesian Inference of Graphical Structure and Parameters with a Single Generative Flow Network
    Conference on Neural Information Processing Systems, 2023
  2. ICML
    Synergies between Disentanglement and Sparsity: Generalization and Identifiability in Multi-Task Learning
    International Conference on Machine Learning, 2023
  3. ICML
    A Theory of Continuous Generative Flow Networks
    Salem LahlouTristan Deleu, Pablo Lemos, Dinghuai Zhang, Alexandra Volokhova, Alex Hernandez-Garcia, Lena Nehale Ezzine, Yoshua Bengio, and Nikolay Malkin
    International Conference on Machine Learning, 2023
  4. ICLR
    GFlowNets and variational inference
    International Conference on Learning Representations, 2023
  5. Journal
    GFlowNets for AI-Driven Scientific Discovery
    Moksh JainTristan Deleu, Jason Hartford, Cheng-Hao Liu, Alex Hernandez-Garcia, and Yoshua Bengio
    Digital Discovery, Royal Society of Chemistry, 2023
  6. AAAI Oral
    The Effect of Diversity in Meta-Learning
    Ramnath Kumar, Tristan Deleu, and Yoshua Bengio
    AAAI Conference on Artificial Intelligence, 2023

2022

  1. UAI
    Bayesian Structure Learning with Generative Flow Networks
    Uncertainty in Artificial Intelligence, 2022
  2. ICLR Spotlight
    Continuous-Time Meta-Learning with Forward Mode Differentiation
    International Conference on Learning Representations, 2022

2021

  1. JMLR
    GFlowNet Foundations
    Journal of Machine Learning Research, 2021
  2. ICLR Spotlight
    Predicting Infectiousness for Proactive Contact Tracing
    Yoshua BengioPrateek GuptaTegan MaharajNasim RahamanMartin WeissTristan DeleuEilif MullerMeng QuVictor Schmidt, Pierre-Luc St-Charles, and  others
    International Conference on Learning Representations, 2021

2020

  1. ICLR
    A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms
    International Conference on Learning Representations, 2020
  2. ICLR
    Gradient-Based Neural DAG Learning
    International Conference on Learning Representations, 2020

2019

  1. Preprint Best in Show
    Torchmeta: A Meta-Learning library for PyTorch
    arXiv preprint, 2019