% Key papers for Latent variable marginalization and estimators (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{cvpr2019_latent_14384,
  title = {{Latent Space Autoregression for Novelty Detection}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{iclr2018_learning_28476,
  title = {{Learning Latent Permutations with Gumbel-Sinkhorn Networks}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2018},
  url = {https://iclr.cc/virtual/2018/poster/183},
}

@inproceedings{aaai2018_mixed_102464,
  title = {{Mixed Sum-Product Networks: A Deep Architecture for Hybrid Domains}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11731},
}

@inproceedings{icml2019_mixture_37545,
  title = {{Mixture Models for Diverse Machine Translation: Tricks of the Trade}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/4319},
}

@inproceedings{icml2019_bit_37194,
  title = {{Bit-Swap: Recursive Bits-Back Coding for Lossless Compression with Hierarchical Latent Variables}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/4305},
}

@inproceedings{neurips2016_multi_55882,
  title = {{Multi-view Anomaly Detection via Robust Probabilistic Latent Variable Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2016},
  url = {https://nips.cc/virtual/2016/poster/7199},
}

@inproceedings{neurips2016_completely_55635,
  title = {{Completely random measures for modelling block-structured sparse networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2016},
  url = {https://nips.cc/virtual/2016/poster/8501},
}

@inproceedings{aaai2017_poisson_104467,
  title = {{Poisson Sum-Product Networks: A Deep Architecture for Tractable Multivariate Poisson Distributions}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2017},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10844},
}

@inproceedings{aaai2016_progressive_105024,
  title = {{Progressive EM for Latent Tree Models and Hierarchical Topic Detection}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2016},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10196},
}

@inproceedings{icml2018_end_36668,
  title = {{End-to-End Learning for the Deep Multivariate Probit Model}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/2259},
}

@inproceedings{neurips2020_sparse_60856,
  title = {{Sparse and Continuous Attention Mechanisms}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18180},
}

@inproceedings{aaai2021_group_692,
  title = {{Group Fairness by Probabilistic Modeling with Latent Fair Decisions}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/12051-group-fairness-by-probabilistic-modeling-with-latent-fair-decisions/},
}

@inproceedings{aaai2016_learning_105048,
  title = {{Learning Continuous-Time Bayesian Networks in Relational Domains: A Non-Parametric Approach}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2016},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10220},
}

@inproceedings{neurips2020_manifold_60286,
  title = {{Manifold GPLVMs for discovering non-Euclidean latent structure in neural data}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18499},
}

@inproceedings{neurips2016_mixed_55877,
  title = {{Mixed vine copulas as joint models of spike counts and local field potentials}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2016},
  url = {https://nips.cc/virtual/2016/poster/7315},
}

@inproceedings{icml2021_finite_39353,
  title = {{Finite mixture models do not reliably learn the number of components}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/10705},
}

@inproceedings{neurips2016_online_55910,
  title = {{Online Bayesian Moment Matching for Topic Modeling with Unknown Number of Topics}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2016},
  url = {https://nips.cc/virtual/2016/poster/7318},
}

@inproceedings{neurips2018_leveraging_57335,
  title = {{Leveraging the Exact Likelihood of Deep Latent Variable Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11384},
}

@inproceedings{neurips2020_efficient_59768,
  title = {{Efficient Marginalization of Discrete and Structured Latent Variables via Sparsity}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17794},
}

@inproceedings{icml2018_learning_36780,
  title = {{Learning Binary Latent Variable Models: A Tensor Eigenpair Approach}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/2053},
}

@inproceedings{aaai2025_gaussian_9303,
  title = {{Gaussian Graphical Modelling Without Independence Assumptions for Uncentered Data}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33689},
}

@inproceedings{aaai2025_learning_9737,
  title = {{Learning Local Neighborhoods of Non-Gaussian Graphical Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34059},
}

@inproceedings{icml2024_total_44043,
  title = {{Total Variation Floodgate for Variable Importance Inference in Classification}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34409},
}

@inproceedings{icml2024_conditionally_45831,
  title = {{Conditionally-Conjugate Gaussian Process Factor Analysis for Spike Count Data via Data Augmentation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/32621},
}

@inproceedings{icml2025_identifying_46674,
  title = {{Identifying Metric Structures of Deep Latent Variable Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45898},
}

@inproceedings{icml2025_learning_47531,
  title = {{Learning Monotonic Probabilities with a Generative Cost Model}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45065},
}

@inproceedings{icml2026_beyond_50479,
  title = {{Beyond Softmax: A Natural Parameterization for Categorical Random Variables}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=ClBpWdkPZd},
}

@inproceedings{neurips2024_scaling_71625,
  title = {{Scaling Continuous Latent Variable Models as Probabilistic Integral Circuits}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95649},
}

@inproceedings{neurips2024_transfer_71994,
  title = {{Transfer Learning for Latent Variable Network Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95319},
}

@inproceedings{neurips2025_learning_76660,
  title = {{Learning Latent Variable Models via Jarzynski-adjusted Langevin Algorithm}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=LpY1jgtk8I},
}

@inproceedings{neurips2025_a_77248,
  title = {{A Latent Multilayer Graphical Model For Complex, Interdependent Systems}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=Rtp3yLWAjI},
}

@inproceedings{neurips2025_multi_78611,
  title = {{Multi-View Oriented GPLVM: Expressiveness and Efficiency}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=gVtk4lzhcl},
}

@inproceedings{iclr2026_how_87856,
  title = {{How to Square Tensor Networks and Circuits Without Squaring Them}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=gHPRSPxIsk},
}

@inproceedings{iclr2024_map_34330,
  title = {{MAP IT to Visualize Representations}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18745},
}

@inproceedings{neurips2024_generic_70849,
  title = {{Generic Unsupervised Optimization for a Latent Variable Model With Exponential Family Observables}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/98325},
}

@inproceedings{iclr2026_graphon_84927,
  title = {{Graphon Cross-Validation: Assessing Models on Network Data}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=8J3GTeQmwl},
}