ICML 2024 Workshop on
Structured Probabilistic Inference & Generative Modeling

Join the SPIGM Slack!

Sign up for Reviewer!

The workshop focuses on theory, methodology, and application of structured probabilistic inference and generative modeling Probabilistic inference addresses the problem of amortization, sampling, and integration of complex quantities from graphical models, while generative modeling captures the underlying probability distributions of a dataset. Apart from applications in computer vision, natural language processing, and speech recognition, probabilistic inference and generative modeling approaches have also been widely used in natural science domains, including physics, chemistry, molecular biology, and medicine. Despite the promising results, probabilistic methods face challenges when applied to highly structured data, which are ubiquitous in real-world settings. We aim to bring experts from diverse backgrounds together, from both academia and industry, to discuss the applications and challenges of probabilistic methods, emphasizing challenges in encoding domain knowledge in these settings. We hope to provide a platform that fosters collaboration and discussion in the field of probabilistic methods. Topics include but are not limited to (see Call for Papers for more details):

  • Inference and generative methods for graphs, time series, text, video, and other structured modalities
  • Scaling and accelerating inference and generative models on structured data
  • Uncertainty quantification in AI systems
  • Applications in decision making, sampling, optimization, generative models, inference
  • Applications and practical implementations of existing methods to areas in science
  • Empirical analysis comparing different architectures for a given data modality and application

Confirmed Speakers

Yingzhen Li

Imperial College London

Molei Tao

Georgia Tech

Charlotte Bunne

Genentech & EPFL

Ben Poole

Google DeepMind

Ricky T. Q. Chen

FAIR, Meta

Maruan Al-Shedivat

Genesis Therapeutics

Confirmed Panelists

Kirill Neklyudov

University of Montreal & Mila

Rianne van den Berg

Microsoft Research

José Miguel Hernández-Lobato

University of Cambridge

Kyle Cranmer

University of Wisconsin-Madison


Dinghuai Zhang

University of Montreal & Mila

Yuanqi Du


Guan-Horng Liu

Georgia Tech

Kirill Neklyudov

University of Montreal & Mila

Chenlin Meng


Ruiqi Gao

Google Brain

Max Welling

University of Amsterdam

Yoshua Bengio

University of Montreal & Mila



Contact us at spigmworkshop2024@gmail.com.