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

Confirmed Panelists

Organizers