Diffusion models have emerged as effective distribution estimators in vision, language, and
reinforcement learning, but their use as priors in downstream tasks poses an intractable …

Monte Carlo methods, Variational Inference, and their combinations play a pivotal role in
sampling from intractable probability distributions. However, current studies lack a unified …

Generative modeling of discrete data underlies important applications spanning text-based
agents like ChatGPT to the design of the very building blocks of life in protein sequences …

An effective approach for sampling from unnormalized densities is based on the idea of
gradually transporting samples from an easy prior to the complicated target distribution. Two …

We study the problem of training neural stochastic differential equations, or diffusion models,
to sample from a Boltzmann distribution without access to target samples. Existing methods …

Divergent thinking, the cognitive process of generating diverse solutions, is a hallmark of
human creativity and problem-solving. For machines, sampling diverse solution trajectories …

This paper studies Generative Flow Networks (GFlowNets), which learn to sample objects
proportionally to a given reward function through the trajectory of state transitions. In this …

Is there a way to design powerful AI systems based on machine learning methods that would
satisfy probabilistic safety guarantees? With the long-term goal of obtaining a probabilistic …

Amortized inference is the task of training a parametric model, such as a neural network, to
approximate a distribution with a given unnormalized density where exact sampling is …

Bayes' rule naturally allows for inference refinement in a streaming fashion, without the need
to recompute posteriors from scratch whenever new data arrives. In principle, Bayesian …