Combinatorial optimization (CO) problems are often NP-hard and thus out of reach for exact
algorithms, making them a tempting domain to apply machine learning methods. The highly …

Autoregressive large language models (LLMs) compress knowledge from their training data
through next-token conditional distributions. This limits tractable querying of this knowledge …

Latent variable models (LVMs) with discrete compositional latents are an important but
challenging setting due to a combinatorially large number of possible configurations of the …

Tackling the most pressing problems for humanity, such as the climate crisis and the threat
of global pandemics, requires accelerating the pace of scientific discovery. While science …

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 …

The recently proposed generative flow networks (GFlowNets) are a method of training a
policy to sample compositional discrete objects with probabilities proportional to a given …

We tackle the problem of sampling from intractable high-dimensional density functions, a
fundamental task that often appears in machine learning and statistics. We extend recent …

Abstract Generative Flow Networks (or GFlowNets for short) are a family of probabilistic
agents that learn to sample complex combinatorial structures through the lens of “inference …

Generative Flow Networks (GFlowNets) are amortized sampling methods that learn a
distribution over discrete objects proportional to their rewards. GFlowNets exhibit a …

We study the problem of training diffusion models to sample from a distribution with a given
unnormalized density or energy function. We benchmark several diffusion-structured …