Branching Flows extends flow matching to variable-sized states by letting elements branch and delete stochastically on binary trees while composing with discrete, continuous, manifold, or multimodal base processes.
Trans-dimensional generative modeling via jump diffusion models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2025 2verdicts
UNVERDICTED 2representative citing papers
GraphBSI uses Bayesian Sample Inference as noise-controlled SDEs to generate discrete graphs in one shot, achieving state-of-the-art results on molecular benchmarks Moses and GuacaMol.
citing papers explorer
-
Branching Flows: Discrete, Continuous, and Manifold Flow Matching with Splits and Deletions
Branching Flows extends flow matching to variable-sized states by letting elements branch and delete stochastically on binary trees while composing with discrete, continuous, manifold, or multimodal base processes.
-
Discrete Bayesian Sample Inference for Graph Generation
GraphBSI uses Bayesian Sample Inference as noise-controlled SDEs to generate discrete graphs in one shot, achieving state-of-the-art results on molecular benchmarks Moses and GuacaMol.