The paper proposes to represent unordered point sets as Gaussian mixtures, learn flow matching over these function representations, and decode generated functions back to point sets via Langevin warm-up and gradient ascent.
Modeling temporal data as continuous functions with stochastic process diffusion
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Generative Unordered Flow for Set-Structured Data Generation
The paper proposes to represent unordered point sets as Gaussian mixtures, learn flow matching over these function representations, and decode generated functions back to point sets via Langevin warm-up and gradient ascent.