Pith. sign in

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 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

Generative Unordered Flow for Set-Structured Data Generation

cs.LG · 2025-01-29 · conditional · novelty 4.0

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.

citing papers explorer

Showing 1 of 1 citing paper.

  • Generative Unordered Flow for Set-Structured Data Generation cs.LG · 2025-01-29 · conditional · none · ref 6

    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.