Béz ierFlow parameterizes stochastic interpolant schedulers as Béz ier functions to learn optimal sampling trajectories, achieving 2-3x better few-step performance than prior timestep optimization methods.
Sinceρ(t) = α(t) σ(t) and ¯ρ(s) =¯α(s) ¯σ(s)are strictly increasing, the mapst7→ν=ρ(t) 2 ands7→ν= ¯ρ(s) 2 are bijections onto the common interval[ν min, νmax]
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
B\'ezierFlow: Learning B\'ezier Stochastic Interpolant Schedulers for Few-Step Generation
Béz ierFlow parameterizes stochastic interpolant schedulers as Béz ier functions to learn optimal sampling trajectories, achieving 2-3x better few-step performance than prior timestep optimization methods.