44 citations · 128 across the 26 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Simulation-free and finite-time diffusion model
Kentaro Kaba, Masayuki Ohzeki, Yuki Sughiyama
The performance of generative diffusion models is determined by the choice of the reference diffusion process connecting the empirical and prior distributions. Conventional approac…
cs.LG2024
Schödinger Bridge Type Diffusion Models as an Extension of Variational Autoencoders
Kentaro Kaba, Reo Shimizu, Masayuki Ohzeki +1
Generative diffusion models use time-forward and backward stochastic differential equations to connect the data and prior distributions. While conventional diffusion models (e.g.,…