Supervised Guidance Training enables conditioning of infinite-dimensional diffusion models via an extended Doob h-transform so that fine-tuned models accurately sample from posteriors in function space.
We use a time-modulated FNO with 4 layers, 16 modes and 64 hidden channels, which results in 1 140 161 trainable parameters
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Supervised Guidance Training for Infinite-Dimensional Diffusion Models
Supervised Guidance Training enables conditioning of infinite-dimensional diffusion models via an extended Doob h-transform so that fine-tuned models accurately sample from posteriors in function space.