PID trains a single-step diffusion student by minimizing a PINN-style residual on the teacher's probability flow ODE, matching recent methods on CIFAR-10 without synthetic data.
Scientific machine learning through physics--informed neural networks: where we are and what’s next
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Physics Informed Distillation for Diffusion Models
PID trains a single-step diffusion student by minimizing a PINN-style residual on the teacher's probability flow ODE, matching recent methods on CIFAR-10 without synthetic data.