Rectified flow learns straight-path neural ODEs for distribution transport, yielding efficient generative models and domain transfers that work well even with a single simulation step.
Accelerating diffusion models via early stop of the diffusion process.arXiv preprint arXiv:2205.12524
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
Muninn accelerates diffusion trajectory planners up to 4.6x by spending an uncertainty budget to decide when to cache denoiser outputs, preserving performance and certifying bounded deviation from full computation.
The paper establishes an O(ε^{-4}) sample complexity bound for score estimation in diffusion models without requiring access to the empirical risk minimizer.
Latent Consistency Models enable high-fidelity text-to-image generation in 2-4 steps by directly predicting solutions to the probability flow ODE in latent space, distilled from pre-trained LDMs.
GLIDE combines multi-scale historical graphs with dual-stream encoding and prior-guided leap inference in a dual-branch diffusion denoiser to improve distribution fitting and next-event prediction in STPPs while lowering reverse-sampling cost.
Embedding Loss aligns feature distributions via MMD in random network embeddings to boost one-step diffusion distillation, reaching SOTA FID of 1.475 on CIFAR-10 unconditional generation.
citing papers explorer
-
Muninn: Your Trajectory Diffusion Model But Faster
Muninn accelerates diffusion trajectory planners up to 4.6x by spending an uncertainty budget to decide when to cache denoiser outputs, preserving performance and certifying bounded deviation from full computation.
-
GLIDE: Graph-guided Leap Inference for Diffusion Estimation of Spatio-Temporal Point Processes
GLIDE combines multi-scale historical graphs with dual-stream encoding and prior-guided leap inference in a dual-branch diffusion denoiser to improve distribution fitting and next-event prediction in STPPs while lowering reverse-sampling cost.
-
Efficient Diffusion Distillation via Embedding Loss
Embedding Loss aligns feature distributions via MMD in random network embeddings to boost one-step diffusion distillation, reaching SOTA FID of 1.475 on CIFAR-10 unconditional generation.