JFDL allows pre-trained Consistency Models to perform guided image generation post-hoc by aligning flow distributions, reducing FID scores on CIFAR-10 and ImageNet without needing a teacher model.
Cifar-10 (canadian institute for advanced research)
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.LG 3verdicts
UNVERDICTED 3representative citing papers
Mono-Forward replaces Forward-Forward's contrastive goodness with local multi-class cross-entropy, outperforming vanilla FF and sometimes backpropagation while using 31% of its memory on MLP-Mixers for PathMNIST.
CollaFuse enables collaborative diffusion model training by splitting computation between resource-limited clients and a central server to reduce local burden and raw data sharing.
citing papers explorer
-
Post-Hoc Guidance for Consistency Models by Joint Flow Distribution Learning
JFDL allows pre-trained Consistency Models to perform guided image generation post-hoc by aligning flow distributions, reducing FID scores on CIFAR-10 and ImageNet without needing a teacher model.
-
Mono-Forward: Revisiting Forward-Forward through Objective-Locality Decomposition
Mono-Forward replaces Forward-Forward's contrastive goodness with local multi-class cross-entropy, outperforming vanilla FF and sometimes backpropagation while using 31% of its memory on MLP-Mixers for PathMNIST.
-
CollaFuse: Collaborative Diffusion Models
CollaFuse enables collaborative diffusion model training by splitting computation between resource-limited clients and a central server to reduce local burden and raw data sharing.