Refining generative process with discriminator guidance in score-based diffusion models

D Kim, Y Kim, SJ Kwon, W Kang, IC Moon - arxiv preprint arxiv …, 2022 - arxiv.org
The proposed method, Discriminator Guidance, aims to improve sample generation of pre-
trained diffusion models. The approach introduces a discriminator that gives explicit …

Score-based generative diffusion models for social recommendations

C Liu, J Zhang, S Wang, W Fan, Q Li - arxiv preprint arxiv:2412.15579, 2024 - arxiv.org
With the prevalence of social networks on online platforms, social recommendation has
become a vital technique for enhancing personalized recommendations. The effectiveness …

Closed-Loop Unsupervised Representation Disentanglement with -VAE Distillation and Diffusion Probabilistic Feedback

X **, B Li, B **e, W Zhang, J Liu, Z Li, T Yang… - … on Computer Vision, 2024 - Springer
Abstract Representation disentanglement may help AI fundamentally understand the real
world and thus benefit both discrimination and generation tasks. It currently has at least …

Label-noise robust diffusion models

B Na, Y Kim, HS Bae, JH Lee, SJ Kwon, W Kang… - arxiv preprint arxiv …, 2024 - arxiv.org
Conditional diffusion models have shown remarkable performance in various generative
tasks, but training them requires large-scale datasets that often contain noise in conditional …

Diffusion Bridge AutoEncoders for Unsupervised Representation Learning

Y Kim, K Lee, M Park, B Na, IC Moon - arxiv preprint arxiv:2405.17111, 2024 - arxiv.org
Diffusion-based representation learning has achieved substantial attention due to its
promising capabilities in latent representation and sample generation. Recent studies have …