Exemplar-based sketch-to-photo synthesis allows users to generate
photo-...
The diffusion model has shown remarkable performance in modeling data
di...
Generative data augmentation, which scales datasets by obtaining fake la...
In this paper, we present ControlVideo, a novel method for text-driven v...
Large vision-language models (VLMs) such as GPT-4 have achieved unpreced...
Score distillation sampling (SDS) has shown great promise in text-to-3D
...
Macro-AUC is the arithmetic mean of the class-wise AUCs in multi-label
l...
Guided sampling is a vital approach for applying diffusion models in
rea...
Large-scale diffusion models like Stable Diffusion are powerful and find...
This paper proposes a unified diffusion framework (dubbed UniDiffuser) t...
We propose a three-stage training strategy called dual pseudo training (...
A large-scale deep model pre-trained on massive labeled or unlabeled dat...
Extensive empirical evidence demonstrates that conditional generative mo...
Diffusion probabilistic models (DPMs) have achieved impressive success i...
Inverse molecular design is critical in material science and drug discov...
Vision transformers (ViT) have shown promise in various vision tasks
inc...
Deep generative models (DGMs) are data-eager. Essentially, it is because...
Score-based diffusion generative models (SDGMs) have achieved the SOTA F...
By applying entropy codecs with learned data distributions, neural
compr...
Score-based generative models have excellent performance in terms of
gen...
Diffusion probabilistic models (DPMs) are a class of powerful deep gener...
Diffusion probabilistic models (DPMs) are emerging powerful generative
m...
Continual learning needs to overcome catastrophic forgetting of the past...
Diffusion probabilistic models (DPMs) represent a class of powerful
gene...
Recently, the (gradient-based) bilevel programming framework is widely u...
(Partial) ranking loss is a commonly used evaluation measure for multi-l...
We present Mixture of Contrastive Experts (MiCE), a unified probabilisti...
Normalizing flows define a probability distribution by an explicit inver...
Semi-supervised domain adaptation (SSDA), which aims to learn models in ...
Continual learning usually assumes the incoming data are fully labeled, ...
The learning and evaluation of energy-based latent variable models (EBLV...
Score matching (SM) provides a compelling approach to learn energy-based...
Generative adversarial networks (GANs) have shown promise in image gener...
Generative adversarial networks (GANs) have made significant progress on...
Deep generative models (DGMs) have shown promise in image generation.
Ho...
Markov random fields (MRFs) find applications in a variety of machine
le...
Implicit generative models are difficult to train as no explicit probabi...
We propose Graphical Generative Adversarial Networks (Graphical-GAN) to ...
Generative Adversarial Nets (GANs) have shown promise in image generatio...
Deep generative models (DGMs) are effective on learning multilayered
rep...
Deep convolutional neural networks (CNNs) have achieved breakthrough
per...
Memory units have been widely used to enrich the capabilities of deep
ne...
Deep generative models (DGMs) are effective on learning multilayered
rep...