Optimizer states are a major source of memory consumption for training n...
Quantizing the activation, weight, and gradient to 4-bit is promising to...
The training process of generative adversarial networks (GANs) is unstab...
Large pre-trained language models (PLMs) have demonstrated strong perfor...
Diffusion models have exhibited excellent performance in various domains...
Guided sampling is a vital approach for applying diffusion models in
rea...
Diffusion probabilistic models (DPMs) have achieved impressive success i...
Training large neural network (NN) models requires extensive memory
reso...
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 emerging powerful generative
m...
Deep Ensemble (DE) is an effective alternative to Bayesian neural networ...
The increasing size of neural network models has been critical for
impro...
Normalizing flows define a probability distribution by an explicit inver...
Binary Neural Networks (BNNs) have received significant attention due to...
Fully quantized training (FQT), which uses low-bitwidth hardware by
quan...
Bird's-eye-view (BEV) is a powerful and widely adopted representation fo...
Generative flows are promising tractable models for density modeling tha...
Probabilistic topic models are popular unsupervised learning methods,
in...
Graph convolutional networks (GCNs) are powerful deep neural networks fo...
In this paper we introduce ZhuSuan, a python probabilistic programming
l...
Nested Chinese Restaurant Process (nCRP) topic models are powerful
nonpa...
Latent Dirichlet Allocation (LDA) is a popular tool for analyzing discre...
Dynamic topic models (DTMs) are very effective in discovering topics and...
Streaming variational Bayes (SVB) is successful in learning LDA models i...
Developing efficient and scalable algorithms for Latent Dirichlet Alloca...
Explosive growth in data and availability of cheap computing resources h...