145 citations · 271 across the 16 of their papers we have counts for
16 papers
EM Distillation for One-step Diffusion Models
Sirui Xie, Zhisheng Xiao, Diederik P Kingma +6
While diffusion models can learn complex distributions, sampling requires a computationally expensive iterative process. Existing distillation methods enable efficient sampling, bu…
UFOGen: You Forward Once Large Scale Text-to-Image Generation via Diffusion GANs
Yanwu Xu, Yang Zhao, Zhisheng Xiao +1
Text-to-image diffusion models have demonstrated remarkable capabilities in transforming textual prompts into coherent images, yet the computational cost of their inference remains…
DreamInpainter: Text-Guided Subject-Driven Image Inpainting with Diffusion Models
Shaoan Xie, Yang Zhao, Zhisheng Xiao +5
This study introduces Text-Guided Subject-Driven Image Inpainting, a novel task that combines text and exemplar images for image inpainting. While both text and exemplar images hav…
HiFi Tuner: High-Fidelity Subject-Driven Fine-Tuning for Diffusion Models
Zhonghao Wang, Wei Wei, Yang Zhao +4
This paper explores advancements in high-fidelity personalized image generation through the utilization of pre-trained text-to-image diffusion models. While previous approaches hav…
MobileDiffusion: Instant Text-to-Image Generation on Mobile Devices
Yang Zhao, Yanwu Xu, Zhisheng Xiao +2
The deployment of large-scale text-to-image diffusion models on mobile devices is impeded by their substantial model size and slow inference speed. In this paper, we propose \textb…
Adaptive Multi-stage Density Ratio Estimation for Learning Latent Space Energy-based Model
Zhisheng Xiao, Tian Han
This paper studies the fundamental problem of learning energy-based model (EBM) in the latent space of the generator model. Learning such prior model typically requires running cos…
Tackling the Generative Learning Trilemma with Denoising Diffusion GANs
Zhisheng Xiao, Karsten Kreis, Arash Vahdat
A wide variety of deep generative models has been developed in the past decade. Yet, these models often struggle with simultaneously addressing three key requirements including: hi…
Do We Really Need to Learn Representations from In-domain Data for Outlier Detection?
Zhisheng Xiao, Qing Yan, Yali Amit
Unsupervised outlier detection, which predicts if a test sample is an outlier or not using only the information from unlabelled inlier data, is an important but challenging task. R…
EBMs Trained with Maximum Likelihood are Generator Models Trained with a Self-adverserial Loss
Zhisheng Xiao, Qing Yan, Yali Amit
Maximum likelihood estimation is widely used in training Energy-based models (EBMs). Training requires samples from an unnormalized distribution, which is usually intractable, and…
ControlVAE: Tuning, Analytical Properties, and Performance Analysis
Huajie Shao, Zhisheng Xiao, Shuochao Yao +3
This paper reviews the novel concept of controllable variational autoencoder (ControlVAE), discusses its parameter tuning to meet application needs, derives its key analytic proper…
VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Models
Zhisheng Xiao, Karsten Kreis, Jan Kautz +1
Energy-based models (EBMs) have recently been successful in representing complex distributions of small images. However, sampling from them requires expensive Markov chain Monte Ca…
Exponential Tilting of Generative Models: Improving Sample Quality by Training and Sampling from Latent Energy
Zhisheng Xiao, Qing Yan, Yali Amit
In this paper, we present a general method that can improve the sample quality of pre-trained likelihood based generative models. Our method constructs an energy function on the la…
Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encoder
Zhisheng Xiao, Qing Yan, Yali Amit
Deep probabilistic generative models enable modeling the likelihoods of very high dimensional data. An important application of generative modeling should be the ability to detect…
A Method to Model Conditional Distributions with Normalizing Flows
Zhisheng Xiao, Qing Yan, Yali Amit
In this work, we investigate the use of normalizing flows to model conditional distributions. In particular, we use our proposed method to analyze inverse problems with invertible…
Understanding Limitation of Two Symmetrized Orders by Worst-case Complexity
Peijun Xiao, Zhisheng Xiao, Ruoyu Sun
Update order is one of the major design choices of block decomposition algorithms. There are at least two classes of deterministic update orders: nonsymmetric (e.g. cyclic order) a…
Generative Latent Flow
Zhisheng Xiao, Qing Yan, Yali Amit
In this work, we propose the Generative Latent Flow (GLF), an algorithm for generative modeling of the data distribution. GLF uses an Auto-encoder (AE) to learn latent representati…