Publications
See my semantic scholar profile page for more details.
Preprints
Ufogen: You Forward Once Large Scale Text-to-image Generation via Diffusion Gans
Yanwu Xu, Yang Zhao, Zhisheng Xiao, Tingbo Hou
MobileDiffusion: Subsecond Text-to-Image Generation on Mobile Devices
Yang Zhao, Yanwu Xu, Zhisheng Xiao, Tingbo Hou
DreamInpainter: Text-Guided Subject-Driven Image Inpainting with Diffusion Models
Shaoan Xie, Yang Zhao, Zhisheng Xiao, Kelvin C.K. Chan, Yandong Li, Yanwu Xu, Kun Zhang, Tingbo Hou
HiFi Tuner: High-Fidelity Subject-Driven Fine-Tuning for Diffusion Models
Zhonghao Wang, Wei Wei, Yang Zhao, Zhisheng Xiao, Mark Hasegawa-Johnson, Humphrey Shi, Tingbo Hou
Conference and Journal Papers
Adaptive Multi-stage Density Ratio Estimation for Learning Latent Space Energy-based Model
Zhisheng Xiao, Tian Han
Conference on Neural Information Processing Systems (NeurIPS), 2022 (Oral)
Tackling the Generative Learning Trilemma with Denoising Diffusion GANs
Codes Project page
Zhisheng Xiao, Karsten Kreis, and Arash Vahdat
International Conference on Learning Representations (ICLR), 2022 (Spotlight)
Two Symmetrized Coordinate Descent Methods Can Be O(n^2) Times Slower Than the Randomized Version
Peijun Xiao, Zhisheng Xiao, and Ruoyu Sun
SIAM Journal on Optimization, 2021
ControlVAE: Tuning, Analytical Properties, and Performance Analysis
Huajie Shao, Zhisheng Xiao, Shuochao Yao, Aston Zhang, Shengzhong Liu, and Tarek Abdelzaher
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021
VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Models
Code
Zhisheng Xiao, Karsten Kreis, Jan Kautz, and Arash Vahdat
International Conference on Learning Representations (ICLR), 2021 (Spotlight)
Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encoder
Code
Zhisheng Xiao, Qing Yan, and Yali Amit
Conference on Neural Information Processing Systems (NeurIPS), 2020
Workshop Papers
Do We Really Need to Learn Representations from In-domain Data for Outlier Detection?
Zhisheng Xiao, Qing Yan, and Yali Amit
ICML Workshop on Uncertainty & Robustness in Deep Learning, 2021
EBMs Trained with Maximum Likelihood are Generator Models Trained with a Self-adverserial Loss
Zhisheng Xiao, Qing Yan, and Yali Amit
Energy Based Models Workshop - ICLR, 2021
Improving Sample Quality by Training and Sampling from Latent Energy
Zhisheng Xiao, Qing Yan, and Yali Amit
ICML Workshop on Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models, 2020
Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encoder
Zhisheng Xiao, Qing Yan, and Yali Amit
ICML Workshop on Uncertainty & Robustness in Deep Learning, 2020 (Spotlight)
Technical Reports
A Method to Model Conditional Distributions with Normalizing Flows
Zhisheng Xiao, Qing Yan, and Yali Amit
Preprint, 2019
Generative Latent Flow
Zhisheng Xiao, Qing Yan, and Yali Amit
Preprint, 2019
Thesis
Designing Deep Generative Models with Symbiotic Composition
Zhisheng Xiao