Tingbo Hou

I am leading a research team working on Generative AI at Google. We are building highly efficient Generative AI that can be served or deployed to end users.


My work enables ML features in multiple Google products, including Photos, YouTube, Meet, Ads, Cloud, Pixel, Android, etc, recognized by several PA/company level awards, including the Google Tech Impact Award of 2023.


Besides Google, I spent two years in a start-up working on autonomous driving. I obtained my Ph.D. in Computer Science from Stony Brook University, and B.S. from University of Science and Technology of China.


Google Scholar  /  LinkedIn  /  Google Research

Research

PRDP: Proximal Reward Difference Prediction for Large-Scale Reward Finetuning of Diffusion Models

Fei Deng, Qifei Wang, Wei Wei, Matthias Grundmann, Tingbo Hou,
[arXiv]    [website]
MobileDiffusion: Subsecond Text-to-Image Generation on Mobile Devices

Yang Zhao, Yanwu Xu, Zhisheng Xiao, Tingbo Hou
[arXiv]
UFOGen: You Forward Once Large Scale Text-to-Image Generation via Diffusion GANs

Yanwu Xu*, Yang Zhao*, Zhisheng Xiao*, Tingbo Hou (*equal contribution)
[arXiv]
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
[arXiv]
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
[arXiv]
HyperDreamBooth: HyperNetworks for Fast Personalization of Text-to-Image Models

Nataniel Ruiz, Yuanzhen Li, Varun Jampani, Wei Wei, Tingbo Hou, Yael Pritch, Neal Wadhwa, Michael Rubinstein, Kfir Aberman
[arXiv]    [website]
Taming Encoder for Zero Fine-tuning Image Customization with Text-to-Image Diffusion Models
Xuhui Jia*, Yang Zhao*, Kelvin C.K. Chan*, Yandong Li, Han Zhang, Boqing Gong, Huisheng Wang, Tingbo Hou, Yu-Chuan Su (*equal contribution)
[arXiv]
Semi-Implicit Denoising Diffusion Models (SIDDMs)

Yanwu Xu, Mingming Gong, Shaoan Xie, Wei Wei, Matthias Grundmann, Kayhan Batmanghelich*, Tingbo Hou* (*equal contribution)
[arXiv], NeurIPS 2023
Towards Authentic Face Restoration with Iterative Diffusion Models and Beyond

Yang Zhao, Tingbo Hou, Yu-Chuan Su, Xuhui Jia, Yandong Li, Matthias Grundmann
[arXiv], ICCV 2023
Multiscale Representation for Real-Time Anti-Aliasing Neural Rendering

Dongting Hu, Zhenkai Zhang, Tingbo Hou, Tongliang Liu, Huang Fu, Mingming Gong
[arXiv], ICCV 2023