Ziyu Wan

Ziyu Wan (万子钰)

I am a Member of Technical Staff at Microsoft AI Superintelligence. We mid/post-train OpenAI and MAI models.
I received my Ph.D. from Department of Computer Science, City University of Hong Kong in 2024, where I was fortunate advised by Prof. Jing Liao.
My current research interests include:

Multi-modality (text, image, video, 3D and 4D) generation
Agentic training
Computational Photography and Neural Rendering

Past Affiliations:

Research & Product

Code Video Model
Project Lead, Code Video Model Team
Technical Report. webpage paper bib benchmark

OPSD-V: On-Policy Self-Distillation for Post-Training Few-Step Autoregressive Video Generators
Hongyu Liu, Chun Wang, Feng Gao, Xuanhua He, Yue Ma, Ziyu Wan, Yong Zhang, Xiaoming Wei, Qifeng Chen
Technical Report. webpage paper bib code

MAI-Thinking-1 & MAI-Code-1-Flash
Contributor, Microsoft Superintelligence Team (MSI)
Technical Report. thinking_1_paper code_1_model_card

Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models
Project Lead, Microsoft Lens Team
Technical Report. paper bib code huggingface model_card

LACON: Training Text-to-Image Model from Uncurated Data
Zhiyang Liang, Ziyu Wan, Hongyu Liu, Dong Chen, Qiu Shen, Hao Zhu, Dongdong Chen
ECCV 2026. webpage paper bib

RubricRL: Simple Generalizable Rewards for Text-to-Image Generation
Xuelu Feng, Yunsheng Li, Ziyu Wan, Zixuan Gao, Junsong Yuan, Dongdong Chen, Chunming Qiao
ECCV 2026. paper bib

AvatarPointillist: AutoRegressive 4D Gaussian Avatarization
Hongyu Liu, Xuan Wang, Zijian Wu, Yating Wang, Ziyu Wan, Yue Ma, Runtao Liu, Boyao Zhou, Yujun Shen, Qifeng Chen
CVPR 2026. webpage paper bib code

VLM4D: Towards Spatiotemporal Awareness in Vision Language Models
Shijie Zhou, Alexander Vilesov, Xuehai He, Ziyu Wan, Shuwang Zhang, Aditya Nagachandra, Di Chang, Dongdong Chen, Xin Eric Wang, Achuta Kadambi
ICCV 2025. webpage paper benchmark bib

ε-VAE: Denoising as Visual Decoding
Long Zhao, Sanghyun Woo, Ziyu Wan, Yandong Li, Han Zhang, Boqing Gong, Hartwig Adam, Xuhui Jia, Ting Liu
ICML 2025. paper bib

AvatarArtist: Open-Domain 4D Avatarization
Hongyu Liu, Xuan Wang, Ziyu Wan, Yue Ma, Jingye Chen, and Yanbo Fan, Yujun Shen, Yibing Song, Qifeng Chen
CVPR 2025. webpage paper bib code demo

EG4D: Explicit Generation of 4D Object without Score Distillation
Qi Sun, Zhiyang Guo, Ziyu Wan, Jing Nathan Yan, Shengming Yin, Wengang Zhou, Jing Liao, Houqiang Li
ICLR 2025. paper bib code

An Object is Worth 64x64 Pixels: Generating 3D Object via Image Diffusion
Xingguang Yan, Han-Hung Lee, Ziyu Wan, Angel X. Chang
3DV 2025, 🏆 Best Paper Award 🏆. webpage paper bib code

RaFE: Generative Radiance Fields Restoration
Zhongkai Wu, Ziyu Wan, Jing Zhang, Jing Liao, Dong Xu
ECCV 2024, Oral. webpage paper bib code

CAD: Photorealistic 3D Generation via Adversarial Distillation
Ziyu Wan, Despoina Paschalidou, Ian Huang, Hongyu Liu, Bokui Shen, Xiaoyu Xiang, Jing Liao, Leonidas Guibas
CVPR 2024. webpage paper bib code

HeadArtist: Text-conditioned 3D Head Generation with Self Score Distillation
Hongyu Liu, Xuan Wang, Ziyu Wan, Yujun Shen, Yibing Song, Jing Liao, Qifeng Chen
SIGGRAPH 2024. webpage paper bib code

High-Fidelity and Efficient Pluralistic Image Completion With Transformers
Ziyu Wan, Jingbo Zhang, Dongdong Chen, Jing Liao
TPAMI 2024. webpage paper bib code

Text2NeRF: Text-Driven 3D Scene Generation with Neural Radiance Fields
Jingbo Zhang, Xiaoyu Li, Ziyu Wan, Can Wang, Jing Liao
TVCG 2024. webpage paper bib code

Learning Neural Duplex Radiance Fields for Real-Time View Synthesis
Ziyu Wan, Christian Richardt, Aljaž Božič, Chao Li, Vijay Rengarajan, Seonghyeon Nam, Xiaoyu Xiang, Tuotuo Li, Bo Zhu, Rakesh Ranjan, Jing Liao
CVPR 2023. webpage paper bib webgl_viewer

FDNeRF: Few-Shot Dynamic Neural Radiance Fields for Face Reconstruction and Expression Editing
Jingbo Zhang, Xiaoyu Li, Ziyu Wan, Can Wang, Jing Liao
SIGGRAPH Asia 2022. webpage paper bib code

Bringing Old Films Back to Life
Ziyu Wan, Bo Zhang, Dongdong Chen, Jing Liao
CVPR 2022. webpage paper bib code

Old Photo Restoration via Deep Latent Space Translation
Ziyu Wan, Bo Zhang, Dongdong Chen, Pan Zhang, Dong Chen, Fang Wen, Jing Liao
TPAMI 2022, 15.3k+ stars! webpage paper bib code

Adaptive Joint Optimization for 3D Reconstruction with Differentiable Rendering
Jingbo Zhang, Ziyu Wan, Jing Liao
TVCG 2022. webpage paper bib code

High-Fidelity Pluralistic Image Completion with Transformers
Ziyu Wan, Jingbo Zhang, Dongdong Chen, Jing Liao
ICCV 2021. webpage paper bib code

Visual Structure Constraint for Transductive Zero-Shot Learning in the Wild
Ziyu Wan, Dongdong Chen, Jing Liao
IJCV 2021. paper bib code

PD-GAN: Probabilistic Diverse GAN for Image Inpainting
Hongyu Liu, Ziyu Wan, Wei Huang, Yibing Song, Xintong Han, Jing Liao
CVPR 2021. paper bib code

DeFLOCNet: Deep Image Editing via Flexible Low-level Controls
Hongyu Liu, Ziyu Wan, Wei Huang, Yibing Song, Xintong Han, Jing Liao, Bin Jiang, Wei Liu
CVPR 2021. paper bib code

Meta-PU: An Arbitrary-Scale Upsampling Network for Point Cloud
Shuquan Ye, Dongdong Chen, Songfang Han, Ziyu Wan, Jing Liao
TVCG 2021. paper bib code

Bringing Old Photos Back to Life
Ziyu Wan, Bo Zhang, Dongdong Chen, Pan Zhang, Dong Chen, Jing Liao, Fang Wen
CVPR 2020, Oral. webpage paper bib code

Transductive Zero-Shot Learning with Visual Structure Constraint
Ziyu Wan*, Dongdong Chen*, Yan Li, Xingguang Yan, Junge Zhang, Yizhou Yu, Jing Liao
NeurIPS 2019. paper bib code