About me

I am a researcher with Shanghai AI Laboratory, working at the Physical Intelligence Center. I received my Ph.D. (2018-2022) from Multimedia Laboratory (MMLab) at CUHK, advised by Prof.Dahua Lin. I obtained my Bachelor's Degree (2014-2018) at Xi'an Jiaotong University. My research interests include 3D content generation and reconstruction, and embodied AI. I am looking for highly motivated interns in 3D generative models and embodied AI at Shanghai AI Laboratory. Drop me an email (lvzhaoyang@pjlab.org.cn) if you are interested.

Education

    The Chinese University of Hong Kong (CUHK)

    August 2018 - July 2022

    Ph.D. in Information Engineering

    Xi'an Jiaotong University (XJTU)

    August 2014 - July 2018

    B.S. in Physics (Experimental Class)

Publications

GetMesh: A Controllable Model for High-quality Mesh Generation and Manipulation

Zhaoyang Lyu, Ben Fei, Jinyi Wang, Xudong Xu, Ya Zhang, Weidong Yang, Bo Dai

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2025

[Paper] [Code] [Bibtex]

SLIDE: Controllable Mesh Generation Through Sparse Latent Point Diffusion Models

Zhaoyang Lyu, Jinyi Wang, Yuwei An, Ya Zhang, Dahua Lin, Bo Dai

IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2023

[Paper] [Code] [Bibtex]

A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completion

Zhaoyang Lyu, Zhifeng Kong, Xudong Xu, Liang Pan, Dahua Lin

International Conference on Learning Representations (ICLR) 2022

[Paper] [Code] [Bibtex]

Infinite Mobility: Scalable High-Fidelity Synthesis of Articulated Objects via Procedural Generation

Xinyu Lian, Zichao Yu, Ruiming Liang, Yitong Wang, Li Ray Luo, Kaixu Chen, Yuanzhen Zhou, Qihong Tang, Xudong Xu, Zhaoyang Lyu (Corresponding Author), Bo Dai, Jiangmiao Pang

arXiv preprint

[Paper] [Code] [Project] [Bibtex]

MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds

Bingquan Dai, Li Ray Luo, Qihong Tang, Jie Wang, Xinyu Lian, Hao Xu, Minghan Qin, Xudong Xu, Bo Dai, Haoqian Wang, Zhaoyang Lyu (Corresponding Author), Jiangmiao Pang

Neural Information Processing Systems (NeurIPS) 2025

[Paper] [Code] [Project] [Bibtex]

PnP-U3D: Plug-and-Play 3D Framework Bridging Autoregression and Diffusion for Unified Understanding and Generation

Yongwei Chen, Tianyi Wei, Yushi Lan, Zhaoyang Lyu, Shangchen Zhou, Xudong Xu, Xingang Pan

arXiv preprint

[Paper] [Project] [Bibtex]

GaussianAnything: Interactive Point Cloud Flow Matching for 3D Generation

Yushi Lan, Shangchen Zhou, Zhaoyang Lyu, Fangzhou Hong, Shuai Yang, Bo Dai, Xingang Pan, Chen Change Loy

International Conference on Learning Representations (ICLR) 2025

[Paper] [Code] [Project] [Bibtex]

LN3Diff++: Scalable Latent Neural Fields Diffusion for Speedy 3D Generation

Yushi Lan, Fangzhou Hong, Shangchen Zhou, Shuai Yang, Xuyi Meng, Yongwei Chen, Zhaoyang Lyu, Bo Dai, Xingang Pan, Chen Change Loy

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2025

[Paper] [Code] [Project] [Bibtex]

MATLABER: Material-Aware Text-to-3D via LAtent BRDF auto-EncodeR

Xudong Xu, Zhaoyang Lyu, Xingang Pan, Bo Dai

arXiv preprint

[Paper] [Code] [Bibtex]

STABLE: Simulation-Ready Tabletop Layout Generation via a Semantics-Physics Dual System

Zhen Luo, Yixuan Yang, Xudong Xu, Jinkun Hao, Zhaoyang Lyu, Feng Zheng, Jiangmiao Pang, Yanwei Fu

International Conference on Machine Learning (ICML) 2026

[Paper] [Bibtex]

STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer

Yushi Lan, Yihang Luo, Fangzhou Hong, Shangchen Zhou, Honghua Chen, Zhaoyang Lyu, Shuai Yang, Bo Dai, Chen Change Loy, Xingang Pan

International Conference on Learning Representations (ICLR) 2026

[Paper] [Code] [Project] [Bibtex]

Code-as-Room: Generating 3D Rooms from Top-Down View Images via Agentic Code Synthesis

Yixuan Yang, Zhen Luo, Wanshui Gan, Jinkun Hao, Junru Lu, Jinghao Yan, Zhaoyang Lyu, Xudong Xu

arXiv preprint

[Paper] [Code] [Project] [Bibtex]

MesaTask: Towards Task-Driven Tabletop Scene Generation via 3D Spatial Reasoning

Jinkun Hao, Naifu Liang, Zhen Luo, Xudong Xu, Weipeng Zhong, Ran Yi, Yichen Jin, Zhaoyang Lyu, Feng Zheng, Lizhuang Ma, Jiangmiao Pang

Neural Information Processing Systems (NeurIPS) 2025 (Spotlight)

[Paper] [Code] [Project] [Bibtex]

InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts

Weipeng Zhong, Peizhou Cao, Yichen Jin, Li Luo, Wenzhe Cai, Jingli Lin, Hanqing Wang, Zhaoyang Lyu, Tai Wang, Bo Dai, Xudong Xu, Jiangmiao Pang

Neural Information Processing Systems (NeurIPS) 2025

[Paper] [Code] [Project] [Bibtex]

RoboVIP: Multi-View Video Generation with Visual Identity Prompting Augments Robot Manipulation

Boyang Wang, Haoran Zhang, Shujie Zhang, Jinkun Hao, Mingda Jia, Qi Lv, Yucheng Mao, Zhaoyang Lyu, Jia Zeng, Xudong Xu, Jiangmiao Pang

arXiv preprint

[Paper] [Project] [Bibtex]

EBench: Elemental Diagnosis of Generalist Mobile Manipulation Policies

Ning Gao, Jinliang Zheng, Xing Gao, Haoxiang Ma, Hanqing Wang, Yukai Wang, Jiantong Chen, Zanxin Chen, Shujie Zhang, Mingda Jia, Xuekun Jiang, Zihou Zhu, Xinyu Li, Shuai Wang, Hao Li, Wenzhe Cai, Yuqiang Yang, Xudong Xu, Zhaoyang Lyu, Yao Mu, Tai Wang, Jiangmiao Pang, Jia Zeng, Weinan Zhang, Chunhua Shen

arXiv preprint

[Paper] [Code] [Project] [Bibtex]

Generative Diffusion Prior for Unified Image Restoration and Enhancement

Ben Fei, Zhaoyang Lyu (Equal Contribution), Liang Pan, Junzhe Zhang, Weidong Yang, Tianyue Luo, Bo Zhang, Bo Dai

IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2023

[Paper] [Code] [Bibtex]

Accelerating Diffusion Models via Early Stop of the Diffusion Process

Zhaoyang Lyu, Xudong Xu, Ceyuan Yang, Dahua Lin, Bo Dai

arXiv preprint

[Paper] [Code] [Bibtex]

DiffBIR: Toward Blind Image Restoration with Generative Diffusion Prior

Xinqi Lin, Jingwen He, Ziyan Chen, Zhaoyang Lyu, Bo Dai, Fanghua Yu, Yu Qiao, Wanli Ouyang, Chao Dong

European Conference on Computer Vision (ECCV) 2024

[Paper] [Code] [Bibtex]

Point Cloud Pre-training with Diffusion Models

Xiao Zheng, Xiaoshui Huang, Guofeng Mei, Yuenan Hou, Zhaoyang Lyu, Bo Dai, Wanli Ouyang, Yongshun Gong

IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2024

[Paper] [Code] [Bibtex]

Guided Diffusion Model for Adversarial Purification

Jinyi Wang, Zhaoyang Lyu (Equal Contribution), Dahua Lin, Bo Dai, Hongfei Fu

arXiv preprint

[Paper] [Code] [Bibtex]

Towards Evaluating and Training Verifiably Robust Neural Networks

Zhaoyang Lyu, Minghao Guo, Tong Wu, Guodong Xu, Kehuan Zhang, Dahua Lin

IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2021 (Oral)

[Paper] [Code] [Bibtex]

Fastened CROWN: Tightened Neural Network Robustness Certificates

Zhaoyang Lyu, Ching-Yun Ko, Zhifeng Kong, Ngai Wong, Dahua Lin, Luca Daniel

AAAI Conference on Artificial Intelligence (AAAI) 2020

[Paper] [Code] [Bibtex]

POPQORN: Quantifying Robustness of Recurrent Neural Networks

Ching-Yun Ko, Zhaoyang Lyu (Equal Contribution), Tsui-Wei Weng, Luca Daniel, Ngai Wong, Dahua Lin

International Conference on Machine Learning (ICML) 2019

[Paper] [Code] [Bibtex]