Haiyang Sun | 孙海洋

Algorithm Specialist at Xiaomi EV
World Model Researcher for Autonomous Driving

Email GitHub Scholar
Profile Photo

About Me

I am an Algorithm Specialist at Xiaomi EV, working on world models for autonomous driving. I focus on turning cutting-edge research into production systems, enabling applications such as closed-loop simulation, synthetic data generation, and closed-loop training.

Previously, I was the World Model Tech Lead at Li Auto, where I defined the technical roadmap and built the team from the ground up, leading to the large-scale deployment of production closed-loop simulation systems.

Earlier, at Alibaba DAMO Academy, I worked on cloud-based data closed-loop algorithms, which shaped my long-term interest in scalable learning systems.

I have published over 20 papers at top conferences and journals, and won multiple international challenges. I am passionate about building systems that truly work in the real world.

News

2026/04/15 🎉 One paper accepted by ICMR 2026 (AutoAWG)
2026/02/21 🎉 Four papers accepted by CVPR 2026 (DriveLaW, DGGT, UFO, ParkGaussian)
2026/01/26 🎉 Three papers accepted by ICLR 2026 (Dream4Drive, ReCogDrive, WorldSplat)
2025/11/25 🎉 One paper accepted by TPAMI (Street Gaussians)
2025/11/08 🎉 Two papers accepted by AAAI 2026 (BAT, CorrectAD/Delphi)
2025/09/18 🎉 Two papers accepted by NeurIPS 2025 (Genesis, Pixel-perfect Depth)
2025/09/15 🏆 Winner of the RealADSim workshop @ ICCV 2025
2025/06/26 🎉 One paper accepted by ICCV 2025 (3DRealCar)
2025/06/16 🎉 One paper accepted by IROS 2025 as oral presentation (PosePilot)
2025/05/01 🎉 One paper accepted by ICML 2025 (S2-Track)
2024/12/20 🎉 One paper accepted by RA-L (DreamCar)
2024/12/10 🎉 One paper accepted by AAAI 2025 (BEV-TSR)
2024/08/16 🏆 Winner of the W-CODA workshop @ ECCV 2024
2024/07/04 🎉 Three papers accepted by ECCV 2024 (StreetGaussians, OpenSight, TOD3Cap)

Publications

† Project Leader

AutoAWG

AutoAWG: Adverse Weather Generation with Adaptive Multi-Controls for Automotive Videos

Jiagao Hu, Daiguo Zhou, Danzhen Fu, Fuhao Li, Zepeng Wang, Fei Wang, Wenhua Liao, Jiayi Xie, Haiyang Sun

ICMR 2026

Paper
PhyGenesis

Toward Physically Consistent Driving Video World Models under Challenging Trajectories

Jiawei Zhou, Zhenxin Zhu, Lingyi Du, Linye Lyu, Lijun Zhou, Zhanqian Wu, Hongcheng Luo, Zhuotao Tian, Bing Wang, Guang Chen, Hangjun Ye, Haiyang Sun†, Yu Li

arxiv

Paper Code
DriveLaW

DriveLaW: Unifying Planning and Video Generation in a Latent Driving World

Tianze Xia, Yongkang Li, Lijun Zhou, Jingfeng Yao, Kaixin Xiong, Haiyang Sun†, Bing Wang, Kun Ma, Guang Chen, Hangjun Ye, Wenyu Liu, Xinggang Wang

CVPR 2026

Paper Code
Dream4Drive

Rethinking Driving World Model as Synthetic Data Generator for Perception Tasks

Kai Zeng, Zhanqian Wu, Kaixin Xiong, Xiaobao Wei, Xiangyu Guo, Zhenxin Zhu, Kalok Ho, Lijun Zhou, Bohan Zeng, Ming Lu, Haiyang Sun†, Bing Wang, Guang Chen, Hangjun Ye, Wentao Zhang

ICLR 2026

Paper
WorldSplat

WorldSplat: Gaussian-Centric Feed-Forward 4D Scene Generation for Autonomous Driving

Ziyue Zhu, Zhanqian Wu, Zhenxin Zhu, Lijun Zhou, Haiyang Sun†, Bing Wan, Kun Ma, Guang Chen, Hangjun Ye, Jin Xie

ICLR 2026

Paper Code
CorrectAD

CorrectAD: A Self-Correcting Agentic System to Improve End-to-end Planning in Autonomous Driving

Enhui Ma, Lijun Zhou, Tao Tang, Jiahuan Zhang, Junpeng Jiang, Zhan Zhang, Dong Han, Kun Zhan, Xueyang Zhang, XianPeng Lang, Haiyang Sun, Xia Zhou, Di Lin, Kaicheng Yu

AAAI 2026

Paper
Genesis

Genesis: Multimodal Driving Scene Generation with Spatio-Temporal and Cross-Modal Consistency

Xiangyu Guo, Zhanqian Wu, Kaixin Xiong, Ziyang Xu, Lijun Zhou, Gangwei Xu, Shaoqing Xu, Haiyang Sun†, Bing Wang, Guang Chen, Hangjun Ye, Wenyu Liu, Xinggang Wang

NeurIPS 2025

Paper Code
PosePilot

PosePilot: Steering Camera Pose for Generative World Models with Self-supervised Depth

Bu Jin, Weize Li, Baihan Yang, Zhenxin Zhu, Junpeng Jiang, Huan-ang Gao, Haiyang Sun, Kun Zhan, Hengtong Hu, Xueyang Zhang, Peng Jia, Hao Zhao

IROS 2025

Paper
Mirage

Mirage: One-Step Video Diffusion for Photorealistic and Coherent Asset Editing in Driving Scenes

Shuyun Wang, Haiyang Sun†, Bing Wang, Hangjun Ye, Xin Yu

arXiv, 2025

Paper Code
Cogen

Cogen: 3d consistent video generation via adaptive conditioning for autonomous driving

Yishen Ji, Ziyue Zhu, Zhenxin Zhu, Kaixin Xiong, Ming Lu, Zhiqi Li, Lijun Zhou, Haiyang Sun†, Bing Wang, Tong Lu

arXiv, 2025

Paper
Delphi

Unleashing generalization of end-to-end autonomous driving with controllable long video generation

Enhui Ma, Lijun Zhou, Tao Tang, Zhan Zhang, Dong Han, Junpeng Jiang, Kun Zhan, Peng Jia, Xianpeng Lang, Haiyang Sun, Di Lin, Kaicheng Yu

arXiv, 2024

Paper Code
UFO

UFO: Unifying Feed-Forward and Optimization-based Methods for Large Driving Scene Modeling

Kaiyuan Tan, Yingying Shen, Mingfei Tu, Haohui Zhu, Bing Wang, Guang Chen, Hangjun Ye, Haiyang Sun†

CVPR 2026

Paper Code
ParkGaussian

ParkGaussian: Surround-view 3D Gaussian Splatting for Autonomous Parking

Xiaobao Wei, Zhangjie Ye, Yuxiang Gu, Zunjie Zhu, Yunfei Guo, Yingying Shen, Shan Zhao, Ming Lu, Haiyang Sun†, Bing Wang, Guang Chen, Rongfeng Lu, Hangjun Ye

CVPR 2026

Paper Code
DGGT

DGGT: Feedforward 4D Reconstruction of Dynamic Driving Scenes using Unposed Images

Xiaoxue Chen, Ziyi Xiong, Yuantao Chen, Gen Li, Nan Wang, Hongcheng Luo, Long Chen, Haiyang Sun†, Bing Wang, Guang Chen, Hangjun Ye, Hongyang Li, Ya-Qin Zhang, Hao Zhao

CVPR 2026

Paper Code
Street Gaussians

Street Gaussians: Modeling Dynamic Urban Scenes With Gaussian Primitives

Sida Peng, Yushi Long, Yunzhi Yan, Haotong Lin, Chenxu Zhou, Haiyang Sun, Kun Zhan, Xianpeng Lang, Hujun Bao, Xiaowei Zhou

IEEE TPAMI

Paper
Pixel-Perfect Depth

Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformers

Gangwei Xu, Haotong Lin, Hongcheng Luo, Xianqi Wang, Jingfeng Yao, Lianghui Zhu, Yuechuan Pu, Cheng Chi, Haiyang Sun†, Bing Wang, Guang Chen, Hangjun Ye, Sida Peng, Xin Yang†

NeurIPS 2025

Paper Code
3DRealCar

3drealcar: An in-the-wild rgb-d car dataset with 360-degree views

Xiaobiao Du, Yida Wang, Haiyang Sun, Zhuojie Wu, Hongwei Sheng, Shuyun Wang, Jiaying Ying, Ming Lu, Tianqing Zhu, Kun Zhan, Xin Yu

ICCV 2025

Paper Code
DreamCar

DreamCar: Leveraging Car-Specific Prior for In-the-Wild 3D Car Reconstruction

Xiaobiao Du, Haiyang Sun, Ming Lu, Tianqing Zhu, Xin Yu

IEEE RA-L 2025

Paper
Street Gaussians

Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting

Yunzhi Yan, Haotong Lin, Chenxu Zhou, Weijie Wang, Haiyang Sun, Kun Zhan, Xianpeng Lang, Xiaowei Zhou, Sida Peng

ECCV 2024

Paper Code
Uni-gaussians

Uni-gaussians: Unifying camera and lidar simulation with gaussians for dynamic driving scenarios

Zikang Yuan, Yuechuan Pu, Hongcheng Luo, Fengtian Lang, Cheng Chi, Teng Li, Yingying Shen, Haiyang Sun†, Bing Wang, Xin Yang

arXiv, 2025

Paper Code
ExtraGS

ExtraGS: Geometric-Aware Trajectory Extrapolation with Uncertainty-Guided Generative Priors

Kaiyuan Tan, Yingying Shen, Haohui Zhu, Zhiwei Zhan, Shan Zhao, Mingfei Tu, Hongcheng Luo, Haiyang Sun†, Bing Wang, Guang Chen, Hangjun Ye

arXiv, 2025

Paper Code
UniDriveVLA

UniDriveVLA: Unifying Understanding, Perception, and Action Planning for Autonomous Driving

Yongkang Li, Lijun Zhou, Sixu Yan, Bencheng Liao, Tianyi Yan, Kaixin Xiong, Long Chen, Hongwei Xie, Bing Wang, Guang Chen, Hangjun Ye, Wenyu Liu, Haiyang Sun†, Xinggang Wang

arxiv

Paper Code
ReCogDrive

ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving

Yongkang Li, Kaixin Xiong, Xiangyu Guo, Fang Li, Sixu Yan, Gangwei Xu, Lijun Zhou, Long Chen, Haiyang Sun†, Bing Wang, Guang Chen, Hangjun Ye, Wenyu Liu, Xinggang Wang

ICLR 2026

Paper Code
DriveMRP

DriveMRP: Enhancing Vision-Language Models with Synthetic Motion Data for Motion Risk Prediction

Zhiyi Hou, Enhui Ma, Fang Li, Zhiyi Lai, Kalok Ho, Zhanqian Wu, Lijun Zhou, Long Chen, Chitian Sun, Haiyang Sun†, Bing Wang, Guang Chen, Hangjun Ye, Kaicheng Yu

arXiv, 2025

Paper
BAT

BAT: Learning Event-based Optical Flow with Bidirectional Adaptive Temporal Correlation

Gangwei Xu, Haotong Lin, Zhaoxing Zhang, Hongcheng Luo, Haiyang Sun, Xin Yang

AAAI 2026

Paper
S2-Track

S2-Track: A Simple yet Strong Approach for End-to-End 3D Multi-Object Tracking

Tao Tang, Lijun Zhou, Pengkun Hao, Zihang He, Kalok Ho, Shuo Gu, Zhihui Hao, Haiyang Sun, Kun Zhan, Peng Jia, XianPeng Lang, Xiaodan Liang

ICML 2025

Paper
BEV-TSR

Bev-tsr: Text-scene retrieval in bev space for autonomous driving

Tao Tang, Dafeng Wei, Zhengyu Jia, Tian Gao, Changwei Cai, Chengkai Hou, Peng Jia, Kun Zhan, Haiyang Sun, Fan JingChen, Yixing Zhao, Xiaodan Liang, Xianpeng Lang, Yang Wang

AAAI 2025

Paper
TOD3Cap

TOD3Cap: Towards 3D Dense Captioning in Outdoor Scenes

Bu Jin, Yupeng Zheng, Pengfei Li, Weize Li, Yuhang Zheng, Sujie Hu, Xinyu Liu, Jinwei Zhu, Zhijie Yan, Haiyang Sun, Kun Zhan, Peng Jia, Xiaoxiao Long, Yilun Chen, Hao Zhao

ECCV 2024

Paper Code
OpenSight

OpenSight: A simple open-vocabulary framework for LiDAR-based object detection

Hu Zhang, Jianhua Xu, Tao Tang, Haiyang Sun, Xin Yu, Zi Huang, Kaicheng Yu

ECCV 2024

Paper

Competition

ViSE

ViSE: A Systematic Approach to Vision-Only Street-View Extrapolation

Kaiyuan Tan, Yingying Shen, Haiyang Sun†, Bing Wang, Guang Chen, Hangjun Ye

🏆 Champion! Winner of the RealADSim workshop @ ICCV 2025

Paper Code
Dive

Dive: Dit-based video generation with enhanced control

Junpeng Jiang, Gangyi Hong, Lijun Zhou, Enhui Ma, Hengtong Hu, Xia Zhou, Jie Xiang, Fan Liu, Kaicheng Yu, Haiyang Sun, Kun Zhan, Peng Jia, Miao Zhang

🏆 Champion! Winner of the W-CODA workshop @ ECCV 2024

Paper

Contact

📧

Email

AmazingRoad@163.com
🐙

GitHub

wm-research
🎓

Google Scholar

View Profile
💬

知乎

AmazingRoad
📕

小红书

View Profile