Guangfeng Jiang

About Me

I am currently a researcher on the World Model Team at XPENG, where I work on predictive world models and multimodal foundation models for autonomous driving. I received my Ph.D. degree from the Department of Electronic Engineering and Information Science at the University of Science and Technology of China (USTC), under the supervision of Prof. Jun Liu. Before pursuing my doctoral studies at USTC, I received my undergraduate education at the Chongxin College of Shandong University. Previously, I interned at COWAROBOT, AMD, and Huawei Noah’s Ark Lab.

Research Interests

World Model
Multimodal Large Model
Autonomous Driving
Computer Vision

News

[Jun. 2026] We released X-Mind, an efficient visual chain-of-thought framework for end-to-end autonomous driving.
[Feb. 2026] Our papers WPT, DLWM, and WorldLens were accepted to CVPR 2026.
[Dec. 2025] We released UniUGP, a unified framework for understanding, generation, and planning.
[Nov. 2025] We released our world-model-based planning paper WPT.
[Sep. 2025] We released our 4D scene generation paper PhiGenesis.
[Feb. 2025] We released our weakly supervised learning paper YoCo.
[Dec. 2024] Our 3D reconstruction paper EGSRAL was accepted to AAAI 2025.
[Dec. 2023] Our weakly supervised learning paper MWSIS was accepted to AAAI 2024.

Publications

Arxiv

X-Mind: Efficient Visual Chain-of-Thought via Predictive World Model for End-to-End Driving (XPeng)

Bohao Zhao*, Chengrui Wei*, Guangfeng Jiang*, Ruixin Liu*, Xuejie Lv*, Liu Liang, Sutao Deng, Xiuyang Fan, Pengkun Zheng, Jinyun Zhou, Rui Guo, Hanpeng Liu, Yutong Zheng, Yi Guo, Xinlong Zheng, Qingyu Luo, Zhuangzhuang Ding, Yu Zhang, Hang Zhang, Xianming Liu

Technical Report, 2026

PDF Project Page *Core contribution

Arxiv

UniUGP: Unifying Understanding, Generation, and Planning for End-to-End Autonomous Driving (ByteDance Seed)

Hao Lu, Ziyang Liu, Guangfeng Jiang, Yuanfei Luo, Sheng Chen, Yangang Zhang, Ying-Cong Chen

PDF Project Page

CVPR

WPT: World-to-Policy Transfer via Online World Model Distillation (Huawei Noah's Ark Lab)

Guangfeng Jiang, Yueru Luo, Jun Liu, Yi Huang, Yiyao Zhu, Zhan Qu, Dave Zhenyu Chen, Bingbing Liu, Xu Yan

CVPR 2026 (CCF-A)

PDF Project Page

Arxiv

4D Driving Scene Generation With Stereo Forcing (Phigent Robotics)

Hao Lu*, Zhuang Ma*, Guangfeng Jiang, Wenhang Ge, Bohan Li, Yuzhan Cai, Wenzhao Zheng, Yunpeng Zhang, Yingcong Chen

PDF Code Project Page

ESWA

You Only Click Once: Single Point Weakly Supervised 3D Instance Segmentation for Autonomous Driving

Guangfeng Jiang, Jun Liu, YongXuan Lv, Yuzhi Wu, Xianfei Li, Wenlong Liao, Tao He, Pai Peng

ESWA

PDF

AAAI

EGSRAL: An Enhanced 3D Gaussian Splatting based Renderer with Automated Labeling for Large-Scale Driving Scene (AMD-AIG)

Yixiong Huo*, Guangfeng Jiang*, Hongyang Wei, Ji Liu, Song Zhang, Han Liu, Xingliang Huang, Mingjie Lu, Jinzhang Peng, Dong Li, Lu Tian, Emad Barsoum (*Equal contribution)

AAAI 2025 (CCF-A)

PDF

AAAI

MWSIS: Multimodal Weakly Supervised Instance Segmentation with 2D Box Annotations for Autonomous Driving

Guangfeng Jiang, Jun Liu, Yuzhi Wu, Wenlong Liao, Tao He, Pai Peng

AAAI 2024 (CCF-A)

PDF Project Page

Arxiv

MLF-4DRCNet: Multi-Level Fusion with 4D Radar and Camera for 3D Object Detection in Autonomous Driving

Yuzhi Wu, Li Xiao, Jun Liu, Guangfeng Jiang, XiangGen Xia

PDF

TITS

Mask-RadarNet: Enhancing Transformer With Spatial-Temporal Semantic Context for Radar Object Detection in Autonomous Driving

Yuzhi Wu, Jun Liu, Guangfeng Jiang, Weijian Liu, Danilo Orlando

TITS

PDF

ESWA

Radar M3-Net: Multi-Scale, Multi-Layer, Multi-Frame Network With a Large Receptive Field for 3D Object Detection

Yunting Yang, Jun Liu, Hongsi Liu, Guangfeng Jiang

ESWA

PDF

TITS

MSSF: A 4D Radar and Camera Fusion Framework With Multi-Stage Sampling for 3D Object Detection in Autonomous Driving

Hongsi Liu, Jun Liu, Guangfeng Jiang, Xin Jin

TITS

PDF

TIV

Spatial and Temporal Awareness Network for Semantic Segmentation on Automotive Radar Point Cloud

Ziwei Zhang, Jun Liu, Guangfeng Jiang

TIV

PDF

Experience

XPENG

· Researcher, World Model Team

· Predictive World Models and Multimodal Foundation Models for Autonomous Driving

· Representative work: X-Mind

Noah's Ark Lab, Huawei

· World Model for End-to-End Autonomous Driving

· Representative works: WPT and DLWM

AMD-AIG

· World Model

· CVPR 2024 Challenge: MapLess Driving, 5/120; World Model, 7/60

· 3D Reconstruction (3DGS) for Autonomous Driving

· Representative work: EGSRAL

COWAROBOT

· Weakly-Supervised Perception for Autonomous Driving

· Representative works: YoCo and MWSIS