Publications

Research with visual evidence.

My research centers on generative world models, scene flow, LiDAR odometry, 3D/4D perception, and end-to-end driving. Looking ahead, I am building toward closed-loop simulation that couples reconstruction with one-step generation, streaming generation, and one-step video / image synthesis.

Generative World Models
Scene Flow
LiDAR Odometry
3D / 4D Perception
End-to-End Driving

ICML Accepted · Spotlight 2026

VectorWorld: Efficient Streaming World Model via Diffusion Flow on Vector Graphs

Chaokang Jiang, Desen Zhou, Jiuming Liu, Kevin Li Sun

Bosch China Research Collaboration

A streaming world model for autonomous-driving scenarios built on vector-graph diffusion flow.

Contribution. It aims to make future scene evolution modeling more efficient by operating on compact vectorized scene representations.

Project Page PDF arXiv Code BibTeX

arXiv Preprint 2026

RegFormer++: An Efficient Large-Scale 3D LiDAR Point Registration Network with Projection-Aware 2D Transformer

Jiuming Liu, Guangming Wang, Zhe Liu, Chaokang Jiang, Haoang Li, Mengmeng Liu, Tianchen Deng, Marc Pollefeys, Michael Ying Yang, Hesheng Wang

Research Collaboration

A large-scale 3D LiDAR point registration network with projection-aware transformer design.

Contribution. It improves registration efficiency and scalability by coupling 3D point registration with projection-aware 2D transformer modeling.

PDF arXiv DOI BibTeX

T-PAMI Published 2026

DifFlow3D: Hierarchical Diffusion Models for Uncertainty-Aware 3D Scene Flow Estimation

Jiuming Liu, Weicai Ye, Guangming Wang, Chaokang Jiang, Lei Pan, Jinru Han, Zhe Liu, Guofeng Zhang, Hesheng Wang

Research Collaboration

A journal version of diffusion-based uncertainty-aware 3D scene flow estimation.

Contribution. It extends the diffusion formulation into a hierarchical framework for more robust and uncertainty-aware point motion estimation.

DOI BibTeX

TITS Published 2025

Unsupervised Learning of 3D Scene Flow With LiDAR Odometry Assistance

Guangming Wang, Zhiheng Feng, Chaokang Jiang, Jiuming Liu, Hesheng Wang

SJTU IRMV Research Collaboration

An unsupervised 3D scene flow learning method assisted by LiDAR odometry.

Contribution. It leverages odometry cues to reduce the dependency on dense point-level motion labels.

DOI BibTeX

CVPR Published 2025

Mamba4D: Efficient 4D Point Cloud Video Understanding with Disentangled Spatial-Temporal State Space Models

Jiuming Liu, Jinru Han, Lihao Liu, Angelica I. Avilés-Rivero, Chaokang Jiang, Zhe Liu, Hesheng Wang

Research Collaboration

A 4D point cloud video understanding framework based on disentangled spatial-temporal state space modeling.

Contribution. It improves long-sequence point cloud video modeling efficiency through separate spatial and temporal sequence reasoning.

DOI BibTeX

arXiv Preprint 2025

GMF-Drive: Gated Mamba Fusion with Spatial-Aware BEV Representation for End-to-End Autonomous Driving

Jian Wang, Chaokang Jiang, Haitao Xu

Research Collaboration

An end-to-end autonomous-driving model with gated Mamba fusion and spatial-aware BEV representation.

Contribution. It explores sequence modeling and BEV feature fusion for integrated autonomous-driving decision pipelines.

PDF arXiv DOI BibTeX

arXiv Preprint 2025

D^2GSLAM: 4D Dynamic Gaussian Splatting SLAM

Siting Zhu, Yuxiang Huang, Wenhua Wu, Chaokang Jiang, Yongbo Chen, I-Ming Chen, Hesheng Wang

Research Collaboration

A dynamic SLAM framework based on 4D Gaussian splatting.

Contribution. It models dynamic scene structure with Gaussian representations for SLAM in changing environments.

PDF arXiv DOI BibTeX

CVPR Published 2024

DifFlow3D: Toward Robust Uncertainty-Aware Scene Flow Estimation with Iterative Diffusion-Based Refinement

Jiuming Liu, Guangming Wang, Weicai Ye, Chaokang Jiang, Jinru Han, Zhe Liu, Guofeng Zhang, Dalong Du, Hesheng Wang

SJTU IRMV Research Collaboration

A diffusion-based 3D scene flow method for robust and uncertainty-aware point motion estimation.

Contribution. It formulates scene flow refinement as an iterative diffusion process to better handle uncertainty and challenging motion.

DOI BibTeX

CVPR Published 2024

3DSFLabelling: Boosting 3D Scene Flow Estimation by Pseudo Auto-labelling

Chaokang Jiang, Guangming Wang, Jiuming Liu, Hesheng Wang, Zhuang Ma, Zhenqiang Liu, Zhujin Liang, Yi Shan, Dalong Du

SJTU IRMV PhiGent Robotics Research Collaboration

A pseudo auto-labeling framework that provides high-quality 3D motion flow labels for LiDAR point clouds.

Contribution. It reduces the scarcity of point-level 3D motion labels and improves downstream scene flow estimation.

DOI Code BibTeX

NeurIPS Published 2024

NeuroGauss4D-PCI: 4D Neural Fields and Gaussian Deformation Fields for Point Cloud Interpolation

Chaokang Jiang, Dalong Du, Jiuming Liu, Siting Zhu, Zhenqiang Liu, Zhuang Ma, Zhujin Liang, Jie Zhou

Research Collaboration

A 4D point cloud interpolation framework using neural fields and Gaussian deformation fields.

Contribution. It reconstructs temporally continuous point clouds by combining neural field representation with deformation-aware Gaussian modeling.

DOI Code BibTeX

TII Published 2023

3-D Scene Flow Estimation on Pseudo-LiDAR: Bridging the Gap on Estimating Point Motion

Chaokang Jiang, Guangming Wang, Yanzi Miao, Hesheng Wang

CUMT SJTU IRMV

A 3D scene flow estimation study on pseudo-LiDAR point representations.

Contribution. It bridges image-derived pseudo-LiDAR representations and point motion estimation for 3D scene understanding.

DOI BibTeX

TIM Published 2023

Pseudo-LiDAR for Visual Odometry

Yanzi Miao, Huiying Deng, Chaokang Jiang, Zhiheng Feng, Xinrui Wu, Guangming Wang, Hesheng Wang

CUMT SJTU IRMV

A visual odometry method using pseudo-LiDAR representations.

Contribution. It leverages pseudo-LiDAR geometry to improve visual odometry estimation.

DOI BibTeX

AAAI Published 2023

TransLO: A Window-Based Masked Point Transformer Framework for Large-Scale LiDAR Odometry

Jiuming Liu, Guangming Wang, Chaokang Jiang, Liu Zhe, Hesheng Wang

SJTU IRMV Research Collaboration

A masked point transformer framework for large-scale LiDAR odometry.

Contribution. It introduces window-based transformer modeling to improve LiDAR odometry scalability.

DOI BibTeX

ICCV Published 2023

RegFormer: An Efficient Projection-Aware Transformer Network for Large-Scale Point Cloud Registration

Jiuming Liu, Guangming Wang, Zhe Liu, Chaokang Jiang, Marc Pollefeys, Hesheng Wang

SJTU IRMV Research Collaboration

A projection-aware transformer network for large-scale point cloud registration.

Contribution. It improves point cloud registration by combining projection-aware representation with efficient transformer reasoning.

DOI BibTeX

AIS Published 2022

SFGAN: Unsupervised Generative Adversarial Learning of 3D Scene Flow from the 3D Scene Self

Guangming Wang, Chaokang Jiang, Zehang Shen, Yanzi Miao, Hesheng Wang

CUMT SJTU IRMV

An unsupervised adversarial learning framework for 3D scene flow.

Contribution. It learns scene flow from self-structured 3D scene signals without dense supervised motion labels.

DOI BibTeX

arXiv Preprint 2022

FFPA-Net: Efficient Feature Fusion with Projection Awareness for 3D Object Detection

Chaokang Jiang, Guangming Wang, Jinxing Wu, Yanzi Miao, Hesheng Wang

CUMT SJTU IRMV

A projection-aware feature fusion method for 3D object detection.

Contribution. It improves multi-modal 3D detection by indexing and fusing image and point cloud features more efficiently.

PDF arXiv DOI BibTeX