News | Publications | Experience | Service

Cheng, Chong 程冲

I am a Ph.D. student in Artificial Intelligence at HKUST (Guangzhou & Clear Water Bay), advised by Prof. Hao Wang and Prof. Long Chen. I was a visiting student at NTU working with Prof. Guosheng Lin. I received my M.Sc. from TU Berlin.

My research focuses on 3D/4D foundation models and world models. Starting from 3D scene representation, I have progressively expanded to long-horizon streaming autoregressive modeling. Currently, I am exploring unified representations that connect spatial reasoning, dynamic modeling, and understanding and generation, toward building unified multimodal world models.

I am graduating soon and actively looking for job opportunities. Feel free to reach out!

News

[2026.02] NEW! LongStream is accepted to CVPR 2026.
[2026.02] NEW! VGGT4D is accepted to CVPR 2026 (Findings).
[2025.07] RegGS is accepted to ICCV 2025.
[2025.07] S3POGS is accepted to ICCV 2025.
[2025.01] GraphGS is accepted to ICLR 2025.
[2025.01] RGB-only GS SLAM is accepted to ICRA 2025.
[2025.01] Decoupled VR Generation is accepted to IEEE VR 2025 (Poster).
[2024.09] GVKF is accepted to NeurIPS 2024.
[2024.01] Prompt, Plan, Perform is accepted to ICRA 2024.

Publications

* denotes equal contribution. Representative papers listed below.

HorizonStream: Long-Horizon Attention for Streaming 3D Reconstruction
Chong Cheng, Peilin Tao, Nanjie Yao, Guanzhi Ding, Xianda Chen, Yuansen Du, Xiaoyang Guo, Wei Yin, Weiqiang Ren, Qian Zhang, Zhengqing Chen, Hao Wang
ArXiv, 2026
[Paper] [Project] [Code]

LongStream: Long-Sequence Autoregression Visual Geometry with Metric Scale
Chong Cheng, Xianda Chen, Tao Xie, Wei Yin, Weiqiang Ren, Qian Zhang, Xiaoyang Guo, Hao Wang
CVPR, 2026
[Paper] [Project] [Code]

VGGT4D: Mining Motion Cues in Visual Geometry Transformers for 4D Scene Reconstruction
Yu Hu*, Chong Cheng*, Sicheng Yu, Xiaoyang Guo, Hao Wang
CVPR, 2026 (Findings)
[Paper] [Project]

RegGS: Unposed Sparse Views Gaussian Splatting with 3DGS Registration
Chong Cheng*, Yu Hu*, Sicheng Yu, Beizhen Zhao, Zijian Wang, Hao Wang
ICCV, 2025
[Paper] [Project] [Code]

S3POGS: Outdoor Monocular SLAM with Global Scale-Consistent 3D Gaussian Pointmaps
Chong Cheng*, Sicheng Yu*, Zijian Wang, Yifan Zhou, Hao Wang
ICCV, 2025
[Paper] [Project] [Code]

GraphGS: Graph-guided Scene Reconstruction from Images with 3D Gaussian Splatting
Chong Cheng*, Gaochao Song*, Yiyang Yao, Qinzheng Zhou, Gangjian Zhang, Hao Wang
ICLR, 2025
[Paper] [Project] [Code]

GVKF: Gaussian Voxel Kernel Functions for Highly Efficient Surface Reconstruction in Open Scenes
Gaochao Song*, Chong Cheng*, Hao Wang
NeurIPS, 2024
[Paper] [Project] [Code]

RGB-only Gaussian Splatting SLAM for Unbounded Outdoor Scenes
Sicheng Yu*, Chong Cheng*, Yifan Zhou, Xiaojun Yang, Hao Wang
ICRA, 2025
[Paper]

Exploring Decoupled Generation for Enhancing VR Interaction and Control
Chong Cheng, Qinzheng Zhou, Jianfeng Zhang, Shiya Zeng, Hao Wang
IEEE VR, 2025 (Poster)
[Paper]

Prompt, Plan, Perform: LLM-based Humanoid Control via Quantized Imitation Learning
Jingkai Sun, Qiang Zhang, Yiqun Duan, Xiaoyang Jiang, Chong Cheng, Renjing Xu
ICRA, 2024
[Paper]

Experience

2026.05 – Present	Tencent — Qingyun Research Intern, working closely with Ran Zhang
2025.08 – 2026.05	Horizon Robotics — Research Intern, working closely with Xiaoyang Guo and Wei Yin
2023.09 – 2024.06	Tsinghua PBCSF — Research Intern (LLM & Agent)
2022.03 – 2022.09	DAI-Lab, TU Berlin — Research Assistant, advised by Prof. Sahin Albayrak
2021.10 – 2022.03	CARIAD (Volkswagen Group) — Research Intern

Academic Service

Reviewer: CVPR, ICCV, ECCV, NeurIPS, ICLR, TIP, WACV, AAAI, ACM MM, Neurocomputing