Qiuhong Shen

I am a final-year Ph.D. student in xML Lab @ NUS, advised by Prof. Xinchao Wang. I received my Master's degree from HIT(SZ), supervised by Prof. Yongsheng Liang. Throughout these years, I have been fortunate to collaborate with Prof. Shuicheng Yan on 3D content generation during my PhD, and with Prof. Wanli Ouyang on visual object tracking during my Master's years.

I aim to build real-time world models and advance efficient spatial intelligence, pursuing feed-forward 3D/4D scene reconstruction and generation that operates at interactive speed and scales to open-world content.

Qiuhong Shen

Publications   Selected  |  All

NutWorld teaser
Seeing World Dynamics in a Nutshell
Qiuhong Shen*, Xuanyu Yi*, Mingbao Lin, Hanwang Zhang, Shuicheng Yan, Xinchao Wang
Tech Report, arXiv (under review)
Paper
SPEED teaser
SPEED: Sharpened-Teacher Distillation for Parallel Decoding of Diffusion Language Models
Qiuhong Shen, Xingyi Yang, Xinyin Ma, Gongfan Fang, Xinchao Wang
International Conference on Machine Learning (ICML 2026)
Paper  /  Bibtex
TreeSplat teaser
TreeSplat: Mergeable Tree for Deformable Gaussian Splatting
Qiuhong Shen, Xingyi Yang, Xinchao Wang
Conference on Neural Information Processing Systems (NeurIPS 2025)
Project Page  /  Paper  /  Bibtex
Test3R teaser
Test3R: Learning to Reconstruct 3D at Test Time
Yuheng Yuan, Qiuhong Shen, Shizun Wang, Xingyi Yang, Xinchao Wang
Conference on Neural Information Processing Systems (NeurIPS 2025)
Project Page  /  Paper  /  Bibtex
4DGS teaser
1000+ FPS 4D Gaussian Splatting for Dynamic Scene Rendering
Yuheng Yuan*, Qiuhong Shen*, Xingyi Yang, Xinchao Wang
Conference on Neural Information Processing Systems (NeurIPS 2025)
Project Page  /  Paper  /  Bibtex
Gamba teaser
Gamba: Marry Gaussian Splatting with Mamba for Single-View 3D Reconstruction
Qiuhong Shen*, Zike Wu*, Xuanyu Yi*, Pan Zhou, Hanwang Zhang, Shuicheng Yan, Xinchao Wang
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI 2025)
Project Page  /  Paper  /  Bibtex
MVGamba teaser
MVGamba: Unify 3D Content Generation as State Space Sequence Modeling
Xuanyu Yi*, Zike Wu*, Qiuhong Shen*, Qingshan Xu, Pan Zhou, Joo-Hwee Lim, Shuicheng Yan, Xinchao Wang, Hanwang Zhang
Conference on Neural Information Processing Systems (NeurIPS 2024)
Paper  /  Bibtex
Vista3D teaser
Vista3D: Unravel the 3D Darkside of a Single Image
Qiuhong Shen, Xingyi Yang, Michael Bi Mi, Xinchao Wang
European Conference on Computer Vision (ECCV 2024)
Project Page  /  Paper  /  Bibtex
FlashSplat teaser
FlashSplat: 2D to 3D Gaussian Splatting Segmentation Solved Optimally
Qiuhong Shen, Xingyi Yang, Xinchao Wang
European Conference on Computer Vision (ECCV 2024), also 3DV 2025 Nectar Track
Paper  /  Bibtex
ULAST teaser
Unsupervised Learning of Accurate Siamese Tracking
Qiuhong Shen, Lei Qiao, Jinyang Guo, Peixia Li, Xin Li, Bo Li, Weitao Feng, Weihao Gan, Wei Wu, Wanli Ouyang
IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2022, Oral)
Paper  /  Bibtex
Anything-3D teaser
Anything-3D: Towards Single-view Anything Reconstruction in the Wild
Qiuhong Shen*, Xingyi Yang*, Xinchao Wang
Tech Report, arXiv  ·  1.6K+ Stars on GitHub
GitHub  /  Paper  /  Bibtex

Academic Service

Conference Reviewer: CVPR / ECCV / ICCV / BMVC / ICLR / NeurIPS / ICML / AAAI

Journal Reviewer: TIP / TVCG / TCSVT / JVCI / CVIU