Xuanyu Yi 易炫宇

Ph.D. Candidate @ Nanyang Technological University

Address: 50 Nanyang Ave, 639798, Singapore
Email: xuanyu001@e.ntu.edu.sg or xuanyucver@gmail.com

Google Scholar

Semantic Scholar

Github

Biography [back top]

I am currently a fourth-year Ph.D. student in MreaL lab @ NTU, advised by Prof. Hanwang Zhang. I am also served as a research scholar in I²R, A^*STAR, advised by Prof. Lim Joo Hwee . Before that, I received my Bachelor's degree from Tsinghua University, supervised by Prof. Ji Wu and closely collabrated with Prof. Yirong Wu and Prof. Demin Han. The outline of my experience is as follows:

01/2024 -- 12/2024: Research Intern, 2050 Research, Skywork AI, Singapore.
08/2023 -- 12/2023: Research Intern, SEA AI Lab, Singapore.
09/2021 -- Present: Ph.D. Student in Computer Science, Nanyang Technological University, Singapore.
06/2020 -- 11/2020: B.S. in Computer Science, Exchange Program @ University of Southern California, Los Angeles, America.
08/2017 -- 07/2021: B.S. in Electronic Engineering, Tsinghua University, Beijng, China.

My research interests include representation learning, generative model, multi-modal LLM and 3D Vision. More recently, I focus on the following aspects:

3D understanding, reconstruction, generation, editting and simulation.
3DGS-based or physics-based video generation model.
World Foundation Model.
MLLM with Spatial Intelligence.

I’m graduating around Jul. 2025 and open to employment opportunities for a Research Scientist/Engineer position starting from 2025 summer in Singapore, Beijing or Shanghai.

Latest News [back top]

09/2024: One paper was accepted by NeurIPS 2024.
07/2024: Two paper were accepted by ECCV 2024.
02/2024: Two paper were accepted by CVPR 2024.
09/2023: One paper was accepted by ICCV 2023.
10/2022: One paper was accepted by ECCV 2022 as oral presentation.

Publication [back top]

* Equal contribution.

Conference

07	Xuanyu Yi, Zike Wu, Qiuhong Shen, Qingshan Xu, Pan Zhou, Joo-Hwee Lim, Shuicheng Yan, Xinchao Wang, Hanwang Zhang MVGamba: Unify 3D Content Generation as State Space Sequence Modeling Conference on Neural Information Processing Systems (NeurIPS), 2024 [Paper] [Code]
06	Yuxuan Wang, Xuanyu Yi, Zike Wu, Na Zhao, Long Chen, Hanwang Zhang View-Consistent 3D Editing with Gaussian Splatting European Conference on Computer Vision (ECCV), 2024 [Paper] [Code]
05	Qingshan Xu, Xuanyu Yi, Jianyao Xu, Wenbing Tao, Yew-Soon Ong, Hanwang Zhang Few-shot NeRF by Adaptive Rendering Loss Regularization European Conference on Computer Vision (ECCV), 2024 [Paper] [Code]
04	Xuanyu Yi, Zike Wu, Qingshan Xu, Pan Zhou, Joo-Hwee Lim, Hanwang Zhang Diffusion time-step curriculum for one image to 3d generation IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024 [Paper] [Code]
03	Zike Wu, Pan Zhou, Xuanyu Yi, Xiaoding Yuan, Hanwang Zhang Consistent3d: Towards consistent high-fidelity text-to-3d generation with deterministic sampling prior IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024 [Paper] [Code]
02	Xuanyu Yi, Jiajun Deng, Qianru Sun, Xian-Sheng Hua, Joo-Hwee Lim, Hanwang Zhang Invariant training 2d-3d joint hard samples for few-shot point cloud recognition IEEE/CVF International Conference on Computer Vision (ICCV), 2023 [Paper] [Code]
01	Xuanyu Yi, Kaihua Tang, Xian-Sheng Hua, Joo-Hwee Lim, Hanwang Zhang Identifying hard noise in long-tailed sample distribution European Conference on Computer Vision (ECCV), 2022 [Oral Presentation, 2.7% acceptance rate] [Paper] [Code]

Preprint

05	Qiuhong Shen, Xuanyu Yi, Mingbao Lin, Hanwang Zhang, Shuicheng Yan, Xinchao Wang Seeing World Dynamics in a Nutshell arXiv preprint arXiv:2502.03465 (Under Review) [Paper] [Code]
04	Yuxuan Wang, Xuanyu Yi, Haohan Weng, Qingshan Xu, Xiaokang Wei, Xianghui Yang, Chunchao Guo, Long Chen, Hanwang Zhang Nautilus: Locality-aware Autoencoder for Scalable Mesh Generation* arXiv preprint arXiv:2501.14317 (Under Review) [Paper] [Code]
03	Qingshan Xu, Jiequan Cui, Xuanyu Yi, Yuxuan Wang, Yuan Zhou, Yew-Soon Ong, Hanwang Zhang Pushing Rendering Boundaries: Hard Gaussian Splatting arXiv preprint arXiv:2412.04826 (Under Review) [Paper]
02	Qiuhong Shen, Zike Wu, Xuanyu Yi, Pan Zhou, Hanwang Zhang, Shuicheng Yan, Xinchao Wang Gamba: Marry gaussian splatting with mamba for single view 3d reconstruction* arXiv preprint arXiv:2406.06367 (Under Review) [Paper] [Code]
01	Qingshan Xu, Wanjuan Su, Xinyao Liao, Xuanyu Yi, Jiequan Cui, Wenbing Tao, Yew-Soon Ong, Shuicheng Yan, Hanwang Zhang Geo-3DGS: Multi-view Geometry Consistency for 3D Gaussian Splatting and Surface Reconstruction OpenReview preprint (Under Review) [Paper] [Code Coming]

Journal

01	Xuanyu Yi, Bochun Wang, Jiandong Gao, Yanru Li, Wen Xu, Ji Wu, Demin Han Real-time prediction of upcoming respiratory events via machine learning using snoring sound signal Journal of Clinical Sleep Medicine [Paper]

Patent

A Real-Time Predictive Method for Sleep Apnea and Hypoventilation Based on Snoring
Chinese Patent No.[CN202110620741.X], granted [2021-08-24].

Professional Activities [back top]

Conference Reviewer
- IEEE/CVF Computer Vision and Pattern Recognition (CVPR), 2023, 2024,2025.
- European Conference on Computer Vision (ECCV), 2022, 2024.
- Conference on Neural Information Processing Systems (NeurIPS), 2024.
- AAAI Conference on Artificial Intelligence (AAAI), 2023.
- International Joint Conference on Artificial Intelligence (IJCAI), 2023.
- The International Conference on Machine Learning (ICML), 2025.
- The International Conference on Learning Representations (ICLR), 2025.
Journal Reviewer
- IEEE Transactions on Multimedia

Honors & Awards [back top]

A^*STAR Merit Award, 2022.
Singapore International Graduate Award, 2021.
Silver Prize, Tsinghua University Rural Education Support, 2018.
Tang Junyuan Scholarship Award，2017.
Tsinghua University Leading Talent Program，2017.