Yuxin Wang

I am currently a Ph.D. student under the supervision of Prof. Dan Xu, at Hong Kong University of Science and Technology (HKUST). I received my Bachelor's Degree from University of Science and Technology of China (USTC) in 2019. I worked as an intern and researcher at SenseTime from 2019 to 2022, working closely with Dr. Wayne Wu, Dr. Bo Dai and Dr. Qianyi Wu. I worked as a research intern at Tencent since 2025, working closely with Dr. Lei Ke.

My research focuses on 3D manipulation and spatial reasoning, with an emphasis on building structured, editable, and grounded 3D systems.

Email / CV / Google Scholar / Github

News

I am currently seeking internship opportunities for 2025/2026. If you are interested, please feel free to reach out to me.

2026: 2 ECCV papers are accepted.

2025: 1 ICCV paper and 1 ICML paper are accepted.

July. 01, 2024: One paper is accepted by ECCV2024.

Sep. 22, 2023: One paper is accepted by NeurIPS2023.

July. 14, 2023: One paper is accepted by ICCV2023. Thanks to Prof. Dan Xu for his great help.

Feb. 28, 2023: One paper is accepted by CVPR2023.

Research

3D Spatial Reasoning & Geometric Perception
	N3D-VLM: Native 3D Grounding Enables Accurate Spatial Reasoning in Vision-Language Models Yuxin Wang, Lei Ke, Boqiang Zhang, Tianyuan Qu, Hanxun Yu, Zhenpeng Huang, Meng Yu, Dan Xu, Dong Yu arXiv, 2025 project page / arxiv / code
	Unlocking Dense Metric Depth Estimation in VLMs Hanxun Yu^, Xuan Qu^, Yuxin Wang, Jianke Zhu, Lei Ke arXiv, 2026 project page / arxiv / code
	Stream3D-VLM: Online 3D Spatial Understanding with Incremental Geometry Priors Hanxun Yu^, Xuan Qu^, Lei Ke, Boqiang Zhang, Yuxin Wang, Jianke Zhu, Dong Yu ECCV, 2026 project page / arxiv / code
3D Modeling & Manipulation
	F3D-Gaus: Feed-forward 3D-aware Generation on ImageNet with Cycle-Consistent Gaussian Splatting Yuxin Wang, Qianyi Wu, Dan Xu, arXiv, 2025 project page / arxiv / code

	GScream: Learning 3D Geometry and Feature Consistent Gaussian Splatting for Object Removal Yuxin Wang, Qianyi Wu, Guofeng Zhang, Dan Xu ECCV, 2024 project page / arxiv / pdf (camera ready) / supp / code
	UDC-NeRF: Learning Unified Decompositional and Compositional NeRF for Editable Novel View Synthesis Yuxin Wang, Wayne Wu, Dan Xu ICCV, 2023 project page / arxiv / code
	One4D: Unified 4D Generation and Reconstruction via Decoupled LoRA Control Zhenxing Mi, Yuxin Wang, Dan Xu ECCV, 2026 project page / arxiv / code
	From One to More: Contextual Part Latents for 3D Generation Shaocong Dong, Lihe Ding, Xiao Chen, Yaokun Li, Yuxin Wang, Yucheng Wang, Qi Wang, Jaehyeok Kim, Chenjian Gao, Zhanpeng Huang, Zibin Wang, Tianfan Xue, Dan Xu ICCV, 2025 project page / arxiv / data / code
3D/4D Datasets & Benchmarks
	OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation Tong Wu, Jiarui Zhang, Xiao Fu, Yuxin Wang, Jiawei Ren, Liang Pan, Wayne Wu, Lei Yang, Jiaqi Wang, Chen Qian, Dahua Lin, Ziwei Liu CVPR, 2023 (Award Candidate: 12/9155) project page / arxiv / data / code
	RenderMe-360: A Large Digital Asset Library and Benchmarks Towards High-fidelity Head Avatars Dongwei Pan, Long Zhuo^, Jingtan Piao^, Huiwen Luo^, Wei Cheng^, Yuxin Wang^, Siming Fan, Shengqi Liu, Lei Yang, Bo Dai, Ziwei Liu, Chen Change Loy, Chen Qian, Wayne Wu, Dahua Lin, Kwan-Yee Lin NeurIPS*, 2023 project page / arxiv / data / code
Book Chapter
	Talking Faces: Audio-to-Video Face Generation Yuxin Wang, Linsen Song, Wayne Wu, Chen Qian, Ran He, Chen Change Loy Handbook of Digital Face Manipulation and Detection, Springer, 2022 project page

Services

Reviewer for Conference: CVPR, ICCV, ICLR, and NeurIPS
Teaching Assistant: Fundamentals of Artificial Intelligence; Introduction to Object-oriented Programming; Deep Perception, Localization, and Planning for Autonomous Vehicles

Source code from Jon Barron, Aljaž Božič, XINTAO, Ekun, and Zhenxing.