Hao Li (Leo Li) Northwestern Polytechnical University lifugan_10027 outlook.com

Biography I am currently a fourth-year (2022-now) Ph.D. student in the School of Automation at Northwestern Polytechnical University (NPU), supervised by Prof. Dingwen Zhang and Prof. Junwei Han (IEEE Fellow). Meanwhile, I am a visiting student at Nanyang Technological University (NTU) since April 2025, supervised by Prof. Ziwei Liu. My research interests lie in 3D Vision, Embodied AI, and Multi-Modal Model. I also join the LongCat Foundation Group, Meituan, Inc. as Research Intern (北斗人才计划). Before that, I worked as a research intern at StepFun Inc., led by Xuanyang Zhang and Dr. Gang Yu. From 2023 to 2024, I worked as a research intern at the Robotcis Team, ByteDance AI Lab, under the mentorship of Minghan Qin. I also interned with the VIS, at Baidu Inc., guided by Dr. Chenming Wu and Jingdong Wang (IEEE Fellow). In 2022 to 2023,I was a research intern at Zhejiang Lab, leading with Prof. Lechao Cheng .

News

[2025/06] STRIDER got accepted by NeurIPS 2025! 🎉
[2025/06] LangScene-X and CityGS-X got accepted by ICCV 2025! 🎉
[2025/05] Step1X-3D released by StepFun! 🎉
[2025/04] Visiting student at NTU, supervised by Prof. Ziwei Liu!
[2025/03] VDG got accepted by IEEE RA-L 2025! 🎉
[2025/02] DGTR got accepted by ICRA 2025! 🎉
[2025/01] Joining AIGC Group, StepFun Inc., led by Xuanyang Zhang and Dr. Gang Yu!
[2024/10] XLD got accepted by 3DV 2025! 🎉
[2024/08] Joining ByteDance AI Lab, led by Minghan Qin!
[2024/08] Invited talk on GAMES Webinar.
[2024/07] GGRt got accepted by ECCV 2024!
[2024/02] GP-NeRF got accepted by CVPR 2024 and selected as Highlight (top 3.8%)! 🎉
[2024/02] LTGC got accepted by CVPR 2024 and selected as Oral (top 0.8%)! 🎉
[2024/01] Invited talk on 3D视觉工坊.
[2023/12] Joining VIS, Baidu, Inc. as Research Intern, led by Dr. Chenming Wu and Jingdong Wang (IEEE Fellow)!
[2023/11] ASDT got accepted by TIP 2024! 🎉
[2023/11] Saliency Prompt got accepted by CVPR 2023! 🎉
[2023/12] Joining Zhejiang Lab as Research Intern, led by Prof. Lechao Cheng!

Publications

	Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assets Weiyu Li, Xuanyang Zhang, Zheng Sun, Di Qi, Hao Li, Weiwei Cheng, Wanggui Cai, Shun Wu, Jie Liu, Ziwei Wang, Gang Yu Tech Report 2025  Home   Paper  Code
	OmniVGGT: Omni-Modality Driven Visual Geometry Grounded Transformer Haoyi Peng†, Hao Li†, Yalun Dai, Yao Lan, Yufei Luo, Tianyu Qi, Zhizheng Zhang, Yuxuan Zhan, Junran Peng, Wu Xu, Ziwei Liu arXiv 2025  Paper
	IGGT: Instance-Grounded Geometry Transformer for Semantic 3D Reconstruction Hao Li, Zhengyu Zou, Fangfu Liu, Xuanyang Zhang, Fangzhou Hong, Yueqi Cao, Yao Lan, Ming Zhang, Gang Yu, Ziwei Liu arXiv 2025  Paper
	From Spatial to Actions: Grounding Vision-Language-Action Model in Spatial Foundation Prior Zhizheng Zhang, Hao Li, Yalun Dai, Ziao Zhu, Lin Zhou, Chen Liu, Dong Wang, Francis E.H. Tay, Shuicheng Chen, Ziwei Liu arXiv 2025  Paper
	STRIDER: Navigation via Instruction-Aligned Structural Decision Space Optimization Diqi He, Xiangyu Gao, Hao Li, Junwei Han, Dingwen Zhang NeurIPS 2025  Paper
	LangScene-X: Reconstruct Generalizable 3D Language-Embedded Scenes with TriMap Video Diffusion Fangfu Liu†, Hao Li†, Junfeng Chi, Hailin Wang, Mingxi Yang, Fangyu Wang, Yachao Duan ICCV 2025  Paper
	CityGS-X: A Scalable Architecture for Efficient and Geometrically Accurate Large-Scale Scene Reconstruction Yuanyuan Gao†, Hao Li†, Jiaqi Chen, Zhengyu Zou, Zhihang Zhong, Dingwen Zhang, Xiao Sun, Junwei Han ICCV 2025  Paper
	CoSurfGS: Collaborative 3D Surface Gaussian Splatting with Distributed Learning for Large Scene Reconstruction Yuanyuan Gao†, Yalun Dai†, Hao Li†, Weicai Ye, Jiaqi Chen, Dingwen Chen, Dingwen Zhang, Tong He, Guofeng Zhang, Junwei Han IJCV 2024  Paper
	DGTR: Distributed Gaussian Turbo-Reconstruction for Sparse-View Vast Scene Hao Li, Yuanyuan Gao, Haoyi Peng, Chenming Wu, Weicai Ye, Yuxuan Zhan, Chen Zhao, Dingwen Zhang, Jingdong Wang, Junwei Han ICRA 2025  Paper
	LangSurf: Language-Embedded Surface Gaussians for 3D Scene Understanding   Hao Li, Minghan Qin#, Zhengyu Zou, Diqi He, Bohan Li, Bingquan Dai, Dingwen Zhang#, Junwei Han arXiv 2024  Home   Paper  Video    Code   Bibtex
	XLD: A Cross-Lane Dataset for Benchmarking Novel Driving View Synthesis Hao Li, Chenming Wu, Chen Zhao, Haocheng Feng, Errui Ding, Dingwe Zhang#, Jingdong Wang 3DV 2025  Home   Paper   Code
	VDG: Vision-Only Dynamic Gaussian for Driving Simulation Hao Li, Jingfeng Li, Dingwen Zhang, Chenming Wu, Jieqi Shi, Chen Zhao, Haocheng Feng, Errui Ding, Jingdong Wang, Junwei Han IEEE RA-L 2025  Home   Paper
	GGRt: Towards Pose-free Generalizable 3D Gaussian Splatting in Real-time Hao Li, Yuanyuan Gao, Chenming Wu, Dingwen Zhang, Yalun Dai, Chen Zhao, Haocheng Feng, Errui Ding, Jingdong Wang, Junwei Han ECCV 2024  Home   Paper  Code
	GP-NeRF: Generalized Perception NeRF for Context-Aware 3D Scene Understanding Hao Li, Dingwen Zhang, Yalun Dai, Nian Liu, Lechao Cheng, Jingfeng, Jingdong Wang, Junwei Han CVPR 2024 - Highlight  Home   Paper  Code
	LTGC: Long-Tail Recognition via Leveraging LLMs-driven Generated Content Qihao Zhao†, Yalun Dai†, Hao Li†, Wei Hu, Fan Zhang, Jun Liu CVPR 2024 - Oral Presentation  Home   Paper  Code
	Weakly Supervised Semantic Segmentation via Alternate Self-Dual Teaching Hao Li, Dingwen Zhang, Chaowei Fang, Lechao Cheng, Mingming Cheng, Junwei Han IEEE TIP 2024  Home   Code
	Unsupervised Pre-training with Language-Vision Prompts for Low-Data Instance Segmentation Dingwen Zhang, Hao Li, Diqi He, Nian Liu, Lechao Cheng, Jingdong Wang, Junwei Han IEEE TPAMI 2024  Paper
	Boosting low-data instance segmentation by unsupervised pre-training with saliency prompt Hao Li, Dingwen Zhang, Nian Liu, Lechao Cheng, Yalun Dai, Xinggang, Junwei Han CVPR 2023  Home

Talks

可泛化3DGS的现状和未来 (GAMES Webinar)

可泛化语义NeRF (3D视觉工坊)

Honors and Awards

Outstanding Students (First Grade) in Northwestern Polytechnical University, 2024.

Outstanding Interns in Baidu Inc., 2023.

2nd in International Algorithm Case Competition, 2022.

Finalist Winner (2%) in International Mathematical Contest in Modeling (MCM), 2021.