Xianglong He

hxl23 AT mails.tsinghua.edu.cn

I'm currently a final-year M.S. student at SIGS, Tsinghua University, advised by Prof. Chun Yuan. I'm now interested in 3D Generation, Video Generation, and MLLM.

Before that, I received my B.S. degree in Computer Science and Technology from Ocean University of China in 2023. I had an unforgettable research experience on adversarial attacks with Prof. Yuezun Li. Additionally, I was the former leader of Blue-Whale CTF (Capture The Flag) Team at Security Lab@OUC, focusing on Cryptanalysis.

I am actively looking for Ph.D. positions (2026 fall).

Scholar / CV (2508)

Publications

	Matrix-Game 2.0: An Open-Source, Real-Time, and Streaming Interactive World Model Xianglong He, Chunli Peng, Zexiang Liu, Boyang Wang†, ..., Yang Liu‡ Eric Li‡, Yahui Zhou Tech Report, 2025 Project Page / Tech Report / Code
	ShapeGen: Towards High-Quality 3D Shape Synthesis Yangguang Li, Xianglong He*, Zi-Xin Zou, Zexiang Liu, Wanli Ouyang, Ding Liang, Yan-Pei Cao Siggraph Asia*, 2025 On Camera-Ready
	DeepVerse: 4D Autoregressive Video Generation as a World Model Junyi Chen, Haoyi Zhu, Xianglong He, ..., Tong He arXiv, 2025 Project Page / arXiv / Code
	(TripoSF) SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modeling Xianglong He, Zi-Xin Zou, Chia-Hao Chen, Yuan-Chen Guo, Ding Liang, Chun Yuan, Wanli Ouyang, Yan-Pei Cao, Yangguang Li ICCV, 2025 (Oral, 64/11152) Project Page / arXiv / Code
	MeshCraft: Exploring Efficient and Controllable Mesh Generation with Flow-based DiTs Xianglong He, Junyi Chen, Di Huang, Zexiang Liu, Xiaoshui Huang, Wanli Ouyang, Chun Yuan, Yangguang Li arXiv, 2025 arXiv / Code
	NOVA3D: Normal Aligned Video Diffusion Model for Single Image to 3D Generation Yuxiao Yang, ..., Xianglong He, ..., Haoqian Wang ICME, 2025 (Best Paper Candidate, 15/3737) arXiv
	GVGEN: Text-to-3D Generation with Volumetric Representation Xianglong He, Junyi Chen, Sida Peng, Di Huang, Yangguang Li, Xiaoshui Huang, Chun Yuan, Wanli Ouyang, Tong He ECCV, 2024 Project Page / arXiv / Code
	PonderV2: Pave the Way for 3D Foundataion Model with A Universal Pre-training Paradigm Haoyi Zhu, Honghui Yang, Xiaoyang Wu, Di Huang, Sha Zhang, Xianglong He, Tong He, Hengshuang Zhao, Chunhua Shen, Yu Qiao, Wanli Ouyang TPAMI, 2025 arXiv / Code
	Improving transferable adversarial attack via feature-momentum Xianglong He, Yuezun Li, Haipeng Qu, Junyu Dong Computers & Security, 128, 2023 Code [Tensorflow] / Unofficial Code [Pytorch]

Experiences

	2025 - 2025 Algorithm Intern Skywork host by Eric Li, and Yang Liu. Topic: World Model.
	2024 - 2025 Algorithm Intern VAST host by Yangguang Li, and Yan-Pei Cao, working closely with Zi-Xin Zou. Topic: Mesh Generation on Tripo 3.0 Exploration.
	2023 - 2024 Research Intern GVLAB @ Shanghai AI Laboratory host by Xiaoshui Huang and Wanli Ouyang, working closely with Junyi Chen, Di Huang, Yangguang Li and Tong He. Topic: 3D Generation, and 3D Reconstruction.
	2021 - 2022 Research Assistant VAS Group @ Ocean University of China host by Prof. Yuezun Li. Topic: Adversarial Attack.

Services

Reviewers: Siggraph Asia 2025, TCSVT, MIR.

Selected Honors & Awards

The CCF Elite Collegiate Award

2021

National College Student Information Security Contest, First Prize (5/2136)

2021

China Graduate Contest on Cyber Security, Second Prize

2022

Lanqiao Programming Designing Contest (Python A Group), Second Prize

2022

Group Programming Ladder Tournament, Personal Second Prize

2021

Lanqiao Programming Designing Contest (C++ A Group), Second Prize

2020

National Crypto-Math Challenge, Third Prize

2021

Global Fincryptography Contest, Third Prize

2020

Qiangwangbei National Cyber Security Challenge Quals, Third Prize

2020

Tencent RisingStar CTF (TCTF), Rank 5

2021

Misc

Love CTF (Away From Keyboard):
Made some cherished friends there;
Exploited & Provided challenges for CTF events as the member of international teams (W&M, Straw Hat, Tea Deliverers, etc.);

Enjoy Exploring and Creating Flavor:: Liquor, Meal, Dessert, and Perfume.