Xiaolu Liu (刘晓璐)

I am currently a fourth-year Ph.D. student at the College of Computer Science and Technology, Zhejiang University, advised by Prof. Jianke Zhu. Prior to this, I received my B.Eng. in Electronics and Computer Engineering from Zhejiang University through the ZJU-UIUC Joint Program (ZJUI). I am also a visiting Ph.D. student at the School of Computing (SoC), NUS, advised by Prof. Angela Yao.

My research interests lie in World Model, Autonomous Driving, and 3D Generation. Various forms of academic collaboration and discussion are welcome. Feel free to reach out!

Email / Google Scholar / GitHub / CV

News

[2026.03] We released the preprint of DynFlowDrive, a dynamic latent world modeling framework for autonomous driving.
[2026.01] Interp3D was accepted to ICLR 2026, which focuses on correspondence-aware interpolation for generative texture 3D morphing.
[2025.06] UIGenMap was accepted to CVPR 2025, designed for Vectorized HD Map Construction.

Preprints & Publications

[arXiv preprint] DynFlowDrive: Flow-Based Dynamic World Modeling for Autonomous Driving Paper / Code Xiaolu Liu, Yicong Li, Song Wang, Junbo Chen, Angela Yao, Jianke Zhu.
[arXiv preprint] RelaxFlow: Text-Driven Amodal 3D Generation Paper / Code Jiayin Zhu, Guoji Fu, Xiaolu Liu, Qiyuan He, Yicong Li, Angela Yao.
[ICLR 2026] Interp3D: Correspondence-aware Interpolation for Generative Texture 3D Morphing Paper / Code Xiaolu Liu, Yicong Li, Qiyuan He, Jiayin Zhu, Wei Ji, Angela Yao, Jianke Zhu.
[CVPR 2025] Uncertainty-Instructed Structure Injection for Generalizable HD Map Construction Paper / Code Xiaolu Liu*, Ruizi Yang*, Song Wang, Wentong Li, Junbo Chen, Jianke Zhu.
[CVPR 2024] MGMap: Mask-guided Learning for Online Vectorized HD Map Construction Paper / Code Xiaolu Liu, Song Wang, Wentong Li, Junbo Chen, Jianke Zhu.
[CVPR 2025] PointLoRA: Low-Rank Adaptation with Token Selection for Point Cloud Learning Paper / Code Song Wang, Xiaolu Liu, Lingdong Kong, ... Jianke Zhu, Xinchao Wang.
[IROS 2025] MambaMap: Online Vectorized HD Map Construction using State Space Model Paper / Code Ruizi Yang, Xiaolu Liu, Jianke Zhu.
[CVPR 2024] Not All Voxels Are Equal: Hardness-Aware Semantic Scene Completion with Self-Distillation Paper / Code Song Wang, Jiawei Yu, Wentong Li, Wenyu Liu, Xiaolu Liu, Junbo Chen, Jianke Zhu.
[CVPR 2023] Lidar2map: In defense of lidar-based semantic map construction using online camera distillation Paper / Code Song Wang, Wentong Li, Wenyu Liu, Xiaolu Liu, Jianke Zhu.

Internship

Udeer.AI

Research Intern | 2025.07 - 2026.04 | Remote

Focus on end-to-end autonomous driving and world models.

Education

Ph.D. @ Zhejiang University, 2022-2027 (expected)

Advisor: Prof. Jianke Zhu
B.Eng. @ Zhejiang University, 2018-2022

ZJU-UIUC Joint Program (ZJUI) | GPA: 3.87/4.0 | Rank: 6/51

Honors and Awards

CSC National Scholarship for Overseas Study (2025)
Outstanding Graduate Student, Zhejiang University (2023 - 2025)
Five-Good Graduate Student, Zhejiang University (2023 - 2025)
Outstanding Graduate, Zhejiang University (Top 5%) (2022)
High Honor Graduate & Dean's List, UIUC (2019 - 2022)
Second-Class Scholarship, Zhejiang University (2021)

Academic Services

Journal Reviewer: T-ITS, T-CSVT, T-IV
Conference Reviewer: ICML 2026, CVPR 2024/2025, ICCV 2025, IJCAI 2025, NeurIPS 2025, IROS 2025
Teaching Assistant: FDS23/FDS25, ECE374, Math213