I am a second-year Ph.D. student at the School of Electronic Information and Communications, Huazhong University of Science and Technology. I am advised by Prof. Wenyu Liu and Prof. Xinggang Wang, and work with the HUST Vision Lab.
I received my B.Eng. degree in Microelectronics Science and Engineering from HUST in 2023. My research interests include autonomous driving, unified model and agentic system.
Publications
AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design
Yaxin Luo, Haobin Jiang, Jialv Zou, Xu Huang, Wenhao Yan, Haodong Li, Zhengrong Yue, Jing Li, Xiaofu Chen, Xiaohan Zhao, Jiacheng Liu, Jiacheng Cui, Zhiqiang Shen, Xiaotong Li
arXiv preprint, 2026
A meta-harness optimizer that recursively improves long-horizon agentic design systems through rollout feedback.
VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System
Haodong Li, Tianfei Ren, Xiaoxiao Ma, Chunmei Qing, Zhen Fang, Sipeng He, Ziyu Guo, Haoyu Wu, Juanxi Tian, Yihang Zou, Ruichuan An, Dongzhi Jiang, Boxue Yang, Ji Xie, Xu Huang, Wenhao Yan, Jialv Zou, Zhengrong Yue, Yaxin Luo, Xiaotong Li, Yuzhu Wang, Junyan Ye, Jinjing Zhao, Zehui Chen, Lin Chen, Renye Yan, Feng Zhao, Pheng-Ann Heng
arXiv preprint, 2026
An agentic dual-engine framework that uses executable Blender code as process-level chain of thought for physically consistent video generation.
Senna-2: Aligning VLM and End-to-End Driving Policy for Consistent Decision Making and Planning
Yuehao Song, Shaoyu Chen, Hao Gao, Yifan Zhu, Weixiang Yue, Jialv Zou, Bo Jiang, Zihao Lu, Yu Wang, Qian Zhang, Xinggang Wang
arXiv preprint, 2026
A VLM-E2E driving policy that aligns high-level decisions with trajectory planning.
ResAD: Normalized Residual Trajectory Modeling for End-to-End Autonomous Driving
Zhiyu Zheng, Shaoyu Chen, Haoran Yin, Xinbang Zhang, Jialv Zou, Xinggang Wang, Qian Zhang, Lefei Zhang
IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2026
Normalized residual trajectory modeling for robust end-to-end autonomous driving.
OmniMamba: Efficient and Unified Multimodal Understanding and Generation via State Space Models
Jialv Zou, Bencheng Liao, Qian Zhang, Wenyu Liu, Xinggang Wang
European Conference on Computer Vision, 2026
An efficient state-space-model framework for unified multimodal understanding and generation.
DiffusionDriveV2: Reinforcement Learning-Constrained Truncated Diffusion Modeling in End-to-End Autonomous Driving
Jialv Zou, Shaoyu Chen, Bencheng Liao, Zhiyu Zheng, Yuehao Song, Lefei Zhang, Qian Zhang, Wenyu Liu, Xinggang Wang
arXiv preprint, 2025
End-to-end autonomous driving with truncated diffusion modeling constrained by reinforcement learning.
MIM4D: Masked Modeling with Multi-View Video for Autonomous Driving Representation Learning
Jialv Zou*, Bencheng Liao*, Qian Zhang, Wenyu Liu, Xinggang Wang (* denotes equal contribution)
International Journal of Computer Vision, 2025
Masked modeling with multi-view video for learning autonomous-driving representations.
Education
- Sep. 2025 – Present, Ph.D. student, School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China.
- Sep. 2023 – Jun. 2025, M.S., School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China.
- Sep. 2019 – Jun. 2023, B.Eng., Microelectronics Science and Engineering, Huazhong University of Science and Technology, Wuhan, China.
Industry Experience
- Dec. 2025 – Present, Research Intern, LongCat Group, Meituan, Beijing, China. Researching unified models. Working with Xiaotong Li.
- Nov. 2022 – Dec. 2025, Research Intern, Basic Algorithms Department, Horizon Robotics, Beijing, China. Working with Dr. Qian Zhang and Dr. Chang Huang.
Honors and Awards
- 2025, China National Scholarship for Master Students.
Competition
- 2023, National First Prize, 18th “Challenge Cup” National College Students Extracurricular Academic Science and Technology Works Competition.
- 2022, National First Prize, RoboMaster.
- 2022, National Second Prize, 5th National College Embedded Chip and System Design Competition.
- 2021, National First Prize, 9th National University Students’ Opt-Sci-Tech Competition. Code and video.
- 2021, National Second Prize, RoboMaster.
Academic Services
- Reviewer for NeurIPS, CVPR, ECCV, and IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI).