Autonomous Driving
Efficient lane perception, monocular 3D detection, and multi-view BEV representation.
Zequn Qin 秦泽群
Researcher · Ph.D. Advisor
School of Software Technology, Zhejiang University
I work at the intersection of autonomous driving, world models, and embodied intelligence—building learning systems that perceive, reason, and act in complex environments.
3.6K+Google Scholar citations
14h-index
3K+GitHub stars
50K+Open model downloads
Research Interests
My research has evolved from efficient visual perception for autonomous systems toward general agents that understand and interact with both digital and physical worlds.
World Models
Learning predictive representations that connect perception, dynamics, and decision-making.
Embodied Intelligence
Generalist agents that reason and act across GUI environments and the 3D physical world.
Open-source Projects
View all repositories
UniFusion
A unified spatial-temporal fusion formulation for bird’s-eye-view representation, supporting long-range fusion and learnable temporal weighting.
Industry Collaborations
Embodied Flight
Combining end-to-end trajectory planning and control with world-model pretraining to enable embodied autonomous flight in complex industrial environments, with applications in industrial inspection and security.
Publications
19 publicationsCitation profile
All Patches Matter, More Patches Better: Enhance AI-Generated Image Detection via Panoptic Patch Learning
NEWZ. Yang, R. Chen, Z. Yan, K. Zhang, X. Fu, S. Wu, X. Shu, T. Yao, S. Ding, et al.
ICLR
OmniActor: A Generalist GUI and Embodied Agent for 2D&3D Worlds
NEWL. Yang, Z. Zeng, Y. Zhong, J. Huang, L. Zheng, L. Chen, H. Qiu, Z. Qin, L. Ma, X. Li
ICLR
MultiCrafter: High-Fidelity Multi-Subject Generation via Disentangled Attention and Identity-Aware Preference Alignment
NEWT. Wu, Y. Jiang, Y. Lu, Z. Wang, Z. Huang, Z. Qin, X. Li
CVPR
Long-Tailed Distribution-Aware Router for Mixture-of-Experts in Large Vision-Language Model
C. Cai, L. Yang, M. Weng, X. Li, Z. Qin, X. Li
arXiv:2507.01351
HeightFormer: Explicit Height Modeling without Extra Data for Camera-Only 3D Object Detection in Bird’s-Eye-View
Y. Wu, R. Li, Z. Qin, X. Zhao, X. Li
IEEE TIP
UniFusion: Unified Multi-View Fusion Transformer for Spatial-Temporal Representation in Bird’s-Eye-View
Z. Qin, J. Chen, C. Chen, X. Chen, X. Li
A Large-Scale Synthetic Gait Dataset Towards In-the-Wild Simulation and Comparison Study
P. Zhang, H. Dou, W. Zhang, Y. Zhao, Z. Qin, D. Hu, Y. Fang, X. Li
ACM TOMM
Ultra Fast Deep Lane Detection with Hybrid Anchor Driven Ordinal Classification
Z. Qin, P. Zhang, X. Li
MonoGround: Detecting Monocular 3D Objects from the Ground
Z. Qin, X. Li
GaitMPL: Gait Recognition with Memory-Augmented Progressive Learning
H. Dou, P. Zhang, Y. Zhao, L. Dong, Z. Qin, X. Li
IEEE TIP
FcaNet: Frequency Channel Attention Networks
Z. Qin, P. Zhang, F. Wu, X. Li
VersatileGait: A Large-Scale Synthetic Gait Dataset with Fine-Grained Attributes and Complicated Scenarios
H. Dou, W. Zhang, P. Zhang, Y. Zhao, S. Li, Z. Qin, F. Wu, L. Dong, X. Li
arXiv:2101.01394
CoDiNet: Path Distribution Modeling with Consistency and Diversity for Dynamic Routing
H. Wang, Z. Qin, S. Li, X. Li
IEEE TPAMI
RDI-Net: Relational Dynamic Inference Networks
H. Wang, S. Li, S. Su, Z. Qin, X. Li
ICCV
Ultra Fast Structure-Aware Deep Lane Detection
Z. Qin, H. Wang, X. Li
Multitask Attention Network for Lane Detection and Fitting
Q. Wang, T. Han, Z. Qin, J. Gao, X. Li
IEEE TNNLS
C2DNDA: A Deep Framework for Nonlinear Dimensionality Reduction
Q. Wang, Z. Qin, F. Nie, X. Li
IEEE TIE
Spectral Embedded Adaptive Neighbors Clustering
Q. Wang, Z. Qin, F. Nie, X. Li
IEEE TNNLS
Convolutional 2D LDA for Nonlinear Dimensionality Reduction
Q. Wang, Z. Qin, F. Nie, Y. Yuan
IJCAI
Selected Honors
- Stanford University's World's Top 2% Scientists list
- ACM Hangzhou Rising Star Award
- CSIG Doctoral Dissertation Incentive Program · National selection
- Outstanding Graduate of Zhejiang University and Zhejiang Province
Contact
I am continuously looking for self-motivated students who are curious about artificial intelligence. If our research interests align, I'd be glad to hear from you.
长期招收对人工智能抱有热情、有好奇心、自驱力强的同学。
qinzequn@zju.edu.cn