Zebin Xing - Homepage

Zebin Xing (邢泽斌)

I am currently a second-year master's student at the Institute of Automation, Chinese Academy of Sciences (CASIA). I conduct my research within the group of Prof. Dongbin Zhao, under the supervision of Prof. Qichao Zhang. My research interests primarily focus on Embodied AI and Autonomous Driving.

I earned my bachelor's degree from Beijing University of Posts and Telecommunications (BUPT). During my time at BUPT, I interned under the guidance of Prof. Shunnan Guo.

I have maintained close collaborations with industry partners, including Horizon Robotics and ChangAn Automobile. At Horizon Robotics, I was very honored to collaborate with Dr. Wei Yin. I also had the great honor of collaborating with Prof. Xiaoxiao Long from Nanjing University.

Email / CV / Google Scholar / GitHub /

Research

My long-term goal is to build Physical AI that understands the physical world. Such intelligence should integrate visual and tactile inputs to comprehend properties like distance and mass, enabling reasonable control and planning. I am open to any related research directions and currently focus on Embodied AI and Autonomous Driving. My main interests include World Models, Structural Modeling, and Visuotactile Fusion.

Publications

(^†: corresponding author; ^*: equal contribution)

	PokéVLA: Empowering Pocket-Sized Vision-Language-Action Model with Comprehensive World Knowledge Guidance Yupeng Zheng^, Xiang Li^, Songen Gu^, Yuhang Zheng, Shuai Tian, Weize Li, Lingbo Wang, Senyu Fei, Pengfei Li, Yinfeng Gao, Zebin Xing, Yilun Chen, Qichao Zhang, Haoran Li, Wenchao Ding^†. TRO, In Submission, 2026* [Homepage] A lightweight vision-language-action foundation model that integrates comprehensive world knowledge into robotic manipulation through novel two-stage training with goal-aware semantic learning.
	DriveVLA-M0: Failure-Aware Memory Augmentation for Autonomous Driving Zebin Xing, Yupeng Zheng, Qiang Chen, Linbo Wang, Yichen Zhang, Pengxuan Yang, Junli Wang, Deheng Qian, Xiaoqing Ye, Junyu Han, Yifeng Pan, Qichao Zhang^†, Dongbin Zhao *ACM MM, In submission, 2026* A failure-aware memory augmentation framework that introduces structural retrieval into VLA driving.
	Mimir: Hierarchical Goal-Driven Diffusion with Uncertainty Propagation for End-to-End Autonomous Driving Zebin Xing, Yupeng Zheng, Qichao Zhang^†, Zhixing Ding, Pengxuan Yang, Songen Gu, Zhongpu Xia, Dongbin Zhao *RA-L, 2025* [arXiv] [Code] A hierarchical dual-system framework that propagates goal uncertainty through Laplace distribution to generate robust trajectories with accelerated multi-rate guidance.
	TrajMoE: Scene-Adaptive Trajectory Planning with Mixture of Experts and Reinforcement Learning ^{Zebin Xing}, Pengxuan Yang, Linbo Wang, Yichen Zhang, Yiming Hu, Yupeng Zheng, Junli Wang, Yinfeng Gao, Guang Li, Kun Ma, Long Cheng, Zhongpu Xia, Qichao Zhang, Hangjun Ye, Dongbin Zhao *CSIS-IAC 2026 (Oral)🥉3rd of ICCV NAVSIM Challenge* [axiv] A scene-adaptive trajectory planning paradigm that dynamically selects trajectory priors via Mixture of Experts and refines scoring through reinforcement learning.
	World4Drive: End-to-End Autonomous Driving via Intention-aware Physical Latent World Model Yupeng Zheng, Pengxuan Yang, Zebin Xing, Qichao Zhang^†, Yuhang Zheng, Yinfeng Gao, Pengfei Li, Teng Zhang, Zhongpu Xia, Peng Jia, Dongbin Zhao *ICCV, 2025* [arXiv] [Code] An intention-aware physical latent world model that enables perception annotation-free end-to-end driving through vision foundation models and self-supervised world modeling.
	UncAD: Towards Safe End-to-end Autonomous Driving via Online Map Uncertainty Pengxuan Yang, Yupeng Zheng, Qichao Zhang^†, Kefei Zhu, Zebin Xing, Qiao Lin, Yunfu Liu, ZHIguo Su, Dongbin Zhao, *ICRA 2025* [arXiv] [Code] A safety-centric planning paradigm that incorporates online map uncertainty estimation into motion prediction with uncertainty-collision-aware trajectory selection.
	GoalFlow: Goal-Driven Flow Matching for Multimodal Trajectories Generation in End-to-End Autonomous Driving Zebin Xing^, Xingyu Zhang^, Yang Hu, Bo Jiang, Tong He, Qian Zhang, Xiaoxiao Long, Wei Yin^† *CVPR, 2025* [arXiv] [Homepage] [Code] A goal-driven flow matching approach that constrains multimodal trajectory generation through scene-aware goal scoring for efficient flow matching-based planning.
	OccRWKV: Rethinking Efficient 3D Semantic Occupancy Prediction with Linear Complexity Junming Wang, Wei Yin^, Xiaoxiao Long^†, Xingyu Zhang, Zebin Xing, Xiaoyang Guo, Qian Zhang, ICRA, 2025* [arXiv] [HomePage] [Code] An efficient 3D semantic occupancy network leveraging linear-complexity RWKV architecture with domain-specific blocks for real-time geometric and semantic understanding.
	ComDrive: Comfort-Oriented End-to-End Autonomous Driving Junming Wang, Xingyu Zhang, Zebin Xing, Songen Gu, Xiaoyang Guo, Yang Hu, Ziying Song, Qian Zhang, Xiaoxiao Long, Wei Yin^† *IROS, 2025* [arXiv] [HomePage] [Code] The first comfort-oriented end-to-end driving framework that generates temporally consistent trajectories through conditional diffusion and dual-stream adaptive scoring.
	Planagent: A multi-modal large language agent for closed-loop vehicle motion planning Yupeng Zheng^, Zebin Xing^, Qichao Zhang^†, Bu Jin, Pengfei Li, Yuhang Zheng, Zhongpu Xia, Kun Zhan, Xianpeng Lang, Yaran Chen, Dongbin Zhao *TCDS, 2025* [arXiv] [Code] The first multi-modal large language model agent for closed-loop planning that introduces hierarchical reasoning and self-reflection into autonomous driving systems.