🙋 About Me

I am currently a second-year master’s student at the School of Artificial Intelligeence and Automation (AIA), Huazhong Univerversity of Science and Technology (HUST). I was conferred the Bachelor’s degree by AIA in June 2024.

Since March 2025, I have been a research intern at the Institute for AI Industry Research (AIR), Tsinghua University, under the supervision of Yan Wang. Since July 2025, I have been an intern at the Autonomous Driving and Robotics Department of Xiaomi EV, supervised by Long Chen and Yan Wang.

My research interests include multimodal large language models (MLLM), reinforcement learning, world models, and their applications in end-to-end autonomous driving. Looking ahead, I plan to shift toward general multimodal understanding and generation. I welcome discussions and potential collaborations.

💖 Research Interests

• Multi-Modal Large Language Model
• Reinforcement Learning
• E2E Autonomous Driving

🔥 News

• 2026.02   We release the paper of DriveFine that investigates dLLM+RL with refinement for AD.
• 2026.01   We release the paper and code of SparseOccVLA that effectively integrates occupancy with VLMs via sparse queries.
• 2025.10   We release the paper and code of SparseWorld, an efficient occupancy world model powered by sparse queries.
• 2025.11:  🎉🎉 One paper accepted by AAAI2026!
• 2025.02:  🎉🎉 Two of our papers are accepted by CVPR2025!

📝 Publications

arXiv 2026

DriveFine: Refining-Augmented Masked Diffusion VLA for Precise and Robust Driving

Chenxu Dang, Sining Ang, Yongkang Li, Haochen Tian, Jie Wang, Guang Li, Hangjun Ye, Jie Ma, Long Chen, Yan Wang

Paper Code

arXiv 2026

SparseOccVLA: Bridging Occupancy and Vision-Language Models via Sparse Queries for Unified 4D Scene Understanding and Planning

Chenxu Dang, Jie Wang, Guang Li, Zhiwen Hou, Zihan You, Hangjun Ye, Jie Ma, Long Chen, Yan Wang

Paper Code Project

AAAI 2026

SparseWorld: A Flexible, Adaptive, and Efficient 4D Occupancy World Model Powered by Sparse and Dynamic Queries

Chenxu Dang, Haiyan Liu, Jason Bao, Pei An, Xinyue Tang, PanAn, Jie Ma, Bingchuan Sun, Yan Wang*

Paper Code

CVPR 2025

FASTer: Focal Token Acquiring-and-Scaling Transformer for Long-term 3D Object Detection

Chenxu Dang, Zaipeng Duan, Pei An, Xinmin Zhang, Xuzhong Hu, Jie Ma*

Paper Code

CVPR 2025

SDGOCC: Semantic and Depth-Guided Bird’s-Eye View Transformation for 3D Multimodal Occupancy Prediction

Zaipeng Duan, Chenxu Dang, Pei An, Xuzhong Hu, Jie Zhan, Jie Ma*

Paper Code

arXiv 2026

From Representational Complementarity to Dual Systems: Synergizing VLM and Vision-Only Backbones for End-to-End Driving

Sining Ang, Yuguang Yang, Chenxu Dang, Canyu Chen, Cheng Chi, Haiyan Liu, Xuanyao Mao, Jason Bao, Xuliang, Bingchuan Sun, Yan Wang*

Paper

🎖 Honors and Awards

• 2024.10 First Class Scholarship
• 2022.11 FiberHome Scholarship
• 2022.10 Merit Student Scholarship.

📖 Educations

• 2024.09 - Present, Huazhong University of Science and Technology (Master Student).
• 2020.09 - 2024.06, Huazhong University of Science and Technology (Undergraduate Student).

🚀 Internships

• 2025.07 - Present, Autonomous Driving and Robotics Department of Xiaomi EV (Beijing).
• 2025.03 - Present, Institute for AI Industry Research (AIR), Tsinghua University.