Zhiqi is currently focusing on the research of autonomous driving. Vision-centric self-driving cars benefit from lower costs compared to leveraging LiDAR sensor, making it more feasible for practical deployment in the real world. Due to the inability of RGB cameras to capture precise spatial information, vision-based perception methods typically fall short in accuracy compared to LiDAR-based perception algorithms. To address this problem, Zhiqi proposes one vision-centric autonomous driving centric method, which demonstrates that temporal information is greatly beneficial for vision-based autonomous driving perception, thus advancing progress in vision-centric autonomous driving research.