Kailang Ma (麻开朗)

Email  /  Google Scholar  /  GitHub

About Me

I am currently a Perception Algorithm Engineer at Weride, a Tier-1 L4 autonomous driving company, where I work on traffic light detection and state estimation systems. I received my M.S. degree in Cyberspace Security from Beihang University (BUAA) in 2024, and my B.S. degree from the same university in 2021. During my master's study, I was a research intern at Tsinghua University working on wafer defect detection. I also spent time at Weride as an intern before joining full-time.

My current research interest focuses on World Models, particularly their applications in autonomous driving and embodied AI. I am interested in how world models can enable better understanding, prediction, and decision-making in complex dynamic environments.

Publications

Instance-wise Batch Label Restoration via Gradients in Federated Learning
Kailang Ma, Yu Sun, Jian Cui, et al.
International Conference on Learning Representations (ICLR), 2023

[Paper] [Code]

Cross-CAM: Focused Visual Explanations for Deep Convolutional Networks via Training-Set Tracing
Yu Sun, Kailang Ma, Xuanxin Liu, et al.
International Conference on Knowledge Science, Engineering and Management (KSEM), 2022

[Paper]

Awards