Liuwei XIE — accepted AI-conference papers

2026

ReflexDiffusion: Reflection-Enhanced Trajectory Planning for High-lateral-acceleration Scenarios in Autonomous Driving

Xuemei Yao, Xiao Yang, Jianbin Sun, Liuwei Xie, Xuebin Shao, Xiyu Fang +2

AAAI 2026technical

Generating safe and reliable trajectories for autonomous vehicles in long-tail scenarios remains a significant challenge, particularly for High-lateral-acceleration maneuvers such as sharp turns that represent critical safety situations. Existing trajectory planners exhibit systematic failures in th

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

Embodied Active Defense: Leveraging Recurrent Feedback to Counter Adversarial Patches

Lingxuan Wu, Xiao Yang, Yinpeng Dong, Liuwei XIE, Hang Su, Jun Zhu

ICLR 2024poster

The vulnerability of deep neural networks to adversarial patches has motivated numerous defense strategies for boosting model robustness. However, the prevailing defenses depend on single observation or pre-established adversary information to counter adversarial patches, often failing to be confron…

Cited by 3 Source ↗PDF ↗Scholar ↗