3 papers
cs.RO2026
Outcome-Guided Distillation: A Teacher-Student Framework to Advance VLM Reasoning in Autonomous Driving
Zeyu Dong, Yimin Zhu, Yu Wu +1
End-to-end (E2E) autonomous driving aims to learn a direct mapping from visual observations to control actions. However, these E2E models often act as black boxes and struggle with…
eess.SY2026
Adaptive Model-Based Reinforcement Learning for Orbit Feedback Control in NSLS-II Storage Ring
Zeyu Dong, Yuke Tian, Yu Sun
The National Synchrotron Light Source II (NSLS-II) uses highly stable electron beam to produce high-quality X-ray beams with high brightness and low-emittance synchrotron radiation…
cs.CV2026
FROST-Drive: Scalable and Efficient End-to-End Driving with a Frozen Vision Encoder
Zeyu Dong, Yimin Zhu, Yu Wu +1
End-to-end (E2E) models in autonomous driving aim to directly map sensor inputs to control commands, but their ability to generalize to novel and complex scenarios remains a key ch…