3 papers
cs.CV2025
Hierarchical Feature-level Reverse Propagation for Post-Training Neural Networks
Ni Ding, Lei He, Shengbo Eben Li +1
End-to-end autonomous driving has emerged as a dominant paradigm, yet its highly entangled black-box models pose significant challenges in terms of interpretability and safety assu…
cs.CV2024
Local Map Construction with SDMap: A Comprehensive Survey
Jiaqi Li, Pingfan Jia, Jiaxing Chen +3
Local map construction is a vital component of intelligent driving perception, offering necessary reference for vehicle positioning and planning. Standard Definition map (SDMap), k…
cs.LG2024
Conformal Symplectic Optimization for Stable Reinforcement Learning
Yao Lyu, Xiangteng Zhang, Shengbo Eben Li +5
Training deep reinforcement learning (RL) agents necessitates overcoming the highly unstable nonconvex stochastic optimization inherent in the trial-and-error mechanism. To tackle…