自动驾驶

Lagrange: An Open-Vocabulary, Energy-Based Sparse Framework for Generalized End-to-End Driving

Lagrange: 一种面向通用端到端驾驶的开放词汇、基于能量的稀疏框架

Shihao Ji, HongXi Li, Zihui Song, Mingyu Li

专题命中 端到端驾驶 ：end-to-end driving(title)；autonomous driving(abstract)；occupancy(abstract)；分类 cs.AI

AI总结 提出Lagrange框架，利用掩码潜在场和视觉语言模型实现开放词汇、稀疏计算，通过拉格朗日动作最小化确保运动学约束，在nuScenes和CODA基准上验证了鲁棒性和可解释性。

Comments Withdrawn due to serious concerns regarding the authenticity and accuracy of the listed authorship. The identity of one or more listed authors cannot presently be verified, and the author list may not represent distinct contributors. The manuscript is withdrawn pending institutional review

MomADv2: Reliable Temporal Memory for End-to-End Autonomous Driving

MomADv2：面向端到端自动驾驶的可靠时序记忆

Ziying Song, Shengkai Zhang, Lin Liu, Peiliang Wu, Lei Yang, Dongyang Xu, Bin Sun, Li Wang, Shaoqing Xu, Caiyan Jia, Yadan Luo

专题命中 端到端驾驶 ：autonomous driving(title,abstract)；分类 cs.RO、cs.CV

AI总结 针对自动驾驶时序记忆易失效的问题，提出 MomADv2 框架，含选择性记忆查询模块与流匹配残差修正器，在多数据集上使碰撞率降 15.6%。

Comments 16 pages, 6 figures