Preprint
Sep 2026
Continuous Actions from Discrete Minds: Latent-Aligned Planning for End-to-End Autonomous Driving
LaPla is introduced, a unified Vision-Language-Action framework featuring latent-aligned planning to seamlessly ground semantic understanding in precise motion execution to bridge the modality gap between high-dimensional semantics and the raw action space.
Ruo-Yu Yao, Yu-Sen Xie, Qing-Zhao Liu et al.
· 0 citations