cs.CVNov 7, 2026

Latent-WAM++: Shaping World and Action Representations for End-to-End Autonomous Driving

Authors: Yichen Zhang, Yupeng Zheng, Linbo Wang, Pengxuan Yang, Zebin Xing, Junli Wang, Shiwei Li, Kangwei Liu, 

Organizations: Institute of Automation, Chinese Academy of Sciences · Chongqing Changan Technology Co., Ltd.

Abstract

We introduce Latent-WAM++, a representation-centered World Action Model (WAM) for end-to-end autonomous driving. Existing WAMs are primarily trained to predict future states or final actions, leaving the intermediate world and action representations that connect prediction to planning only indirectly constrained. Latent-WAM++ matches the supervision of each representation to its role in planning. World Representation Construction combines scene-ego future prediction, SIGReg-based distribution stabilization, and frozen geometric priors to learn a temporally predictive, non-degenerate, and geometry-aware world representation without an EMA target encoder. Trajectory MeanFlow Planner directly predicts multimodal trajectory proposals while being optimized with an Improved MeanFlow velocity-space objective, enabling one-step sampling. Visual-Action Representation Alignment further aligns the resulting pre-output action features with a stop-gradient target derived from current visual semantics. Latent-WAM++ achieves state-of-the-art performance on NAVSIM v2 and under zero-shot evaluation on HUGSIM, reaching 90.1 EPDMS on NAVSIM v2 and 47.0 average RC and 30.1 average HD-Score on HUGSIM. Training the planner end to end costs 190 GPU-hours for Latent-WAM++ versus 1,600 for Latent-WAM, a reduction of 88.1%.

Figures & tables

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Latent-WAM: Latent World Action Modeling for End-to-End Autonomous Driving

    Mar 25, 2026Linbo Wang, Yupeng Zheng, Qiang Chen +13End-to-End Autonomous DrivingWorld Models for Autonomous Driving

  2. PlanWAM: Planning-Shaped Future Representations for End-to-End Autonomous Driving

    Oct 8, 2026Jinchang Xu, Hongda Yu, Fengwei Dong +9End-to-End Autonomous DrivingWorld Model-Based Planning

  3. SimWAM: A Simple World Action Model for End-to-End Autonomous Driving

    Aug 7, 2026Zongchuang Zhao, Xin Zhou, Tianyang Xu +6End-to-End Autonomous DrivingAutonomous Driving