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

arXiv:2603.24581 · cs.CV, cs.RO · Submitted 2026-03-25 · Read on arXiv

cs.CV, cs.RO

Submitted: 2026-03-25

Updated: 2026-10-18

Code: https://github.com/yukki555/Latent-WAM

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Core — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Planner — 1× in this paper · explained in 3 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• World Model — 1× in this paper · explained in 7 episodes

Sources

• Pseudo-Simulation for Autonomous Driving
• VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planning
• SparseWorld: A Flexible, Adaptive, and Efficient 4D Occupancy World Model Powered by Sparse and Dynamic Queries
• NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking
• DiST-4D: Disentangled Spatiotemporal Diffusion with Metric Depth for 4D Driving Scene Generation
• GAIA-1: A Generative World Model for Autonomous Driving
• UniScene: Unified Occupancy-centric Driving Scene Generation
• Scaling Up Occupancy-centric Driving Scene Generation: Dataset and Method
• OmniNWM: Omniscient Driving Navigation World Models
• DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving
• ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving
• Generalized Trajectory Scoring for End-to-end Multimodal Planning
• WorldMirror: Universal 3D World Reconstruction with Any-Prior Prompting
• Decoupled Weight Decay Regularization
• SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representation
• Tokenize the World into Object-level Knowledge to Address Long-tail Events in Autonomous Driving
• Drive-JEPA: Video JEPA Meets Multimodal Trajectory Distillation for End-to-End Driving
• DriveDreamer: Towards Real-world-driven World Models for Autonomous Driving
• Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Driving
• DriveLaW:Unifying Planning and Video Generation in a Latent Driving World

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models