SimVTA: Simulation-Grounded Video-Trajectory Alignment for Driving World Action Models

arXiv:2610.13781 · cs.CV · Submitted 2026-10-09 · Read on arXiv

cs.CV

Submitted: 2026-10-09

Updated: 2026-10-09

Comments: Project page: https://opendrivelab.com/SimVTA/

Code: https://github.com/OpenDriveLab/SimVTA

Project page: https://opendrivelab.com/SimVTA

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

Terminology

• Alignment — 1× in this paper · explained in 1 episode

Sources

• Bench2Drive: Towards Multi-Ability Benchmarking of Closed-Loop End-To-End Autonomous Driving
• Bench2Drive-VL: Benchmarks for Closed-Loop Autonomous Driving with Vision-Language Models
• PlannerRFT: Reinforcing Diffusion Planners through Closed-Loop and Sample-Efficient Fine-Tuning
• World Engine: Towards the Era of Post-Training for Autonomous Driving
• DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving
• End-to-End Driving with Online Trajectory Evaluation via BEV World Model
• UNIVERSE: Unified Video Action Models for Autonomous Driving with Flexible Mask-Modulated Modality Generation
• DriveVA: Video Action Models are Zero-Shot Drivers
• Uni-World VLA: Interleaved World Modeling and Planning for Autonomous Driving
• Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation
• Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• DriveWAM: Video Generative Priors Enable Scalable World-Action Modeling for Autonomous Driving
• Latent-WAM: Latent World Action Modeling for End-to-End Autonomous Driving
• WA-JEPA: Rethinking the Video JEPA Paradigm for World-Action Modeling in Autonomous Driving
• DriveMoE: Mixture-of-Experts for Vision-Language-Action Model in End-to-End Autonomous Driving
• Fast-WAM: Do World Action Models Need Test-time Future Imagination?
• SimWAM: A Simple World Action Model for End-to-End Autonomous Driving
• HUGSIM: A Real-Time, Photo-Realistic and Closed-Loop Simulator for Autonomous Driving

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