NAVSIM v-2

NAVSIM v2 is a benchmark dataset used to evaluate the performance of Vision-Language-Action models in autonomous driving, specifically focusing on their ability to integrate perception and planning in a physically grounded manner.

Papers using NAVSIM v-2 (6)

LaST-VLA: Thinking in Latent Spatio-Temporal Space for Vision-Language-Action in Autonomous Driving2026DriveWorld-VLA: Unified Latent-Space World Modeling with Vision-Language-Action for Autonomous Driving2026HiST-VLA: A Hierarchical Spatio-Temporal Vision-Language-Action Model for End-to-End Autonomous Driving2026DriveFine: Refining-Augmented Masked Diffusion VLA for Precise and Robust Driving2026MindDrive: An All-in-One Framework Bridging World Models and Vision-Language Model for End-to-End Autonomous Driving2025IRL-VLA: Training an Vision-Language-Action Policy via Reward World Model2025