Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous Driving Paper • 2609.00111 • Published 3 days ago • 335
Magpie: Real-Time World Renderer for Interactive Games Paper • 2608.27168 • Published 7 days ago • 10
WorldExam: Benchmarking World Models from Apparent Appearance to Inherent Reactivity Paper • 2608.02603 • Published about 1 month ago • 34
Runtime error 15 AV Causal Scenario Retrieval Challenge 🔍 15 Retrieve driving scenarios from video annotations
Running 17 Physical AI AV Reasoning Challenge 🚗 17 Submit reasoning explanations for driving clips and view leaderboard
World Pilot: Steering Vision-Language-Action Models with World-Action Priors Paper • 2606.12403 • Published Jun 10 • 27
MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research Paper • 2605.26114 • Published May 25 • 68
Sensor2Sensor: Cross-Embodiment Sensor Conversion for Autonomous Driving Paper • 2605.22809 • Published May 21 • 27
DexJoCo: A Benchmark and Toolkit for Task-Oriented Dexterous Manipulation on MuJoCo Paper • 2605.16257 • Published May 15 • 55
Running on A100 Featured 29 Asset Harvester 🚗 29 Image-to-3D for autonomous-vehicle simulation assets