3 papers
cs.RO2026
Imagined Rollouts are Kinematic, Not Dynamic: A Diagnosis of Long-Horizon World-Model Failure
Finn Rasmus Schäfer, Korbinian Moller, Yuan Gao +3
Long-horizon failure in world models is conventionally attributed to compounding error, a generic framing that does not distinguish what kind of error compounds. We propose a kinem…
cs.RO2026
StyleVLA: Driving Style-Aware Vision Language Action Model for Autonomous Driving
Yuan Gao, Dengyuan Hua, Mattia Piccinini +4
Vision Language Models (VLMs) bridge visual perception and linguistic reasoning. In Autonomous Driving (AD), this synergy has enabled Vision Language Action (VLA) models, which tra…
cs.CV2025
Target-Bench: Can Video World Models Achieve Mapless Path Planning with Semantic Targets?
Dingrui Wang, Zhihao Liang, Hongyuan Ye +13
While recent video world models can generate highly realistic videos, their ability to perform semantic reasoning and planning remains unclear and unquantified. We introduce Target…