#computer vision
Jun 2026
RoboTrustBench: Benchmarking the Trustworthiness of Video World Models for Robotic Manipulation
It is found that current models often generate visually coherent videos, but struggle with constraint reasoning, counterfactual grounding, physical interaction, and unsafe-instruction suppression, and results show that visual quality and surface-level instruction following are insufficient for trustworthy robotic video world modeling.
Huiqiong Li, Jia-Yu Wang, Zhiting Mei et al.
· arXiv.org · 4 citations