ForesightSafety-VLA Benchmark
Explore score history ↗A diagnostic safety benchmark for vision-language-action models, evaluating policies across physical interaction, instruction, and perception safety with cumulative cost and risk exposure metrics.
- Released
- 2026-06-25
- Institutions
- Institute of Automation · University of Chinese Academy of Sciences
- Evaluates
- Multimodal, Robotics & Embodied AI, Safety, Safety & Trustworthiness
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
ForesightSafety-VLA paper
No reported scores are on record for this benchmark yet.