SafeVLA-Bench adds STL-based safety checks to VLA benchmarks and finds 13-56% of successful rollouts on LIBERO and RoboCasa-365 violate at least one safety clause.
arXiv preprint arXiv:2603.10052 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.RO 2years
2026 2representative citing papers
COAST applies contrastive conceptors to steer VLA hidden states into task-specific success subspaces, yielding over 20% simulation and 40% real-robot success rate gains across three distinct policies.
citing papers explorer
-
SafeVLA-Bench: A Benchmark for the Success-Safety Gap in Vision-Language-Action Models
SafeVLA-Bench adds STL-based safety checks to VLA benchmarks and finds 13-56% of successful rollouts on LIBERO and RoboCasa-365 violate at least one safety clause.
-
Contrastive Conceptor Activation Steering (COAST): Unlocking Vision-Language-Action Models through Hidden States
COAST applies contrastive conceptors to steer VLA hidden states into task-specific success subspaces, yielding over 20% simulation and 40% real-robot success rate gains across three distinct policies.