SafeVLA applies constrained reinforcement learning via CMDP min-max optimization to VLAs, cutting safety violation costs by 83.58% while preserving task success on long-horizon mobile manipulation tasks.
Towards testing and evaluating vision-language-action models for robotic manipulation: An empirical study
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.RO 3verdicts
UNVERDICTED 3representative citing papers
ACT-VLA synthesizes novel demonstrations from existing VLA tasks via latent representations to reduce overfitting and improve generalization on manipulation tasks in simulation.
Real-robot trials with OpenVLA on a UR5e arm show consistent offline-to-closed-loop gaps driven by action semantics, coordinate conventions, temporal alignment, image preprocessing, and dataset quality rather than model capacity.
citing papers explorer
-
SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning
SafeVLA applies constrained reinforcement learning via CMDP min-max optimization to VLAs, cutting safety violation costs by 83.58% while preserving task success on long-horizon mobile manipulation tasks.
-
Unleashing More Actions via Action Compositional Training for VLA Models
ACT-VLA synthesizes novel demonstrations from existing VLA tasks via latent representations to reduce overfitting and improve generalization on manipulation tasks in simulation.
-
Vision-Language-Action Models: Experimental Insights from a Real-World UR5 Platform
Real-robot trials with OpenVLA on a UR5e arm show consistent offline-to-closed-loop gaps driven by action semantics, coordinate conventions, temporal alignment, image preprocessing, and dataset quality rather than model capacity.