ActFovea: Runtime Safeguarding for VLA Policies via Spatiotemporal Visual-Action Consistency
Vision-language-action (VLA) policies achieve strong performance in robotic manipulation but remain vulnerable to runtime disturbances that break the temporal alignment among visual observations, robot states, and executed actions. We introduce ActFovea, a plug-and-play safeguarding framework that detects and mitigates such failures without retraining or modifying the underlying VLA policy. ActFovea uses robot kinematics, proprioceptive states, and recent actions to construct action-conditioned
Record details
Published: 31 July 2026
Source: arXiv
Category: Research
Topics: Regulation · Safety & alignment · Agents & autonomy
Retrieved: 3 August 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Inference-Time Policy Alignment for Fair Reinforcement Learning
arXiv fairness query · 31 July 2026
Share No More Than the Request Requires: Federated Disclosure for Perspective-Aware AI
arXiv cs.CY · 28 July 2026
Towards Robust Reinforcement Learning for Small-Scale Language Model Agents
arXiv · 27 July 2026
When Privileged Guidance Misaligns: State-Matched Routing and Contextualized Self-Distillation for Multi-Turn Agents
HuggingFace Daily Papers · 4 August 2026
Towards Robust Reinforcement Learning for Small-Scale Language Model Agents
HuggingFace Daily Papers · 26 July 2026
MemOPD: On-Policy Distillation through Memory State Alignment for Long-Horizon Agents
arXiv · 7 August 2026
How to cite this record
ethics.ai (31 July 2026), “ActFovea: Runtime Safeguarding for VLA Policies via Spatiotemporal Visual-Action Consistency,” evidence record 15677, https://ethics.ai/record/15677 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.