VLA-Forget: Vision-Language-Action Unlearning for Embodied Foundation Models
Vision-language-action (VLA) models are emerging as embodied foundation models for robotic manipulation, but their deployment introduces a new unlearning challenge: removing unsafe, spurious, or privacy-sensitive behaviors without degrading perception, language grounding, and action control. In OpenVLA-style policies, behavior is produced through a fused visual encoder, a cross-modal projector, and a language backbone that predicts tokenized robot actions, so undesirable knowledge can be distrib
Record details
Published: 5 April 2026
Source: arXiv
Category: Research
Topics: Privacy · Agents & autonomy
Retrieved: 14 July 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.
EmoMAS: Emotion-Aware Multi-Agent System for High-Stakes Edge-Deployable Negotiation with Bayesian Orchestration
arXiv · 8 April 2026
Frequency-Enhanced Diffusion Models: Curriculum-Guided Semantic Alignment for Zero-Shot Skeleton Action Recognition
arXiv · 10 April 2026
FeDMRA: Federated Incremental Learning with Dynamic Memory Replay Allocation
arXiv · 30 March 2026
Mobile GUI Agent Privacy Personalization with Trajectory Induced Preference Optimization
arXiv · 13 April 2026
CIA: Inferring the Communication Topology from LLM-based Multi-Agent Systems
arXiv · 14 April 2026
Listening Alone, Understanding Together: Collaborative Context Recovery for Privacy-Aware AI
arXiv · 14 April 2026
How to cite this record
ethics.ai (5 April 2026), “VLA-Forget: Vision-Language-Action Unlearning for Embodied Foundation Models,” evidence record 6357, https://ethics.ai/record/6357 (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.