When Listening Becomes Easier: Scrubbing Visual Cues for Shortcut-Free VLAs

The paper addresses shortcut learning in vision‑language‑action (VLA) models, showing that different backbones vary in their susceptibility to visual shortcuts that arise from limited demonstration diversity. It introduces a representation‑level metric called action margin to predict shortcut use without rollouts, and proposes task scrubbing—a domain‑adversarial training method—to reduce reliance on visual cues and enhance out‑of‑distribution robustness. Experiments in simulation and real‑world settings demonstrate that task scrubbing improves generalization and often eliminates visual shortcut learning.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

• llms
• robotics
• multimodal
• safety