No AI summary available for this article.
Why It Matters
Vision-language-action models (VLAs) are strikingly sensitive to instruction phrasing and do not inherit the language robustness of the vision-language models they are built on.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
Vision-language-action models (VLAs) are strikingly sensitive to instruction phrasing and do not inherit the language robustness of the vision-language models they are built on. A one-word edit can move success by tens of points: $π_{0.5}$ turns on a LIBERO stove 100% of the time for "switch on the stove" and 2% for "switch on the hot plate", and a $π_0$ checkpoint finetuned with rephrase augmentation still shows swings of up to 61 points. We characterize this sensitivity with statistically tested single-edit swings and an oracle phrase search, which shows that phrasing alone nearly closes the...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2610.10526v1 · Indexed about 2 hours ago