Rephrase Before You Act: Characterizing and Mitigating Language Sensitivity in Vision-Language-Action Models
Paper recorded by Signals 4 on 2026-10-07 in cs.LG. Abstract reproduced from arXiv; link to the original below.
Published 2026-10-07 on arXiv · recorded by Signals 4 on 2026-10-08
Category: cs.LG · 机器学习 · first seen 2026-10-08
Abstract
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 augmenta
Read on arXiv →
Cite this page: Rephrase Before You Act: Characterizing and Mitigating Language Sensitivity in Vision-Language-Action Models: the #331 most recent of 749 cs.LG papers we have recorded (as of 2026-10-07). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/rephrase-before-you-act-characterizing-and-mitigating-language-sensitivity-in-vi.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable:
papers.json
Get 4 AI signals a day by email — free.
Get 4 AI signals a day by email — free