RageVLA claims state-of-the-art robustness on LIBERO benchmarks
A new paper introduces RageVLA, a vision-language-action model trained with augmentation for perception and action, reporting state-of-the-art robustness on LIBERO where many VLA models fail when objects move or instructions change.
Read the full story at arXiv cs.RO ↗
Timeline · 1 report
- 2026-11-19 05:00 · arXiv cs.RO
RageVLA: Augmentation-Trained Perception and Action for State-of-the-Art Robustness on LIBERO