AIBearisharXiv – CS AI · Mar 36/106
🧠
LangGap: Diagnosing and Closing the Language Gap in Vision-Language-Action Models
Researchers reveal that state-of-the-art Vision-Language-Action (VLA) models largely ignore language instructions despite achieving 95% success on standard benchmarks. The new LangGap benchmark exposes significant language understanding deficits, with targeted data augmentation only partially addressing the fundamental challenge of diverse instruction comprehension.