Jun 2026
Drop-Then-Recovery: How Redundant Are Vision-Language-Action Models?
The results suggest that current VLA benchmarks may exert limited pressure on deep language grounding and compositional instruction understanding, and that future VLA architectures should allocate capacity more deliberately across language, vision, and action components.
Guoheng Sun, Kai Feng, Shwai He et al.
· arXiv.org · 0 citations