GuidedVLA improves VLA success rates by manually supervising separate attention heads in the action decoder with auxiliary signals for task-relevant factors.
We investigate two strategies for supervising these attention heads: a binary mask–based region loss, and a Gaussian prior–based KL divergence loss
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
GuidedVLA: Specifying Task-Relevant Factors via Plug-and-Play Action Attention Specialization
GuidedVLA improves VLA success rates by manually supervising separate attention heads in the action decoder with auxiliary signals for task-relevant factors.