Subtracting a task vector from a vision-language-action robot policy suppresses the target skill but not its collateral damage: only five of ten LIBERO-Goal skills separate cleanly, and held-out control retention averages 52%.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Suppression Sticks, Locality Is Fragile: A Closed-Loop Target-and-Control Audit of Task-Vector Negation in VLA Policies
Subtracting a task vector from a vision-language-action robot policy suppresses the target skill but not its collateral damage: only five of ten LIBERO-Goal skills separate cleanly, and held-out control retention averages 52%.