Selecting 50% of robot demonstrations by maximizing exposure to reusable primitive-transition patterns outperforms full-data training while halving training steps.
arXiv preprint arXiv:2606.16208 , year=
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
-
SIEVE: Structure-Aware Data Selection for Imitation Learning with VLA Models
Selecting 50% of robot demonstrations by maximizing exposure to reusable primitive-transition patterns outperforms full-data training while halving training steps.