ReGIL retrieves segments from a single demonstration to compute local temporal-alignment rewards and guide policy training, achieving >75% success on three real-robot tasks with <1 hour of online data.
Hand me the data: Fast robot adaptation via hand path retrieval,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.RO 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
LiMoDE uses dynamic MoE pre-training on motion cues followed by lifelong expert addition for continuous robot task adaptation.
citing papers explorer
-
ReGIL: Retrieval-Guided Imitation Learning from a Single Demonstration
ReGIL retrieves segments from a single demonstration to compute local temporal-alignment rewards and guide policy training, achieving >75% success on three real-robot tasks with <1 hour of online data.
-
LiMoDE: Rethinking Lifelong Robot Manipulation from a Mixture-of-Dynamic-Experts Perspective
LiMoDE uses dynamic MoE pre-training on motion cues followed by lifelong expert addition for continuous robot task adaptation.