A single human video is enough for a robot to acquire a new manipulation skill at inference time, with no parameter updates, reaching 62% success on 50 novel tasks.
Vid2Robot: 23 End-to-end Video-conditioned Policy Learning with Cross-Attention Transformers
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
-
Robots Acquire Manipulation Skills in Seconds from a Single Human Video
A single human video is enough for a robot to acquire a new manipulation skill at inference time, with no parameter updates, reaching 62% success on 50 novel tasks.