UMA treats object motion and robot actions as co-evolving variables under a masked generative objective with hindsight relabeling and contrastive disentanglement to support multi-task pretraining and deployment across heterogeneous robot data.
Correspondence- oriented imitation learning: Flexible visuomotor control with 3d con- ditioning,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.RO 2years
2026 2representative citing papers
KIL using foundation model keypoints reaches 75% success on five manipulation tasks, beating RGB (47%) but matching S2-diffusion (73%), with generalization tests on unseen objects via over 2000 real-world rollouts.
citing papers explorer
-
On the Generalization Capabilities, Design Choices and Limitations of Keypoint Imitation Learning
KIL using foundation model keypoints reaches 75% success on five manipulation tasks, beating RGB (47%) but matching S2-diffusion (73%), with generalization tests on unseen objects via over 2000 real-world rollouts.