Averaging and temporally interpolating text latents in VLAs enables 83% success on novel task combinations in the libero-ood benchmark where SOTA models achieve under 15%.
Univla: Learning to act anywhere with task-centric latent actions
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.RO 2verdicts
UNVERDICTED 2representative citing papers
MotuBrain jointly models video and action via a three-stream Mixture-of-Transformers UniDiffuser to reach 95.8-96.1% success on RoboTwin 2.0 benchmarks, top EWMScore, and fast 11 Hz inference while adapting to new robots with 50-100 trajectories.
citing papers explorer
-
VLAs are Confined yet Capable of Generalizing to Novel Instructions
Averaging and temporally interpolating text latents in VLAs enables 83% success on novel task combinations in the libero-ood benchmark where SOTA models achieve under 15%.
-
MotuBrain: An Advanced World Action Model for Robot Control
MotuBrain jointly models video and action via a three-stream Mixture-of-Transformers UniDiffuser to reach 95.8-96.1% success on RoboTwin 2.0 benchmarks, top EWMScore, and fast 11 Hz inference while adapting to new robots with 50-100 trajectories.