DIAL decouples intent from action in end-to-end VLAs using a latent visual foresight bottleneck and two-stage training, reaching SOTA on RoboCasa with 10x fewer demonstrations and zero-shot real-world transfer.
Starvla: A lego-like codebase for vision-language-action model develop- ing
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.RO 1years
2026 1verdicts
UNVERDICTED 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
DIAL: Decoupling Intent and Action via Latent World Modeling for End-to-End VLA
DIAL decouples intent from action in end-to-end VLAs using a latent visual foresight bottleneck and two-stage training, reaching SOTA on RoboCasa with 10x fewer demonstrations and zero-shot real-world transfer.