LEEVLA improves VLA robot policies by training-time prioritization of dynamic instruction-relevant patches plus structured latent future-feature prediction with topology constraints.
Open x-embodiment: Robotic learning datasets and rt-x models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
LEEVLA: Seeing What Matters in Latent Environment Evolution for Vision-Language-Action
LEEVLA improves VLA robot policies by training-time prioritization of dynamic instruction-relevant patches plus structured latent future-feature prediction with topology constraints.