LEEVLA improves VLA robot policies by training-time prioritization of dynamic instruction-relevant patches plus structured latent future-feature prediction with topology constraints.
Univla: Learning to act anywhere with task-centric latent ac- tions.Proceedings of Robotics: Science and Systems (RSS),
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.