LaMem-VLA reconstructs robotic history into dual short-term and long-term latent memory tokens that are woven directly into a VLA model's reasoning sequence to improve long-horizon manipulation.
Fast-thinkact: Efficient vision-language-action reasoning via verbalizable latent planning.arXiv e-prints, pages arXiv–2601, 2026
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Dual Latent Memory in Vision-Language-Action Models for Robotic Manipulation
LaMem-VLA reconstructs robotic history into dual short-term and long-term latent memory tokens that are woven directly into a VLA model's reasoning sequence to improve long-horizon manipulation.