GMP selectively activates and represents memory via a gate and lightweight cross-attention, yielding 30.1% higher success on non-Markovian robotic tasks while staying competitive on Markovian ones.
Scene memory transformer for embodied agents in long-horizon tasks.IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Gated Memory Policy
GMP selectively activates and represents memory via a gate and lightweight cross-attention, yielding 30.1% higher success on non-Markovian robotic tasks while staying competitive on Markovian ones.