A standardized 16-task memory benchmark and 14 controlled VLA variants show perceptual memory (especially frame sampling + AdaLN modulation) is strongest overall, while symbolic subgoals win on counting and short-horizon reasoning.
first press the button, then pick up all highlighted cubes, finally press the button again to stop
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policies
A standardized 16-task memory benchmark and 14 controlled VLA variants show perceptual memory (especially frame sampling + AdaLN modulation) is strongest overall, while symbolic subgoals win on counting and short-horizon reasoning.