A language-conditioned robotic rearrangement framework retrieves past successful arrangements as templates to guide an LLM's spatial reasoning, improving placement accuracy over baselines.
Mental models and lifelong learning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learn from the Past: Language-conditioned Object Rearrangement with Large Language Models
A language-conditioned robotic rearrangement framework retrieves past successful arrangements as templates to guide an LLM's spatial reasoning, improving placement accuracy over baselines.