RePlan-Bot achieves state-of-the-art results on the ALFRED benchmark for embodied instruction following by integrating LLM-based auditing, commonsense map search, and ViT action correction.
Look wide and interpret twice: Improving per- formance on interactive instruction-following tasks.arXiv preprint arXiv:2106.00596, 2021
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
-
RePlan-Bot: Multi-Level Replanning for Embodied Instruction Following
RePlan-Bot achieves state-of-the-art results on the ALFRED benchmark for embodied instruction following by integrating LLM-based auditing, commonsense map search, and ViT action correction.