Research map / Vision-language and multimodal / Robot action and navigation
LLM as Copilot for Coarse-grained Vision-and-Language Navigation
Yanyuan Qiao, Qianyi Liu, Jiajun Liu, Jing Liu, Qi Wu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add LLM-selected guidance information triggered by confusion score (ablation) | AutoVLN agent · REVERIE Val Unseen | SPL: 40.15 -> 43.63 | Improved |
| let LLM select one guidance type instead of generating all four (ablation) | VLN-Copilot · REVERIE Val Unseen | SPL: 41.36 -> 43.63 | Improved |
| LLM-selected guidance type instead of random selection (ablation) | VLN-Copilot · REVERIE Val Unseen | SPL: 42.16 -> 43.63 | Improved |
| add location guidance only (ablation) | AutoVLN agent · REVERIE Val Unseen | SPL: 40.15 -> 42.97 | Improved |
| add previous observations guidance only (ablation) | AutoVLN agent · REVERIE Val Unseen | SPL: 40.15 -> 42.83 | Improved |
| change confusion threshold tau between 0.8 and 1.4 (ablation) | VLN-Copilot · REVERIE Val Unseen | SPL / RGSPL: SPL 42.55 to 43.68 across tau | No clear effect |
| VLN-Copilot versus MiC on REVERIE val unseen | VLN-Copilot · REVERIE Val Unseen | SPL: 43.60 -> 43.63 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- DUET — DUET: Cross-Modal Semantic Grounding for Contrastive Zero-Shot Learning (AAAI 2023) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- NavGPT-2: Unleashing Navigational Reasoning Capability for Large Vision-Language Models (ECCV 2024 · similarity 0.92)
- AwareVLN: Reasoning with Self-awareness for Vision-Language Navigation (CVPR 2026 · similarity 0.90)
- NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models (AAAI 2024 · similarity 0.90)
- VELMA: Verbalization Embodiment of LLM Agents for Vision and Language Navigation in Street View (AAAI 2024 · similarity 0.89)
- General Scene Adaptation for Vision-and-Language Navigation (ICLR 2025 · similarity 0.89)
- Run, Ruminate, and Regulate: A Dual-process Thinking System for Vision-and-Language Navigation (AAAI 2026 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
