Research map / Multi-agent systems and games / LLM agents
DialNav: Multi-turn Dialog Navigation with a Remote Guide
Leekyeung Han, Hyunji Min, Gyeom Hwangbo, Jonghyun Choi, Paul Hongsuck Seo
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 dialog with remote guide | DUET navigator · DialNav RAIN Val Seen | SR: 18.2 -> 27.0 | Improved |
| add dialog with remote guide | DUET navigator · DialNav RAIN Val Unseen | SR: 15.4 -> 13.9 | Hurt |
| add dialog with remote guide | DUET navigator · DialNav RAIN Test | SR: 12.7 -> 11.9 | Hurt |
| add dialog with remote guide | DUET navigator · DialNav RAIN Val Unseen | NSC: 20.8 -> 14.2 | Improved |
| give ground-truth Navigator location to Guide | DialNav · DialNav RAIN Val Seen | SR: 27.0 -> 31.4 | Improved |
| give ground-truth location to Guide | DialNav · DialNav RAIN Val Unseen | SR: 13.9 -> 19.8 | Improved |
| add pretraining to navigation module (ablation) | DialNav · DialNav RAIN Val Seen | SR: 9.2 -> 27.0 | Improved |
| add pretraining to answer generation module (ablation) | DialNav · DialNav RAIN Val Seen | SR: 11.7 -> 27.0 | Improved |
| add pretraining to localization module (ablation) | DialNav · DialNav RAIN Val Seen | SR: 25.7 -> 27.0 | Improved |
| add pretraining to question generation module (ablation) | DialNav · DialNav RAIN Val Seen | SR: 27.7 -> 27.0 | No clear effect |
| replace LANA question generator with LLaVA-1.5 | DialNav · DialNav RAIN Val Seen | question fluency: 4.7 -> 9.0; SR 27.0 -> 27.3; NE 11.4 -> 12.0 | Mixed |
| replace LANA answer generator with Llama-3.1 | DialNav · DialNav RAIN Val Seen | SR: 27.0 -> 22.2 | Hurt |
Closest papers by meaning
- DiaLoc: An Iterative Approach to Embodied Dialog Localization (CVPR 2024 · similarity 0.89)
- NavBench: Probing Multimodal Large Language Models for Embodied Navigation (NeurIPS 2025 · similarity 0.88)
- CAVEN: An Embodied Conversational Agent for Efficient Audio-Visual Navigation in Noisy Environments (AAAI 2024 · similarity 0.87)
- Human-Aware Vision-and-Language Navigation: Bridging Simulation to Reality with Dynamic Human Interactions (NeurIPS 2024 · similarity 0.86)
- EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents (ICML 2025 · similarity 0.86)
- VELMA: Verbalization Embodiment of LLM Agents for Vision and Language Navigation in Street View (AAAI 2024 · similarity 0.86)
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.
