Research map / Vision-language and multimodal / Robot action and navigation
Multimodal LLM Guided Exploration and Active Mapping using Fisher Information
Wen Jiang, Boshu Lei, Katrina Ashton, Kostas Daniilidis
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 multimodal LLM long-horizon planner (GPT-4o) (ablation) | active mapping with EIG and localization uncertainty · HM3D | PSNR: 16.94 -> 19.86 | Improved |
| add localization uncertainty term to path selection (ablation) | active mapping without LLM · HM3D | RMSE ATE: 0.2478 -> 0.1694 | Improved |
| add LLM planner on top of localization uncertainty (ablation) | active mapping · HM3D | RMSE ATE: 0.1694 -> 0.0336 | Improved |
| use Llava-7b instead of GPT-4o as the LLM planner (ablation) | active mapping · HM3D | Completeness (%): 49.76 -> 17.41 | Hurt |
| use Llava-7b instead of GPT-4o as the LLM planner (ablation) | active mapping · HM3D | RMSE ATE: 0.0336 -> 0.0159 | Improved |
| change FisherRF-style prior regularizer lambda from 2e-6/5e-6 (ablation) | active mapping (GPT-4o) · HM3D | completeness: 49.76 -> 18.12 (lambda 2e-6) | Hurt |
| use proposed method instead of FBE | active mapping · Gibson | LPIPS: FBE 0.2126 vs Ours 0.2507 | Hurt |
| use proposed method instead of FBE | active mapping · Gibson | Completeness (%): 55.87 -> 84.38 | Improved |
Closest papers by meaning
- Understanding while Exploring: Semantics-driven Active Mapping (NeurIPS 2025 · similarity 0.89)
- Affordances-Oriented Planning Using Foundation Models for Continuous Vision-Language Navigation (AAAI 2025 · similarity 0.87)
- Scene Map-based Prompt Tuning for Navigation Instruction Generation (CVPR 2025 · similarity 0.86)
- Enhancing Multi-Robot Semantic Navigation Through Multimodal Chain-of-Thought Score Collaboration (AAAI 2025 · similarity 0.86)
- Run, Ruminate, and Regulate: A Dual-process Thinking System for Vision-and-Language Navigation (AAAI 2026 · similarity 0.86)
- BeliefMapNav: 3D Voxel-Based Belief Map for Zero-Shot Object Navigation (NeurIPS 2025 · 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.
