Research map / Vision-language and multimodal / Robot action and navigation
Structured Scene Memory for Vision-Language Navigation
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 structured scene memory, iterative reasoning, and frontier-exploration decision making | VLN agent · R2R test unseen | SR: 0.60 -> 0.61 | Helped |
| Add structured scene memory, iterative reasoning, and frontier-exploration decision making | VLN agent · R4R validation seen | CLS: 0.60 -> 0.65 | Helped |
| Add structured scene memory, iterative reasoning, and frontier-exploration decision making | VLN agent · R4R validation unseen | CLS: 0.44 -> 0.53 | Helped |
| Add fine-grained instruction grounding (ablation) | SSM on R2R validation unseen · R2R validation unseen | SR: 0.59 -> 0.62 | Helped |
| Add iterative reasoning (ablation) | SSM on R2R validation unseen · R2R validation unseen | SR: 0.57 -> 0.62 | Helped |
| Use global rather than local action space decision making (ablation) | SSM on R2R validation unseen · R2R validation unseen | SR: 0.54 -> 0.62 | Helped |
| Use frontier-exploration rather than global one-step decision making (ablation) | SSM on R2R validation unseen · R2R validation unseen | SR: 0.56 -> 0.62 | Helped |
Closest papers by meaning
- MemoNav: Working Memory Model for Visual Navigation (CVPR 2024 · similarity 0.91)
- Towards Long-Horizon Vision-Language Navigation: Platform, Benchmark and Method (CVPR 2025 · similarity 0.90)
- 3D-Mem: 3D Scene Memory for Embodied Exploration and Reasoning (CVPR 2025 · similarity 0.89)
- Hierarchical Semantic-Augmented Navigation: Optimal Transport and Graph-Driven Reasoning for Vision-Language Navigation (NeurIPS 2025 · similarity 0.88)
- LangMap: A Human-Verified Benchmark for Hierarchical Open-Vocabulary Goal Navigation (NeurIPS 2026 · similarity 0.88)
- Aux-Think: Exploring Reasoning Strategies for Data-Efficient Vision-Language Navigation (NeurIPS 2025 · similarity 0.88)
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.