Research map / Vision-language and multimodal / Robot action and navigation
Actional Atomic-Concept Learning for Demystifying Vision-Language Navigation
Read the paperCheck 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 AACL to DUET | DUET · R2R Val Unseen | SR: 72 -> 74 | Helped |
| Add AACL to DUET | DUET · REVERIE Val Unseen | SR: 46.98 -> 49.42 | Helped |
| Add AACL to HAMT | HAMT · R2R-Last Val Unseen | SR: 45.2 -> 47.2 | Helped |
| Add actional atomic concepts using separate embeddings (ablation) | HAMT-based AACL · R2R Val Unseen | SR: 66.67 -> 67.94 | Helped |
| Add observation contrast (ablation) | AACL without contrast · R2R Val Unseen | SPL: 61.48 -> 62.33 | Helped |
| Add concept refining adapter (ablation) | AACL without refine · R2R Val Unseen | SR: 67.82 -> 68.54 | Helped |
| Use 1 object concept instead of 5 (ablation) | AACL · R2R Val Unseen | SR: 67.94 -> 67.52 | Hurt |
| Use 10 object concepts instead of 5 (ablation) | AACL · R2R Val Unseen | SR: 67.94 -> 66.88 | Hurt |
| Use action and object concepts together instead of object concepts only (ablation) | AACL · R2R Val Unseen | SR: 66.37 -> 67.94 | Helped |
| Use action and object concepts together instead of action concepts only (ablation) | AACL · R2R Val Unseen | SR: 67.13 -> 67.94 | Helped |
Closest papers by meaning
- Instruction Decomposition and Action Alignment for Vision-Language Navigation (ICML 2026 · similarity 0.89)
- V-ABS: Action-Observer Driven Beam Search for Dynamic Visual Reasoning (ICML 2026 · similarity 0.87)
- NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models (AAAI 2024 · similarity 0.87)
- OTTER: A Vision-Language-Action Model with Text-Aware Visual Feature Extraction (ICML 2025 · similarity 0.87)
- Aux-Think: Exploring Reasoning Strategies for Data-Efficient Vision-Language Navigation (NeurIPS 2025 · similarity 0.87)
- FantasyVLN: Unified Multimodal Chain-of-Thought Reasoning for Vision-and-Language Navigation (CVPR 2026 · 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.