Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Bridging the Gap Between Learning in Discrete and Continuous Environments for Vision-and-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 |
|---|---|---|---|
| Use predicted waypoints instead of low-level actions | CMA · R2R-CE Val-Unseen | SPL: 24.97 -> 33.90 | Helped |
| Use predicted waypoints instead of low-level actions | VLN→BERT · R2R-CE Val-Unseen | SPL: 21.67 -> 38.53 | Helped |
| Train CMA to adapt to predicted waypoints rather than freeze the predictor (ablation) | CMA · R2R-CE Val-Unseen | SPL: 29.92 -> 33.90 | Helped |
| Train VLN→BERT to adapt to predicted waypoints rather than freeze the predictor (ablation) | VLN→BERT · R2R-CE Val-Unseen | SPL: 34.42 -> 38.53 | Helped |
| Augment predicted waypoints during training (ablation) | CMA · R2R-CE Val-Unseen | SPL: 33.90 -> 36.73 | Helped |
| Augment predicted waypoints during training (ablation) | VLN→BERT · R2R-CE Val-Unseen | SPL: 38.53 -> 39.91 | Helped |
| Replace the baseline waypoint predictor with the Transformer predictor (ablation) | Waypoint prediction · MP3D Val-Unseen | %Open: 80.18 -> 79.86 | No clear effect |
| Use the Transformer predictor rather than U-Net (ablation) | Waypoint prediction · MP3D Val-Unseen | %Open: 52.54 -> 79.86 | Helped |
| Allow sliding along obstacles (ablation) | CMA · RxR-CE Unseen | SR: 26.59 -> 31.36 | Helped |
| Allow sliding along obstacles (ablation) | VLN→BERT · RxR-CE Unseen | SR: 27.08 -> 33.25 | Helped |
| Add view selection to continuous navigation (ablation) | RCM · R2R-CE Val-Unseen | SR: 27.29 -> 37.72 | Helped |
| Add waypoint teleportation to continuous navigation (ablation) | RCM · R2R-CE Val-Unseen | SR: 27.29 -> 39.32 | Helped |
Closest papers by meaning
- Improving Vision-and-Language Navigation by Generating Future-View Image Semantics (CVPR 2023 · similarity 0.90)
- STRIDER: Navigation via Instruction-Aligned Structural Decision Space Optimization (NeurIPS 2025 · similarity 0.90)
- NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models (AAAI 2024 · similarity 0.89)
- Affordances-Oriented Planning Using Foundation Models for Continuous Vision-Language Navigation (AAAI 2025 · similarity 0.89)
- Hierarchical Semantic-Augmented Navigation: Optimal Transport and Graph-Driven Reasoning for Vision-Language Navigation (NeurIPS 2025 · similarity 0.89)
- General Scene Adaptation for Vision-and-Language Navigation (ICLR 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.