Research map / Vision-language and multimodal / Robot action and navigation
Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environments
Jacob Krantz, Erik Wijmans, Arjun Majumdar, Dhruv Batra, Stefan Lee
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 |
|---|---|---|---|
| use cross-modal attention instead of Seq2Seq (teacher forcing) | Seq2Seq baseline · VLN-CE val-unseen | SPL: 0.18 -> 0.22 | Improved |
| use cross-modal attention instead of Seq2Seq (with all three augmentations) | Seq2Seq PM+DA*+Aug · VLN-CE val-unseen | SPL: 0.22 -> 0.30 | Improved |
| add DAgger training (ablation) | Seq2Seq baseline · VLN-CE val-unseen | SPL: 0.18 -> 0.23 | Improved |
| add DAgger training (ablation) | Cross-Modal · VLN-CE val-unseen | SPL: 0.22 -> 0.25 | Improved |
| add progress monitor loss (ablation) | Seq2Seq baseline · VLN-CE val-unseen | SPL: 0.18 -> 0.15 | Hurt |
| add synthetic data augmentation (ablation) | Seq2Seq baseline · VLN-CE val-unseen | SPL: 0.18 -> 0.17 | Hurt |
| add progress monitor loss (ablation) | Cross-Modal · VLN-CE val-unseen | SPL: 0.22 -> 0.19 | Hurt |
| add synthetic data augmentation (ablation) | Cross-Modal · VLN-CE val-unseen | SPL: 0.22 -> 0.19 | Hurt |
| combine progress monitor, data augmentation and DAgger fine-tuning | Cross-Modal · VLN-CE val-unseen | SPL: 0.22 -> 0.30 | Improved |
| add progress monitor to augmented training (ablation) | Cross-Modal + Aug · VLN-CE val-unseen | SPL: 0.19 -> 0.22 | Improved |
| add data augmentation to DAgger fine-tuning (ablation) | Cross-Modal + DA · VLN-CE val-unseen | SPL: 0.25 -> 0.26 | Improved |
| add DAgger fine-tuning to PM+Aug pretraining (ablation) | Cross-Modal PM+Aug · VLN-CE val-unseen | SPL: 0.22 -> 0.30 | Improved |
Closest papers by meaning
- Hierarchical Semantic-Augmented Navigation: Optimal Transport and Graph-Driven Reasoning for Vision-Language Navigation (NeurIPS 2025 · similarity 0.91)
- NavMorph: A Self-Evolving World Model for Vision-and-Language Navigation in Continuous Environments (ICCV 2025 · similarity 0.91)
- Agent Journey Beyond RGB: Hierarchical Semantic-Spatial Representation Enrichment for Vision-and-Language Navigation (AAAI 2026 · similarity 0.91)
- NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models (AAAI 2024 · similarity 0.90)
- NavBench: Probing Multimodal Large Language Models for Embodied Navigation (NeurIPS 2025 · similarity 0.89)
- STRIDER: Navigation via Instruction-Aligned Structural Decision Space Optimization (NeurIPS 2025 · similarity 0.89)
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.
