Research map / Multi-agent systems and games / Human-AI and goal-conditioned
EnvEdit: Environment Editing 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 |
|---|---|---|---|
| Add edited-environment augmentation to HAMT and ensemble the resulting agents | HAMT · R2R test unseen | SR: 3.2% | Helped |
| Add edited-environment augmentation to HAMT and ensemble the resulting agents | HAMT · R2R test unseen | SPL: 3.9% | Helped |
| Add edited-environment augmentation to HAMT and ensemble the resulting agents | HAMT · RxR test unseen | nDTW: 4.7% | Helped |
| Add edited-environment augmentation to HAMT and ensemble the resulting agents | HAMT · RxR test unseen | sDTW: 6.6% | Helped |
| Add style-transfer environment augmentation | EnvDrop · R2R val-unseen | SR: 5.2% | Helped |
| Use different styles across views within a panorama instead of one shared style (ablation) | E_st-16 · R2R val-unseen | SR: 2.3% | Hurt |
| Use different styles across views within a panorama instead of one shared style (ablation) | E_st-16 · R2R val-unseen | SPL: 1.7% | Hurt |
| Use one fixed style for the whole environment rather than varying style by viewpoint (ablation) | E_st-16 · R2R val-unseen | SR: 2.4% | Hurt |
| Use a style-aware speaker instead of the baseline speaker for back translation (ablation) | E_st-32 + back translation · R2R val-unseen | SR: 59.0 -> 60.2 | Helped |
| Use a style-aware speaker instead of the baseline speaker for back translation (ablation) | E_is1m-16 + back translation · R2R val-unseen | SR: 60.2 -> 60.8 | Helped |
| Ensemble agents trained on E_st, E_is1, and E_is1m instead of using E_st alone | EnvDrop · R2R val-unseen | SR: 0.6% | Helped |
| Mask out more object classes in edited environments (ablation) | E_is1m-16 · R2R val-unseen | SR | Hurt |
Closest papers by meaning
- General Scene Adaptation for Vision-and-Language Navigation (ICLR 2025 · similarity 0.89)
- Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-Training (CVPR 2020 · similarity 0.88)
- Improving Vision-and-Language Navigation by Generating Future-View Image Semantics (CVPR 2023 · similarity 0.88)
- NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models (AAAI 2024 · similarity 0.86)
- NavBench: Probing Multimodal Large Language Models for Embodied Navigation (NeurIPS 2025 · similarity 0.85)
- Human-Aware Vision-and-Language Navigation: Bridging Simulation to Reality with Dynamic Human Interactions (NeurIPS 2024 · similarity 0.85)
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.