Research map / Vision-language and multimodal / Human and embodied modeling
Grounded Entity-Landmark Adaptive Pre-Training for Vision-and-Language Navigation
Yibo Cui, Liang Xie, Yakun Zhang, Meishan Zhang, Ye Yan, Erwei Yin
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 |
|---|---|---|---|
| add GELA adaptive pre-training to HAMT (none aug) | HAMT · R2R val unseen | SR: 65.7 -> 69.2 | Improved |
| add GELA adaptive pre-training to HAMT | HAMT · R2R val unseen (NE) | NE: 2.29 -> 3.33 | Hurt |
| add EPP alone (ablation) | HAMT · R2R val unseen (none aug) | SR: 65.7 -> 65.8 | No clear effect |
| add LBP alone (ablation) | HAMT · R2R val unseen (none aug) | SR: 65.7 -> 65.6 | No clear effect |
| add ELSA alone (ablation) | HAMT · R2R val unseen (none aug) | SR: 65.7 -> 66.3 | Improved |
| combine EPP and LBP (ablation) | HAMT · R2R val unseen (none aug) | SR: 65.8 -> 67.0 | Improved |
| add ELSA on top of EPP+LBP (ablation) | GELA · R2R val unseen (none aug) | SR: 67.0 -> 69.2 | Improved |
| use scene entities only (ablation) | GELA · R2R val unseen (none aug) | SR: 65.7 -> 66.7 | Improved |
| use both object and scene entities versus object only (ablation) | GELA · R2R val unseen (none aug) | SR: 66.8 -> 69.2 | Improved |
| GELA vs HAMT on CVDN val seen | HAMT · CVDN val seen | Goal Progress (m): 6.91 -> 8.57 | Improved |
Closest papers by meaning
- Fine-Grained Alignment Supervision Matters in Vision-and-Language Navigation (TPAMI 2026 · similarity 0.91)
- Landmark-RxR: Solving Vision-and-Language Navigation with Fine-Grained Alignment Supervision (NeurIPS 2021 · similarity 0.90)
- Learning Fine-Grained Alignment for Aerial Vision-Dialog Navigation (AAAI 2025 · similarity 0.89)
- Correctable Landmark Discovery via Large Models for Vision-Language Navigation (TPAMI 2024 · similarity 0.89)
- Less Is More: Generating Grounded Navigation Instructions From Landmarks (CVPR 2022 · similarity 0.88)
- Fine-Grained Verifiers: Preference Modeling as Next-token Prediction in Vision-Language Alignment (ICLR 2025 · 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.
