Research map / Vision-language and multimodal / Robot action and navigation
HOP: History-and-Order Aware Pre-Training 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 |
|---|---|---|---|
| Pre-train with PREVALENT and BnB data, using all five proxy tasks (ablation) | HOP · REVERIE validation unseen | RGSPL: 15.31 -> 15.73 | Helped |
| Add MLM pre-training (ablation) | HOP · R2R validation unseen | SR: 54.19 -> 60.75 | Helped |
| Add TIM to MLM pre-training (ablation) | HOP · R2R validation unseen | SR: 60.75 -> 61.52 | Helped |
| Add TOM to MLM pre-training (ablation) | HOP · R2R validation unseen | SR: 60.75 -> 61.81 | Helped |
| Add GOM to MLM pre-training (ablation) | HOP · R2R validation unseen | SR: 60.75 -> 61.98 | Helped |
| Add APH to MLM pre-training (ablation) | HOP · R2R validation unseen | SR: 60.75 -> 62.01 | Helped |
| Add action prediction without history instead of APH (ablation) | HOP · R2R validation unseen | SR: 62.01 -> 61.27 | Hurt |
| Combine TIM, TOM, and GOM with MLM (ablation) | HOP · R2R validation unseen | SR: 60.75 -> 63.09 | Helped |
| Add APH to MLM, TIM, TOM, and GOM (ablation) | HOP · R2R validation unseen | SR: 63.09 -> 63.86 | Helped |
| Remove pre-training (ablation) | HOP · R2R validation unseen | SR: 63.86 -> 54.19 | Hurt |
| Add PREVALENT and BnB* data to pre-training (ablation) | HOP · R2R validation unseen | SPL: 57.07 -> 57.22 | Helped |
| Use HOP pre-training rather than no pre-training (ablation) | HOP · R2R test unseen | SPL: 50 -> 59 | Helped |
Closest papers by meaning
- Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-Training (CVPR 2020 · similarity 0.90)
- Improving Vision-and-Language Navigation by Generating Future-View Image Semantics (CVPR 2023 · similarity 0.90)
- History to Future: Evolving Agent with Experience and Thought for Zero-shot Vision-and-Language Navigation (CVPR 2026 · similarity 0.89)
- NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models (AAAI 2024 · similarity 0.88)
- Towards Long-Horizon Vision-Language Navigation: Platform, Benchmark and Method (CVPR 2025 · similarity 0.87)
- WorldVLN: Autoregressive World Action Model for Aerial Vision-Language Navigation (NeurIPS 2026 · similarity 0.87)
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.