Research map / Vision-language and multimodal / Robot action and navigation
CorrectNav: Self-Correction Flywheel Empowers Vision-Language-Action Navigation Model
Zhuoyuan Yu, Yuxing Long, Zihan Yang, Chengyan Zeng, Hongwei Fan, Jiyao Zhang, Hao Dong
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 Navigation Trajectory Correction data (ablation) | CorrectNav (1st iteration) · R2R-CE Val-Unseen | SR (%): 59.2 -> 63.0 | Improved |
| add Navigation Trajectory Correction data (ablation) | CorrectNav (1st iteration) · RxR-CE Val-Unseen | SR (%): 60.7 -> 63.1 | Improved |
| add error-correcting keyframe perception data (ablation) | CorrectNav (1st iteration) · R2R-CE Val-Unseen | SR (%): 60.1 -> 63.0 | Improved |
| add data sampling strategy (ablation) | CorrectNav (1st iteration) · R2R-CE Val-Unseen | SR (%): 60.0 -> 63.0 | Improved |
| add data sampling strategy (ablation) | CorrectNav (1st iteration) · RxR-CE Val-Unseen | SR (%): 62.2 -> 63.1 | Improved |
| add self-correction flywheel iterations 1 to 3 (ablation) | CorrectNav · R2R-CE and RxR-CE Val-Unseen | SR | Improved |
| add a fourth flywheel iteration (ablation) | CorrectNav · R2R-CE and RxR-CE Val-Unseen | SR | Hurt |
| CorrectNav vs StreamVLN with monocular RGB only | CorrectNav · R2R-CE Val-Unseen | SR (%): 56.9 -> 65.1 | Improved |
| CorrectNav vs StreamVLN | CorrectNav · RxR-CE Val-Unseen | SR (%): 52.9 -> 69.3 | Improved |
| CorrectNav vs NaVILA on complex real-world instructions (Home) | CorrectNav · Real-world Home complex | SR: 0.10 -> 0.80 | Improved |
Later papers that compared with this method
4 later accepted papers report CorrectNav as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.
- NavForesee: A Unified Vision-Language World Model for Hierarchical Planning and Dual-Horizon Navigation Prediction (CVPR 2026 · better on 3 of 7 shared results)
- MobileVLA-R1: Reinforcing Vision-Language-Action for Mobile Robots (ECCV 2026 · better on 4 of 4 shared results)
- OmniNav: A Unified Framework for Prospective Exploration and Visual-Language Navigation (ICLR 2026 · better on 2 of 2 shared results)
- One Scan is Enough: Demonstration-Free Adaptation for Language-Guided Navigation (NeurIPS 2026 · better on 2 of 2 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- CoT-VLNBench: A Benchmark for Visual Chain-of-Thought Reasoning in Vision-Language-Navigation Robots (AAAI 2026 · similarity 0.88)
- ElegantVLA: Learning When to Think for Efficient Vision-Language-Action Models (NeurIPS 2026 · similarity 0.87)
- Bootstrapping Language-Guided Navigation Learning with Self-Refining Data Flywheel (ICLR 2025 · similarity 0.86)
- Towards Realistic UAV Vision-Language Navigation: Platform, Benchmark, and Methodology (ICLR 2025 · similarity 0.86)
- WorldVLN: Autoregressive World Action Model for Aerial Vision-Language Navigation (NeurIPS 2026 · similarity 0.86)
- PriorVLA: Prior-Preserving Adaptation for Vision-Language-Action Models (NeurIPS 2026 · 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.
