Research map / Vision-language and multimodal / Robot action and navigation
SC$^{2}$-WM: A Self-Correcting World Model with Closed-Loop Feedback for Vision-and-Language Navigation in Continuous Environments
Xuan Yao, Yuze Zhu, Junyu Gao, Zongmeng Wang, Changsheng Xu
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 feedback-guided state-level plan refinement (ablation) | VLN-3DFF base · R2R-CE Val Unseen (monocular) | SR: 43.77 -> 48.34 | Improved |
| add Visual Calibration Module (episodic memory) (ablation) | SC2-WM with state-level correction · R2R-CE Val Unseen (monocular) | SPL: 33.02 -> 36.05 | Improved |
| add conditional world-aware adaptation (model-level correction) (ablation) | SC2-WM with VCM · R2R-CE Val Unseen (monocular) | SR: 49.86 -> 50.90 | Improved |
| feedback-triggered adaptation instead of fixed-interval adaptation (T = 2) (ablation) | SC2-WM · R2R-CE Val Unseen (monocular) | SPL: 36.58 -> 37.17 | Improved |
| add reconstruction loss Lrec (ablation) | SC2-WM · R2R-CE Val Unseen (monocular) | SPL: 34.58 -> 37.17 | Improved |
| add SC2-WM on VLN-3DFF | VLN-3DFF · R2R-CE Val Unseen (monocular) | TL: 26.16 -> 17.65 | Improved |
| add SC2-WM on VLN-3DFF | VLN-3DFF · RxR-CE Val Unseen (monocular) | SR: 26.7 -> 35.8 | Improved |
| add SC2-WM on HNR | HNR · R2R-CE Val Unseen (panoramic) | SR: 61 -> 66 | Improved |
| add SC2-WM on ETPNav | ETPNav · R2R-CE Val Unseen (panoramic) | SR: 57 -> 59 | Improved |
| add SC2-WM on ETPNav | ETPNav · RxR-CE Val Unseen (panoramic) | SR: 55 -> 57 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- ETPNav* — ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environments (TPAMI 2024) · better on 3 of 3 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
- Toward a Causally-Inspired Evolving World Model for Vision-and-Language Navigation in Continuous Environments (TPAMI 2026 · similarity 0.92)
- NavMorph: A Self-Evolving World Model for Vision-and-Language Navigation in Continuous Environments (ICCV 2025 · similarity 0.90)
- Space-Aware World Models: Spatial Persistence Through Factored Scene Representations (NeurIPS 2026 · similarity 0.89)
- WorldVLN: Autoregressive World Action Model for Aerial Vision-Language Navigation (NeurIPS 2026 · similarity 0.88)
- STRIDER: Navigation via Instruction-Aligned Structural Decision Space Optimization (NeurIPS 2025 · similarity 0.87)
- Test-Time Adaptation for Online Vision-Language Navigation with Feedback-based Reinforcement Learning (ICML 2025 · 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.
