AI Paper Atlas

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

ICML 2026 · Vision-language and multimodal › Robot action and navigation · approach: Pretraining and data augmentation for VLN · 0 citations (OpenAlex)

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 changedWhereMeasuredEffect
add feedback-guided state-level plan refinement (ablation)VLN-3DFF base · R2R-CE Val Unseen (monocular)SR: 43.77 -> 48.34Improved
add Visual Calibration Module (episodic memory) (ablation)SC2-WM with state-level correction · R2R-CE Val Unseen (monocular)SPL: 33.02 -> 36.05Improved
add conditional world-aware adaptation (model-level correction) (ablation)SC2-WM with VCM · R2R-CE Val Unseen (monocular)SR: 49.86 -> 50.90Improved
feedback-triggered adaptation instead of fixed-interval adaptation (T = 2) (ablation)SC2-WM · R2R-CE Val Unseen (monocular)SPL: 36.58 -> 37.17Improved
add reconstruction loss Lrec (ablation)SC2-WM · R2R-CE Val Unseen (monocular)SPL: 34.58 -> 37.17Improved
add SC2-WM on VLN-3DFFVLN-3DFF · R2R-CE Val Unseen (monocular)TL: 26.16 -> 17.65Improved
add SC2-WM on VLN-3DFFVLN-3DFF · RxR-CE Val Unseen (monocular)SR: 26.7 -> 35.8Improved
add SC2-WM on HNRHNR · R2R-CE Val Unseen (panoramic)SR: 61 -> 66Improved
add SC2-WM on ETPNavETPNav · R2R-CE Val Unseen (panoramic)SR: 57 -> 59Improved
add SC2-WM on ETPNavETPNav · RxR-CE Val Unseen (panoramic)SR: 55 -> 57Improved

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy