ROCVAug 1

SC$^{2}$-WM: A Self-Correcting World Model with Closed-Loop Feedback for Vision-and-Language Navigation in Continuous Environments

arXiv:2608.0754810.0Has CodeICML
Predicted impact top 18% in RO · last 90 daysOriginality Incremental advance
AI Analysis

This work addresses the specific bottleneck of error correction in VLN-CE, offering a novel method for a known problem, but the improvements are incremental and domain-specific.

The paper tackles the problem of internal state drift in Vision-and-Language Navigation in Continuous Environments (VLN-CE), where agents lack mechanisms to correct errors during inference. They propose SC2-WM, a self-correcting world model framework with closed-loop feedback, achieving improved navigation robustness and generalization on standard benchmarks.

Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires agents to make fine-grained navigation decisions under partial observability. However, most existing methods rely on open-loop execution, lacking mechanisms to detect and correct internal state drift during inference. We propose SC$^{2}$-WM, a self-correcting world model framework that introduces internal feedback for closed-loop decision making in VLN-CE. Our method derives feedback from world-model foresight to perform state-level plan refinement before action execution. To handle challenging scenarios, we further introduce conditional world-aware adaptation, which enables model-level correction by selectively updating the world model at test time when feedback indicates model capacity insufficiency. Experiments on standard VLN-CE benchmarks demonstrate improved navigation robustness and generalization. Our code is available at https://github.com/sunrise-ikun/SC2_WM.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes