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

• URL: http://arxiv.org/abs/2608.07548v1
• Date: Sat, 01 Aug 2026 03:17:48 GMT
• Title: SC$^{2}$-WM: A Self-Correcting World Model with Closed-Loop Feedback for Vision-and-Language Navigation in Continuous Environments
• Abstract summary: We propose SC$2$-WM, a self-correcting world model framework that introduces internal feedback for closed-loop decision making in VLN-CE.<n>Our method derives feedback from world-model foresight to perform state-level plan refinement before action execution.<n>Experiments on standard VLN-CE benchmarks demonstrate improved navigation and generalization.
• Score: 54.76467884696539
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• FlowDec: Temporal Conditional Flow Decorruptor for Robust Continuous Vision-Language Navigation [8.00310534826872]
  Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires agents to follow natural-language instructions in unseen scenes.<n>We introduce Temporal Flow Decorruptor (FlowDec), a novel image restoration framework tailored for LM-based VLN-CE.<n>FlowDec outperforms state-of-the-art decorruption methods in both navigation accuracy and generation latency.
  arXiv  Detail & Related papers  (2026-06-21T10:24:16Z)
• WorldFly: A World-Model-Based Vision-Language-Action Model for UAV Navigation [42.8714305455232]
  We argue that the ability to "imagine" future states is critical for robust decision-making under such partial observability.<n>We propose WorldFly, a novel world-model-based VLA framework that employs a dual-branch coupled flow matching mechanism to jointly generate future video predictions and navigation actions.
  arXiv  Detail & Related papers  (2026-06-04T13:23:05Z)
• WorldArena 2.0: Extending Embodied World Model Benchmarking on Modality, Functionality and Platform [130.8118909583659]
  We introduce WorldArena 2.0, an expanded benchmark for embodied world model evaluation.<n>WorldArena 2.0 systematically broadens embodied world model evaluation along three dimensions: modality, functionality, and platform.<n>Under a standardized protocol, WorldArena 2.0 comprehensively evaluates perceptual quality, interactive utility, and cross-platform performance.
  arXiv  Detail & Related papers  (2026-05-18T06:18:21Z)
• User-Feedback-Driven Continual Adaptation for Vision-and-Language Navigation [50.51140007672333]
  Vision-and-Language Navigation (VLN) requires agents to navigate complex environments by following natural-language instructions.<n>Current GSA-VLN frameworks exclude user feedback, relying solely on unsupervised adaptation from repeated environmental exposure.<n>We introduce a user-feedback-driven adaptation framework that extends GSA-VLN by systematically integrating human interactions into continual learning.
  arXiv  Detail & Related papers  (2025-12-11T06:11:45Z)
• Fast-SmartWay: Panoramic-Free End-to-End Zero-Shot Vision-and-Language Navigation [16.632191523127865]
  Fast-SmartWay is an end-to-end zero-shot VLN-CE framework that eliminates the need for panoramic views and waypoint predictors.<n>Our approach uses only three frontal RGB-D images combined with natural language instructions, enabling MLLMs to directly predict actions.
  arXiv  Detail & Related papers  (2025-11-02T13:21:54Z)
• VLN-Zero: Rapid Exploration and Cache-Enabled Neurosymbolic Vision-Language Planning for Zero-Shot Transfer in Robot Navigation [52.00474922315126]
  We present VLN-Zero, a vision-language navigation framework for unseen environments.<n>We use vision-language models to efficiently construct symbolic scene graphs and enable zero-shot neurosymbolic navigation.<n>VLN-Zero achieves 2x higher success rate compared to state-of-the-art zero-shot models, outperforms most fine-tuned baselines, and reaches goal locations in half the time.
  arXiv  Detail & Related papers  (2025-09-23T03:23:03Z)
• TrajBooster: Boosting Humanoid Whole-Body Manipulation via Trajectory-Centric Learning [79.59753528758361]
  We present TrajBooster, a cross-embodiment framework that leverages abundant wheeled-humanoid data to boost bipedal VLA.<n>Our key idea is to use end-effector trajectories as a morphology-agnostic interface.<n>Results show that TrajBooster allows existing wheeled-humanoid data to efficiently strengthen bipedal humanoid VLA performance.
  arXiv  Detail & Related papers  (2025-09-15T12:25:39Z)
• View Invariant Learning for Vision-Language Navigation in Continuous Environments [1.2530458935333404]
  Vision-Language Navigation in Continuous Environments (VLNCE) is a key research problem in embodied AI.<n>Most navigation policies are sensitive to viewpoint changes, i.e., variations in camera height and viewing angle that alter the agent's observation.<n>We propose VIL (View Invariant Learning), a view-invariant post-training strategy that enhances the robustness of existing navigation policies to changes in camera viewpoint.
  arXiv  Detail & Related papers  (2025-07-05T18:04:35Z)
• NavMorph: A Self-Evolving World Model for Vision-and-Language Navigation in Continuous Environments [67.18144414660681]
  Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires agents to execute sequential navigation actions in complex environments guided by natural language instructions.<n>Inspired by human cognition, we present NavMorph, a self-evolving world model framework that enhances environmental understanding and decision-making in VLN-CE tasks.
  arXiv  Detail & Related papers  (2025-06-30T02:20:00Z)
• VLN-R1: Vision-Language Navigation via Reinforcement Fine-Tuning [77.34267241692706]
  Vision-Language Navigation (VLN) is a core challenge in embodied AI, requiring agents to navigate real-world environments using natural language instructions.<n>We propose VLN-R1, an end-to-end framework that leverages Large Vision-Language Models (LVLM) to directly translate egocentric video streams into continuous navigation actions.
  arXiv  Detail & Related papers  (2025-06-20T17:59:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.