# NavMorph: A Self-Evolving World Model for Vision-and-Language Navigation in Continuous Environments

Source: [NavMorph: A Self-Evolving World Model for Vision-and-Language Navigation in Continuous Environments](<https://www.sota2.com/research/paper/68fa7a2d1e209131cea81913>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:14:13.950Z

Authors: Xuan Yao, Junyu Gao, Changsheng Xu

Published: 2025-06-30T02:20:00.000Z

## Abstract

Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires agents to execute sequential navigation actions in complex environments guided by natural language instructions. Current approaches often struggle with generalizing to novel environments and adapting to ongoing changes during navigation. Inspired by human cognition, we present NavMorph, a self-evolving world model framework that enhances environmental understanding and decision-making in VLN-CE tasks. NavMorph employs compact latent representations to model environmental dynamics, equipping agents with foresight for adaptive planning and policy refinement. By integrating a novel Contextual Evolution Memory, NavMorph leverages scene-contextual information to support effective navigation while maintaining online adaptability. Extensive experiments demonstrate that our method achieves notable performance improvements on popular VLN-CE benchmarks. Code is available at https://github.com/Feliciaxyao/NavMorph.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Vision-and-Language Navigation on R2R-CE unseen continuous (val)](<https://www.sota2.com/research/sota/vision-and-language-navigation-on-r2r-ce-unseen-continuous-val.md>): Vision-and-Language Navigation; R2R-CE unseen continuous (val); SR: 47.9.

- [Vision-Language Navigation on RxR (val-unseen)](<https://www.sota2.com/research/sota/vision-language-navigation-on-rxr-val-unseen.md>): Vision-Language Navigation; RxR (val-unseen); Success Rate (SR): 30.8.

- [Vision-and-Language Navigation on R2R (val unseen)](<https://www.sota2.com/research/sota/vision-and-language-navigation-on-r2r-val-unseen.md>): Vision-and-Language Navigation; R2R (val unseen); Success Rate (SR): 47.9.

- [Vision-Language Navigation on RxR-CE (val-unseen)](<https://www.sota2.com/research/sota/vision-language-navigation-on-rxr-ce-val-unseen.md>): Vision-Language Navigation; RxR-CE (val-unseen); SR: 30.8.

- [Vision-Language Navigation on R2R-CE (val-unseen)](<https://www.sota2.com/research/sota/vision-language-navigation-on-r2r-ce-val-unseen.md>): Vision-Language Navigation; R2R-CE (val-unseen); Success Rate (SR): 47.9.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2506.23468>)

[PDF](<https://arxiv.org/pdf/2506.23468.pdf>)