Turning Adaptation into Assets: Cross-Domain Bridging for Online Vision-Language Navigation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913154933456896 |
|---|---|
| author | Hu, Zixuan Huang, Xuantuo Li, Yancheng Hu, Yichun Xu, Shengyong Duan, Ling-Yu |
| author_facet | Hu, Zixuan Huang, Xuantuo Li, Yancheng Hu, Yichun Xu, Shengyong Duan, Ling-Yu |
| contents | Navigating under non-stationary environment shifts poses a critical challenge for a Vision-and-Language Navigation (VLN) agent deployed in the wild. Yet, existing Test-Time Adaptation (TTA) methods for VLN largely treat online adaptation as transient, isolated updates, leading to catastrophic forgetting and negative transfer. To overcome these issues, we propose Inter-Domain BridgE with Historical Assets (IDEA), a novel TTA framework that transforms adaptation into the accumulation and composition of assets. Specifically, IDEA introduces soft prompts optimized via a Fisher-guided weighting scheme to capture the transferable knowledge. These optimized prompts are then augmented with domain coordinates to form a dynamic asset library. Leveraging this library, IDEA constructs a cross-domain bridge by projecting the target domain onto the convex hull of historical knowledge. These designs form a complementary loop: the evolving library underpins bridge construction, while the bridge provides superior initialization to accelerate asset optimization. Extensive experiments across REVERIE, R2R, and R2R-CE benchmarks demonstrate the consistent superiority of IDEA over existing methods, showcasing its ability to enable training-free adaptation via asset sharing. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_23257 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Turning Adaptation into Assets: Cross-Domain Bridging for Online Vision-Language Navigation Hu, Zixuan Huang, Xuantuo Li, Yancheng Hu, Yichun Xu, Shengyong Duan, Ling-Yu Robotics Computer Vision and Pattern Recognition Navigating under non-stationary environment shifts poses a critical challenge for a Vision-and-Language Navigation (VLN) agent deployed in the wild. Yet, existing Test-Time Adaptation (TTA) methods for VLN largely treat online adaptation as transient, isolated updates, leading to catastrophic forgetting and negative transfer. To overcome these issues, we propose Inter-Domain BridgE with Historical Assets (IDEA), a novel TTA framework that transforms adaptation into the accumulation and composition of assets. Specifically, IDEA introduces soft prompts optimized via a Fisher-guided weighting scheme to capture the transferable knowledge. These optimized prompts are then augmented with domain coordinates to form a dynamic asset library. Leveraging this library, IDEA constructs a cross-domain bridge by projecting the target domain onto the convex hull of historical knowledge. These designs form a complementary loop: the evolving library underpins bridge construction, while the bridge provides superior initialization to accelerate asset optimization. Extensive experiments across REVERIE, R2R, and R2R-CE benchmarks demonstrate the consistent superiority of IDEA over existing methods, showcasing its ability to enable training-free adaptation via asset sharing. |
| title | Turning Adaptation into Assets: Cross-Domain Bridging for Online Vision-Language Navigation |
| topic | Robotics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.23257 |