# SimpleVLN: A Vision-Language Navigation Framework Without Task-Specific Architectures

- Source: arXiv cs.RO
- Published: 2026-10-19T04:00:00.000Z
- RoboHot: https://robohot.news/en/items/ohmv5qq3y4th2sy3io6rio6yh
- Original: https://arxiv.org/abs/2610.23203

## Summary

SimpleVLN is a vision-language navigation (VLN) framework that preserves the native architecture, achieving success rates of 76.7% and 80.1% on the R2R-CE and RxR-CE splits, respectively, significantly outperforming existing methods.