# Multi-View Learning for Vision-and-Language Navigation

arXiv: https://arxiv.org/abs/2003.00857 · HTML: https://mlsanity.com/paper/2003.00857/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Mar 2020.

## Built on by (most cited first, 11 of 11)

- [Vision-and-Language Navigation: A Survey of Tasks, Methods, and Future Directions](https://mlsanity.com/paper/2203.12667/) (2022)
- [Vision-and-Language Navigation Today and Tomorrow: A Survey in the Era of Foundation Models](https://mlsanity.com/paper/2407.07035/) (2024)
- [Diagnosing Vision-and-Language Navigation: What Really Matters](https://mlsanity.com/paper/2103.16561/) (2021)
- [Vision-Language Navigation: A Survey and Taxonomy](https://mlsanity.com/paper/2108.11544/) (2021)
- [Improving Cross-Modal Alignment in Vision Language Navigation via Syntactic Information](https://mlsanity.com/paper/2104.09580/) (2021)
- [MLANet: Multi-Level Attention Network with Sub-instruction for Continuous Vision-and-Language Navigation](https://mlsanity.com/paper/2303.01396/) (2023)
- [CLEAR: Improving Vision-Language Navigation with Cross-Lingual, Environment-Agnostic Representations](https://mlsanity.com/paper/2207.02185/) (2022)
- [Neural Brain: A Neuroscience-inspired Framework for Embodied Agents](https://mlsanity.com/paper/2505.07634/) (2025)
- [Vision-Language Navigation with Embodied Intelligence: A Survey](https://mlsanity.com/paper/2402.14304/) (2024)
- [Deep Learning for Embodied Vision Navigation: A Survey](https://mlsanity.com/paper/2108.04097/) (2021)
- [What Limits Vision-and-Language Navigation ?](https://mlsanity.com/paper/2605.13328/) (2026)

## Abstract (arXiv)

Learning to navigate in a visual environment following natural language instructions is a challenging task because natural language instructions are highly variable, ambiguous, and under-specified. In this paper, we present a novel training paradigm, Learn from EveryOne (LEO), which leverages multiple instructions (as different views) for the same trajectory to resolve language ambiguity and improve generalization. By sharing parameters across instructions, our approach learns more effectively from limited training data and generalizes better in unseen environments. On the recent Room-to-Room (R2R) benchmark dataset, LEO achieves 16% improvement (absolute) over a greedy agent as the base agent (25.3% rightarrow 41.4%) in Success Rate weighted by Path Length (SPL). Further, LEO is complementary to most existing models for vision-and-language navigation, allowing for easy integration with the existing techniques, leading to LEO+, which creates the new state of the art, pushing the R2R benchmark to 62% (9% absolute improvement).