# FutureNav: Unified World-Action Modeling for Vision-and-Language Navigation

arXiv: https://arxiv.org/abs/2606.30367 · HTML: https://mlsanity.com/paper/2606.30367/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in World models for navigation, one of 11 directions in World models.
- Builds on 37 of its 79 references that are in the map.
- First posted on arXiv 29 Jun 2026.

## Placed in

- World models / [World models for navigation](https://mlsanity.com/wm/world-models-for-navigation/)

## Builds on (most cited first, 30 of 37)

- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [Matterport3D: Learning from RGB-D Data in Indoor Environments](https://mlsanity.com/paper/1709.06158/) (2017)
- [Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding](https://mlsanity.com/paper/2010.07954/) (2020)
- [Fast-WAM: Do World Action Models Need Test-time Future Imagination?](https://mlsanity.com/paper/2603.16666/) (2026)
- [Navigation World Models](https://mlsanity.com/paper/2412.03572/) (2024)
- [NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation](https://mlsanity.com/paper/2402.15852/) (2024)
- [NaVILA: Legged Robot Vision-Language-Action Model for Navigation](https://mlsanity.com/paper/2412.04453/) (2024)
- [InstructNav: Zero-shot System for Generic Instruction Navigation in Unexplored Environment](https://mlsanity.com/paper/2406.04882/) (2024)
- [Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks](https://mlsanity.com/paper/2412.06224/) (2024)
- [Pathdreamer: A World Model for Indoor Navigation](https://mlsanity.com/paper/2105.08756/) (2021)
- [StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modeling](https://mlsanity.com/paper/2507.05240/) (2025)
- [RoboBrain 2.0 Technical Report](https://mlsanity.com/paper/2507.02029/) (2025)
- [NavCoT: Boosting LLM-Based Vision-and-Language Navigation via Learning Disentangled Reasoning](https://mlsanity.com/paper/2403.07376/) (2024)
- [Ground Slow, Move Fast: A Dual-System Foundation Model for Generalizable Vision-and-Language Navigation](https://mlsanity.com/paper/2512.08186/) (2025)
- [NavMorph: A Self-Evolving World Model for Vision-and-Language Navigation in Continuous Environments](https://mlsanity.com/paper/2506.23468/) (2025)
- [Sim-to-Real Transfer via 3D Feature Fields for Vision-and-Language Navigation](https://mlsanity.com/paper/2406.09798/) (2024)
- [MiMo-Embodied: X-Embodied Foundation Model Technical Report](https://mlsanity.com/paper/2511.16518/) (2025)
- [1st Place Solutions for RxR-Habitat Vision-and-Language Navigation Competition (CVPR 2022)](https://mlsanity.com/paper/2206.11610/) (2022)
- [OA-WAM: Object-Addressable World Action Model for Robust Robot Manipulation](https://mlsanity.com/paper/2605.06481/) (2026)
- [TriHelper: Zero-Shot Object Navigation with Dynamic Assistance](https://mlsanity.com/paper/2403.15223/) (2024)
- [AstraNav-World: World Model for Foresight Control and Consistency](https://mlsanity.com/paper/2512.21714/) (2025)
- [MonoDream: Monocular Vision-Language Navigation with Panoramic Dreaming](https://mlsanity.com/paper/2508.02549/) (2025)
- [NavForesee: A Unified Vision-Language World Model for Hierarchical Planning and Dual-Horizon Navigation Prediction](https://mlsanity.com/paper/2512.01550/) (2025)
- [NavA3: Understanding Any Instruction, Navigating Anywhere, Finding Anything](https://mlsanity.com/paper/2508.04598/) (2025)
- [WorldVLN: Autoregressive World Action Model for Aerial Vision-Language Navigation](https://mlsanity.com/paper/2605.15964/) (2026)
- [HumanoidPano: Hybrid Spherical Panoramic-LiDAR Cross-Modal Perception for Humanoid Robots](https://mlsanity.com/paper/2503.09010/) (2025)
- [Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation](https://mlsanity.com/paper/2604.18486/) (2026)
- [WAM-Nav: Asymmetric Latent World-Action Modeling for Unified Visual Navigation](https://mlsanity.com/paper/2606.04907/) (2026)
- [VISTAv2: World Imagination for Indoor Vision-and-Language Navigation](https://mlsanity.com/paper/2512.00041/) (2025)
- [MeshMimic: Geometry-Aware Humanoid Motion Learning through 3D Scene Reconstruction](https://mlsanity.com/paper/2602.15733/) (2026)

## Built on by (most cited first, 7 of 7)

- [WNM-3D: A World Navigation Model with 3D Scene Conditioning for Closed-Loop VLN](https://mlsanity.com/paper/2608.07267/) (2026)
- [WAVE-Go: World-Model Navigation with Adaptive Execution for Wheel-Legged Robots](https://mlsanity.com/paper/2609.18193/) (2026)
- [Skytopia: Monocular Drone Navigation with Action-Conditioned Latent World Models](https://mlsanity.com/paper/2609.26007/) (2026)
- [FINE: Future-Informed Navigation Encoding for Data-Efficient Vision-Language Navigation](https://mlsanity.com/paper/2609.32855/) (2026)
- [ForeFly: A Dual-Horizon World Action Model for Aerial Vision-Language Navigation](https://mlsanity.com/paper/2609.33581/) (2026)
- [GuidedNav: Shaping Vision-Language Navigation Representations through Pre-action Attention and Spatial Guidance](https://mlsanity.com/paper/2610.13122/) (2026)
- [MemoryVLN: From Ego-Aware Memory Representation to Cross-Context Memory Reuse in Vision-Language Navigation](https://mlsanity.com/paper/2610.18478/) (2026)

## Abstract (arXiv)

Vision-and-language navigation (VLN) in continuous environments requires an agent to ground instructions in egocentric observations while maintaining spatial understanding across long action sequences. Recent navigation foundation models have shown strong progress by scaling vision-language models, but they often learn navigation primarily as direct action generation, without explicitly modeling world states or predicting their future evolution. We introduce FutureNav, a VLM-based unified world-action modeling framework for vision-and-language navigation. Specifically, FutureNav jointly encodes text, visual, and spatial features and feeds them into the LLM, and optimizes four objectives for simultaneous world and action modeling: an action policy objective for navigation action prediction, inverse and forward dynamics objectives for modeling state transitions, and a future generation objective for predicting future spatial states. This unified architecture strengthens action prediction while explicitly modeling the world, without sacrificing inference speed. Extensive experiments show that, with only a 4B-scale backbone, FutureNav achieves state-of-the-art performance on multiple VLN benchmarks and substantially outperforms prior VLN methods, paving the way toward future world-action models for VLN. We will release the code and models to support future research.