# ForeFly: A Dual-Horizon World Action Model for Aerial Vision-Language Navigation

arXiv: https://arxiv.org/abs/2609.33581 · HTML: https://mlsanity.com/paper/2609.33581/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in World models for navigation, one of 11 directions in World models.
- Builds on 22 of its 58 references that are in the map.
- First posted on arXiv 27 Sep 2026.

## Placed in

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

## Builds on (most cited first, 22 of 22)

- [Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments](https://mlsanity.com/paper/1711.07280/) (2017)
- [World Action Models are Zero-shot Policies](https://mlsanity.com/paper/2602.15922/) (2026)
- [WorldVLA: Towards Autoregressive Action World Model](https://mlsanity.com/paper/2506.21539/) (2025)
- [NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation](https://mlsanity.com/paper/2402.15852/) (2024)
- [Large Video Planner Enables Generalizable Robot Control](https://mlsanity.com/paper/2512.15840/) (2025)
- [Aerial Vision-and-Dialog Navigation](https://mlsanity.com/paper/2205.12219/) (2022)
- [DriveWorld-VLA: Unified Latent-Space World Modeling with Vision-Language-Action for Autonomous Driving](https://mlsanity.com/paper/2602.06521/) (2026)
- [AutoFly: Vision-Language-Action Model for UAV Autonomous Navigation in the Wild](https://mlsanity.com/paper/2602.09657/) (2026)
- [LongFly: Long-Horizon UAV Vision-and-Language Navigation with Spatiotemporal Context Integration](https://mlsanity.com/paper/2512.22010/) (2025)
- [WorldVLN: Autoregressive World Action Model for Aerial Vision-Language Navigation](https://mlsanity.com/paper/2605.15964/) (2026)
- [OpenVLN: Open-world Aerial Vision-Language Navigation](https://mlsanity.com/paper/2511.06182/) (2025)
- [RAVEN: Resilient Aerial Navigation via Open-Set Semantic Memory and Behavior Adaptation](https://mlsanity.com/paper/2509.23563/) (2025)
- [MindDriver: Introducing Progressive Multimodal Reasoning for Autonomous Driving](https://mlsanity.com/paper/2602.21952/) (2026)
- [Aerial Vision-Language Navigation with a Unified Framework for Spatial, Temporal and Embodied Reasoning](https://mlsanity.com/paper/2512.08639/) (2025)
- [Diffusion Models for Smarter UAVs: Decision-Making and Modeling](https://mlsanity.com/paper/2501.05819/) (2025)
- [FutureNav: Unified World-Action Modeling for Vision-and-Language Navigation](https://mlsanity.com/paper/2606.30367/) (2026)
- [WorldFly: A World-Model-Based Vision-Language-Action Model for UAV Navigation](https://mlsanity.com/paper/2606.06147/) (2026)
- [Vision-and-Language Navigation for UAVs: Progress, Challenges, and a Research Roadmap](https://mlsanity.com/paper/2604.13654/) (2026)
- [SpatialFly: Implicit 3D Prior-Guided Visual Reparameterization for Continuous UAV Vision-and-Language Navigation](https://mlsanity.com/paper/2603.21046/) (2026)
- [Think Like a Pilot: Fine-Grained Long-Horizon UAV Navigation](https://mlsanity.com/paper/2606.06836/) (2026)
- [Anticipate Before Acting: Future-State-Conditioned Vision-Language Navigation](https://mlsanity.com/paper/2607.18042/) (2026)
- [VoLN: Vision-Only Long-Horizon Navigation---Paradigm, Benchmark, and Method](https://mlsanity.com/paper/2607.21400/) (2026)

## Abstract (arXiv)

Aerial Vision-Language Navigation (AVLN) requires UAVs to maintain reliable instruction following over long trajectories in complex 3D environments. However, existing AVLN approaches are predominantly reactive or limited to single-horizon prediction, overlooking complementary future cues across different temporal horizons. To address this limitation, we propose ForeFly, a dual-horizon latent world action model that predicts both a proximal future for local continuity and an adaptive route-critical future for long-range guidance. Horizon-specific foresight queries are primed with recent and route-critical visual memories, providing history-aware context for future prediction. To exploit their distinct roles in action generation, we introduce Foresight-Guided Action Refinement (FGAR), which asymmetrically exploits proximal foresight for local action enhancement and route-critical foresight for feature-wise correction and route-level guidance. Experiments on the TravelUAV and UAV-ON benchmarks show that ForeFly consistently outperforms strong baselines across seen and unseen settings, validating the effectiveness of dual-horizon foresight and FGAR learning. The code is available at: https://github.com/kunhuiW/ForeFly