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

arXiv:2609.33581 · cs.CV · Submitted 2026-09-27 · Read on arXiv

cs.CV

Submitted: 2026-09-27

Updated: 2026-09-27

Code: https://github.com/kunhuiW/ForeFly

Terminology

• Vision-Language Navigation — 18× in this paper
• Foresight-Guided Action Refinement — 15× in this paper
• Aerial Vision-Language Navigation — 10× in this paper
• Benchmark — 10× in this paper · explained in 2 episodes
• Ablation — 7× in this paper · explained in 1 episode
• Conference on Computer Vision and Pattern Recognition — 7× in this paper
• Consistency — 5× in this paper · explained in 3 episodes
• Generalization — 5× in this paper · explained in 13 episodes
• Robustness — 5× in this paper · explained in 5 episodes
• World Model — 5× in this paper · explained in 7 episodes
• Grounding — 4× in this paper · explained in 3 episodes
• Success Rate — 4× in this paper
• Ablation study — 3× in this paper · explained in 1 episode
• APEX — 2× in this paper · explained in 1 episode
• Alignment — 2× in this paper · explained in 1 episode
• Diffusion Model — 2× in this paper · explained in 8 episodes
• Diffusion Models — 2× in this paper · explained in 6 episodes
• Latent Space — 2× in this paper · explained in 7 episodes
• Navigation Error — 2× in this paper
• Unified Framework — 2× in this paper · explained in 5 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Action Decoder — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• CVF International Conference on Computer Vision — 1× in this paper
• Contrastive Learning — 1× in this paper · explained in 5 episodes
• Distribution Shift — 1× in this paper · explained in 5 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Flow Matching — 1× in this paper · explained in 8 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Multimodal Reasoning — 1× in this paper · explained in 5 episodes
• Oracle Success Rate — 1× in this paper
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Temporal Reasoning — 1× in this paper · explained in 2 episodes
• Temporal consistency — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments
• WorldVLA: Towards Autoregressive Action World Model
• Large Video Planner Enables Generalizable Robot Control
• Vision-and-Language Navigation for UAVs: Progress, Challenges, and a Research Roadmap
• Diffusion Models for Smarter UAVs: Decision-Making and Modeling
• Aerial Vision-and-Dialog Navigation
• DriveWorld-VLA: Unified Latent-Space World Modeling with Vision-Language-Action for Autonomous Driving
• LongFly: Long-Horizon UAV Vision-and-Language Navigation with Spatiotemporal Context Integration
• SpatialFly: Implicit 3D Prior-Guided Visual Reparameterization for Continuous UAV Vision-and-Language Navigation
• RAVEN: Resilient Aerial Navigation via Open-Set Semantic Memory and Behavior Adaptation
• OpenVLN: Open-world Aerial Vision-Language Navigation
• VoLN: Vision-Only Long-Horizon Navigation---Paradigm, Benchmark, and Method
• AutoFly: Vision-Language-Action Model for UAV Autonomous Navigation in the Wild
• Aerial Vision-Language Navigation with a Unified Framework for Spatial, Temporal and Embodied Reasoning
• World Action Models are Zero-shot Policies
• NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation
• FutureNav: Unified World-Action Modeling for Vision-and-Language Navigation
• Anticipate Before Acting: Future-State-Conditioned Vision-Language Navigation
• MindDriver: Introducing Progressive Multimodal Reasoning for Autonomous Driving
• WorldVLN: Autoregressive World Action Model for Aerial Vision-Language Navigation

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models