LightVLN: Efficient Aerial Vision-and-Language Navigation with Compact Memory and History-Guided Local Aggregation

arXiv:2610.05024 · cs.CV, cs.RO · Submitted 2026-10-04 · Read on arXiv

cs.CV, cs.RO

Submitted: 2026-10-04

Updated: 2026-10-04

Comments: 8 pages, 5 figures

Code: https://github.com/Stanford-ILIAD/openvla-mini

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Aggregation — 1× in this paper · explained in 1 episode

Sources

• Towards Realistic UAV Vision-Language Navigation: Platform, Benchmark, and Methodology
• Exploring Spatial Representation to Enhance LLM Reasoning in Aerial Vision-Language Navigation
• Fly0: Persistent Metric Anchoring for Zero-Shot Aerial Vision-Language Navigation
• Aerial Vision-Language Navigation with a Unified Framework for Spatial, Temporal and Embodied Reasoning
• DreamFly: Causal Memory and Receding-Horizon Diffusion Planning for Aerial Vision-Language Navigation
• LongFly: Long-Horizon UAV Vision-and-Language Navigation with Spatiotemporal Context Integration
• VLA-AN: An Efficient and Onboard Vision-Language-Action Framework for Aerial Navigation in Complex Environments
• FSD-VLN: Fast-Slow Dual-System Modeling for Aerial Long-Horizon Vision-Language Navigation
• OnFly: Onboard Zero-Shot Aerial Vision-Language Navigation toward Safety and Efficiency
• NativeMEM: Native Memory Compression for Long-Horizon Robotic Manipulation
• Qwen2.5 Technical Report

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