Signals 4 · free daily AI digest

SatNav: A Scalable Benchmark for Long-Horizon UAV Vision-Language Navigation from Satellite Imagery

Paper recorded by Signals 4 on 2026-09-25 in cs.CV. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-25 on arXiv · recorded by Signals 4 on 2026-09-28

Category: cs.CV · 计算机视觉 · first seen 2026-09-28

Abstract

Urban uncrewed aerial vehicle (UAV) vision-language navigation (VLN) requires agents to follow instructions across extended urban spaces, inherently demanding long-term memory and geospatial grounding. However, scaling existing benchmarks remains difficult because of their reliance on costly reconstructed 3D assets, limiting geographic diversity and episode scale. To address this, we introduce Sat

Read on arXiv →

#23 most recent of 342 cs.CV papers we have recorded · ↑ newer: Forensic Twins: Self-Supervised Residual Learning for AI-Generated Ima · ↓ older: KneePreM: Towards 3D Knee MRI Foundation Models via Large-Scale Unlabe
Cite this page: SatNav: A Scalable Benchmark for Long-Horizon UAV Vision-Language Navigation from Satellite Imagery: the #23 most recent of 342 cs.CV papers we have recorded (as of 2026-09-25). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/satnav-a-scalable-benchmark-for-long-horizon-uav-vision-language-navigation-from.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CV papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions