Image de couverture de livre

Are VLMs Lost Between Sky and Space? LinkS$^2$Bench for UAV-Satellite Dynamic Cross-View Spatial Intelligence

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Liu, Dian, Feng, Jie, Li, Di, Zheng, Yuhui, Li, Guanbin, Dong, Weisheng, Shi, Guangming
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

A3R: Agentic Affordance Reasoning via Cross-Dimensional Evidence in 3D Gaussian Scenes
par: Li, Di, et autres
Publié: (2026)

SeqAffordSplat: Scene-level Sequential Affordance Reasoning on 3D Gaussian Splatting
par: Li, Di, et autres
Publié: (2025)

EgoSplat: Open-Vocabulary Egocentric Scene Understanding with Language Embedded 3D Gaussian Splatting
par: Li, Di, et autres
Publié: (2025)

SkyLink: A Large Vision-Language Model Driven Re-ranking Framework for Cross-View UAV geolocalization
par: Liu, Bowen, et autres
Publié: (2026)

S4DL: Shift-sensitive Spatial-Spectral Disentangling Learning for Hyperspectral Image Unsupervised Domain Adaptation
par: Feng, Jie, et autres
Publié: (2024)

SIRI-Bench: Challenging VLMs' Spatial Intelligence through Complex Reasoning Tasks
par: Song, Zijian, et autres
Publié: (2025)

Have the VLMs Lost Confidence? A Study of Sycophancy in VLMs
par: Li, Shuo, et autres
Publié: (2024)

Is your VLM Sky-Ready? A Comprehensive Spatial Intelligence Benchmark for UAV Navigation
par: Zhang, Lingfeng, et autres
Publié: (2025)

Scale-Aware UAV-to-Satellite Cross-View Geo-Localization: A Semantic Geometric Approach
par: Ye, Yibin, et autres
Publié: (2026)

SDesc3D: Towards Layout-Aware 3D Indoor Scene Generation from Short Descriptions
par: Feng, Jie, et autres
Publié: (2026)

SkyLink: Unifying Street-Satellite Geo-Localization via UAV-Mediated 3D Scene Alignment
par: Zhang, Hongyang, et autres
Publié: (2025)

Fast Window-Based Event Denoising with Spatiotemporal Correlation Enhancement
par: Fang, Huachen, et autres
Publié: (2024)

Adaptive Betweenness Clustering for Semi-Supervised Domain Adaptation
par: Li, Jichang, et autres
Publié: (2024)

Stepping VLMs onto the Court: Benchmarking Spatial Intelligence in Sports
par: Yang, Yuchen, et autres
Publié: (2026)

ERVD: An Efficient and Robust ViT-Based Distillation Framework for Remote Sensing Image Retrieval
par: Dong, Le, et autres
Publié: (2024)

SpinBench: Perspective and Rotation as a Lens on Spatial Reasoning in VLMs
par: Zhang, Yuyou, et autres
Publié: (2025)

Cross-Modal Attention Calibration for LVLM Hallucination Mitigation
par: Li, Jiaming, et autres
Publié: (2025)

CrossViewDiff: A Cross-View Diffusion Model for Satellite-to-Street View Synthesis
par: Li, Weijia, et autres
Publié: (2024)

DSI-Bench: A Benchmark for Dynamic Spatial Intelligence
par: Zhang, Ziang, et autres
Publié: (2025)

Securing the Sky: Integrated Satellite-UAV Physical Layer Security for Low-Altitude Wireless Networks
par: Li, Jiahui, et autres
Publié: (2025)

Rethinking Exposure Correction for Spatially Non-uniform Degradation
par: Li, Ao, et autres
Publié: (2026)

ViewSpatial-Bench: Evaluating Multi-perspective Spatial Localization in Vision-Language Models
par: Li, Dingming, et autres
Publié: (2025)

GUI Knowledge Bench: Revealing the Knowledge Gap of VLMs in GUI Tasks
par: Shi, Chenrui, et autres
Publié: (2025)

Aerial Vision-and-Language Navigation with Grid-based View Selection and Map Construction
par: Zhao, Ganlong, et autres
Publié: (2025)

Style Alignment based Dynamic Observation Method for UAV-View Geo-localization
par: Shao, Jie, et autres
Publié: (2024)

How Far are VLMs from Visual Spatial Intelligence? A Benchmark-Driven Perspective
par: Yu, Songsong, et autres
Publié: (2025)

ProSR: Process-Shaped Spatial Reasoning for Reliable Chain-of-Thought in VLMs
par: Li, Jiangyang, et autres
Publié: (2026)

CrossView Suite: Harnessing Cross-view Spatial Intelligence of MLLMs with Dataset, Model and Benchmark
par: Wang, Wei, et autres
Publié: (2026)

Igniting VLMs toward the Embodied Space
par: Zhai, Andy, et autres
Publié: (2025)

Cross-View Geo-Localization with Street-View and VHR Satellite Imagery in Decentrality Settings
par: Xia, Panwang, et autres
Publié: (2024)

Unifying UAV Cross-View Geo-Localization via 3D Geometric Perception
par: Li, Haoyuan, et autres
Publié: (2026)

SPACENUM: Revisiting Spatial Numerical Understanding in VLMs
par: Zhang, Jianshu, et autres
Publié: (2026)

MVRD-Bench: Multi-View Learning and Benchmarking for Dynamic Remote Photoplethysmography under Occlusion
par: He, Zuxian, et autres
Publié: (2026)

Multi-Teacher Multi-Objective Meta-Learning for Zero-Shot Hyperspectral Band Selection
par: Feng, Jie, et autres
Publié: (2024)

Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution
par: Lin, Shuchen, et autres
Publié: (2025)

ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop
par: Hong, Yining, et autres
Publié: (2026)

MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligence
par: Yang, Sihan, et autres
Publié: (2025)

AICA-Bench: Holistically Examining the Capabilities of VLMs in Affective Image Content Analysis
par: She, Dong, et autres
Publié: (2026)

Learning Multi-View Spatial Reasoning from Cross-View Relations
par: Jeong, Suchae, et autres
Publié: (2026)

Can World Models Benefit VLMs for World Dynamics?
par: Zhang, Kevin, et autres
Publié: (2025)