GTPred is a new benchmark for geo‑temporal prediction that evaluates multi‑modal large language models (MLLMs) on 370 images taken across 120 years worldwide. It assesses predictions by matching both the year and a hierarchical location sequence, and includes annotated reasoning chains to test intermediate reasoning. Experiments on 15 MLLMs show that while visual perception is strong, models still lack world knowledge and geo‑temporal reasoning, and that adding temporal data improves location inference.
By Jinnao Li, Tingzhu Chen, Changbo Wang
Genesis is a generative engine designed to synthesize complete, globally consistent quadtree pyramids for satellite imagery. It tackles the new multi‑scale tile completion task by combining a vertical super‑resolution model with a horizontal mask‑based outpainting model, enabling seamless generation across arbitrary zoom levels and positions. The authors also release dense500, a fully observed multi‑scale dataset, and a suite of pyramid‑level metrics to benchmark performance.
Genesis is a generative engine that produces fully consistent multi‑scale satellite image pyramids by combining a vertical super‑resolution model with a horizontal mask‑based outpainting model. It addresses the lack of existing methods that can synthesize a complete quadtree from sparse seed tiles at arbitrary zoom levels and positions, ensuring coherence across both scale and space. The authors also release dense500, a comprehensive multi‑scale dataset and evaluation suite, to benchmark this new task.
By Subash Khanal, Yangzhi Cui, Daniel Cher, Eric Xing, Brian Wei, Srikumar Sastry, Nathan Jacobs
arXiv:2606. 28369v1 Announce Type: cross Abstract: Semantic search and recommendation of similar documents, such as news and reports about unusual environmental events (e.
By Yuanyuan Tian, Wenwen Li, Xiao Chen, Michael Brook, Michael Brubaker, Anna Liljedahl, Chitta Baral
arXiv:2607. 12748v1 Announce Type: cross Abstract: Farm site discovery from satellite imagery is a spatiotemporal candidate ranking problem because farm evidence is distributed across pasture, field boundaries, roads, buildings, and seasonal vegetation patterns.
By Usman Haider, Fatima Khalid, Karl Mason
The paper introduces RSMEB, a unified benchmark for remote‑sensing multimodal retrieval that evaluates both cross‑modal and interleaved retrieval across 21 tasks under a single ranking protocol. It also presents VLM2GeoVec, an instruction‑conditioned single‑encoder model that embeds image, text, bounding‑box, and geo‑coordinate tokens into one sequence and achieves state‑of‑the‑art performance on region‑caption, referring‑expression, and semantic geo‑aware retrieval while remaining competitive on conventional tasks. The authors provide code, checkpoints, and data on GitHub to facilitate reproducibility.
By Emanuel S\'anchez Aimar, Gulnaz Zhambulova, Fahad Shahbaz Khan, Yonghao Xu, Michael Felsberg
The paper introduces COL‑Tree, a compact landmark‑based tree structure designed to accelerate hierarchical object search in spatial networks. It supports diverse query types—such as aggregate k‑nearest neighbor (AkNN), k‑farthest neighbor (kFN), and others—by enabling efficient graph traversal with a more accurate heuristic than Euclidean‑based methods. Experiments on real‑world and synthetic road, terrain, and physics mesh networks show that COL‑Tree outperforms existing approaches by up to three orders of magnitude, with only modest preprocessing overhead.
By Tenindra Abeywickrama, Muhammad Aamir Cheema, Sabine Storandt
arXiv:2606. 08046v1 Announce Type: new Abstract: We present OSMGraphCLIP, a CLIP-style geospatial representation model that learns global location embeddings from freely available OpenStreetMap (OSM) data.
By Dimitrios Michail, Eleni Saka, Ioannis Giannopoulos, Ioannis Papoutsis
DamageScope is a retrieval‑augmented framework that combines satellite imagery, Vision‑Language Models (VLMs), and Large Language Models (LLMs) to automate property damage assessment after natural disasters. It uses a Retrieval‑Augmented Generation (RAG) architecture to extract structured visual representations from satellite images, enabling interactive natural language queries. The system introduces a multi‑vector embedding‑based clustering algorithm that improves scalability and reduces indexing time by up to 14×, and a dual‑store data architecture that cuts LLM API calls, lowering operational cost and response latency by roughly 3×.
By Ravi K. Rajendran, Biplob Debnath, Murugan Sankaradas, Srimat T. Chakradhar
arXiv:2607. 00090v1 Announce Type: cross Abstract: Urban-scale Visual Place Recognition (VPR) aims to identify the geographic location of a query image by matching it against a geo-tagged database.
By Zhiyao Shu, Jiacheng Yang, Yang Lu, Waishan Qiu, Chuan Li, Da Chen
AerialDojo-200K is a large-scale benchmark suite for open-world aerial object-goal search, featuring 42 simulation scenes across four families and 21 types, including urban, natural, infrastructure, and disaster environments. The dataset contains 205,732 task instances—over 100K semantic-goal and over 100K image-goal tasks—each with a collision-free reference trajectory and multi-view video recordings. A unified evaluation framework splits scenes into 21 in-distribution and 21 out-of-distribution sets, and preliminary tests on multimodal large language models show significant room for improvement in general-purpose aerial agents.
By Tongtong Feng, Xin Wang, Haoran Hou, Ren Wang, Weiran Wang, Shaokai Zhu, Ziqi Jia, Hao Wang, Yu-Wei Zhan, Zongyuan Wu, Jinghao Cui, Wenwu Zhu
arXiv:2512.02697v4 Announce Type: replace
Abstract: Cross-view geo-localization infers a location by retrieving geo-tagged reference images matching a query image. However, the traditional satellite-...
By Zixuan Song, Jing Zhang, Di Wang, Zhiming Luo, Wenbin Liu, Haonan Guo, En Wang, Bo Du, Liangpei Zhang