Location encoders transform geographic coordinates into high‑dimensional embeddings for machine learning, yet it is unclear how well these embeddings capture interpretable spatial effects. This study benchmarks GeoShapley—a game‑theoretic explainer treating all location features as a single joint player—against eleven TorchSpatial encoders on a synthetic process with known coefficients, across grid, county, and global scales, with and without raw coordinates and under different training regimes. The results show that primary coefficient recovery is consistently high across encoders, while secondary coefficient recovery varies more with scale, especially at the global level, and raw‑coordinate baselines remain competitive throughout.
By Daniel Kiv, Shaowen Wang
arXiv:2610.20592v1 Announce Type: new
Abstract: Existing geometry-aware Multimodal Large Language Models (MLLMs) increasingly rely on external 3D encoders to provide structural priors, but executing...
By Haoyuan Li, Qihang Cao, Huanyuan Zhou, Xin Hu, Sijia Chen, Zihan Guo, Kun Xiang, Yunshuang Nie, Tao Tang, Xinlong Zheng, Jia-Wang Bian, Xianming Liu, Xiaodan Liang
arXiv:2606. 24997v1 Announce Type: new Abstract: Geographic implicit neural representations (INRs) learn to map any coordinate on Earth to a location embedding, implicitly encoding geospatial data into the weights of a neural network.
By Livia Betti, Sebastian Ricke, Ivica Obadic, Adam J. Stewart, Esther Rolf
arXiv:2610.23416v1 Announce Type: new
Abstract: Multimodal Large Language Models (MLLMs) have significantly advanced instruction-driven perception through the "Embedding-as-Mask" paradigm. However, e...
By Cheng Fan, Han Wu, Tingzhang Luo, Minjing Dong, Yehui Tang, Jianyuan Guo
arXiv:2608. 19766v1 Announce Type: cross Abstract: Self-supervised pretraining on remote sensing imagery typically treats all samples as equally informative, despite large variability in geographic and visual structure.
By Daniele Rege Cambrin, Francesco Rossi, Mattia Varile
arXiv:2608. 06612v1 Announce Type: cross Abstract: The plethora of readily available geospatial data offers exciting opportunities to learn high quality representations of the planet, but the sheer size of the Earth Observations (EO), differing modalities, and different sensor types pose significant challenges in doing so.
By Kevin Lane, Zhongying Wang, Esther Rolf, Morteza Karimzadeh
arXiv:2606. 02374v1 Announce Type: new Abstract: Earth Observation (EO) has fundamentally transformed the monitoring of environmental processes and human activities up to planetary scale.
By Steffen Knoblauch, Hao Li, Gengchen Mai, Konstantin Klemmer, Song Gao, WenWen Li
MoRA is a human‑centric geospatial representation learning framework that uses a large mobility graph as its backbone to fuse spatial tokenization, graph neural networks, and asymmetric contrastive learning. It aligns over 100 million points of interest, massive remote sensing imagery, and structured demographic data with a billion‑edge mobility graph, producing compact 128‑dimensional embeddings that capture socio‑economic context and functional roles of locations. On a benchmark of nine downstream social and economic prediction tasks, MoRA outperforms state‑of‑the‑art models by an average of 12.9% and demonstrates scaling behavior analogous to large language models.
By Ya Wen, Jixuan Cai, Qiyao Ma, Linyan Li, Xinhua Chen, Chris Webster, Yulun Zhou
arXiv:2606. 03988v1 Announce Type: new Abstract: Vision language models (VLMs) excel at many tasks but still struggle with spatial reasoning when critical information is not directly observable.
By Mahtab Bigverdi, Lindsey Li, Weikai Huang, Yiming Liu, Jaemin Cho, Jieyu Zhang, Tuhin Kundu, Chris Dangjoo Kim, Zelun Luo, Linda Shapiro, Ranjay Krishna
The paper introduces VHR-Bench, a benchmark of ten very high resolution (VHR) Earth observation datasets, and evaluates twelve encoders pretrained under different regimes. Results show that both large natural‑image pretraining and VHR‑specific pretraining transfer well to VHR tasks, with SkySense excelling when labels are scarce and DINOv3 ViT‑L performing best with full labels. Continuing self‑supervised pretraining of DINOv3 on VHR tiles further improves performance, especially in low‑label scenarios, without extra inference cost.
By Kshitij Raj Sharma, Pierre Adorni, Minh-Tan Pham, Dirk Tiede, S\'ebastien Lef\`evre
PlacePulse is a structural geospatial foundation model that transforms 572 attributes—expanded to 2,288 through H3 neighborhood aggregates—into 256‑dimensional unit‑norm embeddings for over a million H3 resolution‑7 cells across the United States. The model achieves high intrinsic reconstruction quality (mean $R^2 = 0.853$) and strong spatial organization (Moran's $I = 0.93$), while outperforming a dimensionality‑matched baseline on 74 held‑out targets from 12 external sources and competing with Google’s Population Dynamics Foundation Model on various health, economic, election, mobility, and social‑vulnerability outcomes. These results demonstrate that static structural composition can serve as a distinct and complementary modality for geospatial foundation models.
By Luc\'ia Garc\'ia-Duarte, Miguel \'Alvarez, Diego Vicente, Javier P\'erez Trufero, Javier de la Torre
arXiv:2606. 13896v1 Announce Type: cross Abstract: Self-supervised geospatial foundation models (GeoFMs) learn transferable representations from remote sensing data, but their downstream behavior is difficult to characterize.
By Julia Romero, Qin Lv, Morteza Karimzadeh