{"total":138,"rows":[{"id":"2311.17179","title":"SatCLIP: Global, General-Purpose Location Embeddings with Satellite Imagery","created":"2023-11-28","cited_by_count":151,"area":null},{"id":"2403.15356","title":"Neural Plasticity-Inspired Multimodal Foundation Model for Earth Observation","created":"2024-03-22","cited_by_count":104,"area":null},{"id":"2402.01444","title":"Mission Critical -- Satellite Data is a Distinct Modality in Machine Learning","created":"2024-02-02","cited_by_count":77,"area":null},{"id":"2406.11519","title":"HyperSIGMA: Hyperspectral Intelligence Comprehension Foundation Model","created":"2024-06-17","cited_by_count":73,"area":null},{"id":"2403.13430","title":"MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining","created":"2024-03-20","cited_by_count":66,"area":null},{"id":"2412.10510","title":"DEFAME: Dynamic Evidence-based FAct-checking with Multimodal Experts","created":"2024-12-13","cited_by_count":43,"area":null},{"id":"2411.00683","title":"TaxaBind: A Unified Embedding Space for Ecological Applications","created":"2024-11-01","cited_by_count":35,"area":null},{"id":"2405.14702","title":"G3: An Effective and Adaptive Framework for Worldwide Geolocalization Using Large Multi-Modality Models","created":"2024-05-23","cited_by_count":34,"area":null},{"id":"2403.19584","title":"Img2Loc: Revisiting Image Geolocalization using Multi-modality Foundation Models and Image-based Retrieval-Augmented Generation","created":"2024-03-28","cited_by_count":32,"area":null},{"id":"2404.06637","title":"GeoSynth: Contextually-Aware High-Resolution Satellite Image Synthesis","created":"2024-04-09","cited_by_count":32,"area":null},{"id":"2406.15658","title":"TorchSpatial: A Location Encoding Framework and Benchmark for Spatial Representation Learning","created":"2024-06-21","cited_by_count":31,"area":null},{"id":"2502.13759","title":"Geolocation with Real Human Gameplay Data: A Large-Scale Dataset and Human-Like Reasoning Framework","created":"2025-02-19","cited_by_count":24,"area":null},{"id":"2402.01749","title":"Towards Urban General Intelligence: A Review and Outlook of Urban Foundation Models","created":"2024-01-30","cited_by_count":23,"area":null},{"id":"2408.06761","title":"Cross-View Geolocalization and Disaster Mapping with Street-View and VHR Satellite Imagery: A Case Study of Hurricane IAN","created":"2024-08-13","cited_by_count":23,"area":null},{"id":"2407.08156","title":"AddressCLIP: Empowering Vision-Language Models for City-wide Image Address Localization","created":"2024-07-11","cited_by_count":21,"area":null},{"id":"2403.16831","title":"UrbanVLP: Multi-Granularity Vision-Language Pretraining for Urban Socioeconomic Indicator Prediction","created":"2024-03-25","cited_by_count":19,"area":null},{"id":"2502.19781","title":"RANGE: Retrieval Augmented Neural Fields for Multi-Resolution Geo-Embeddings","created":"2025-02-27","cited_by_count":19,"area":null},{"id":"2503.22081","title":"A Survey on Remote Sensing Foundation Models: From Vision to Multimodality","created":"2025-03-28","cited_by_count":19,"area":null},{"id":"2505.13731","title":"GeoRanker: Distance-Aware Ranking for Worldwide Image Geolocalization","created":"2025-05-19","cited_by_count":19,"area":null},{"id":"2403.12702","title":"Learning Cross-view Visual Geo-localization without Ground Truth","created":"2024-03-19","cited_by_count":18,"area":null},{"id":"2411.07207","title":"General Geospatial Inference with a Population Dynamics Foundation Model","created":"2024-11-11","cited_by_count":18,"area":null},{"id":"2403.08851","title":"PAPERCLIP: Associating Astronomical Observations and Natural Language with Multi-Modal Models","created":"2024-03-13","cited_by_count":15,"area":null},{"id":"2412.14428","title":"WildSAT: Learning Satellite Image Representations from Wildlife Observations","created":"2024-12-19","cited_by_count":13,"area":null},{"id":"2410.10931","title":"Combining Observational Data and Language for Species Range Estimation","created":"2024-10-14","cited_by_count":12,"area":null},{"id":"2508.01608","title":"From Pixels to Places: A Systematic Benchmark for Evaluating Image Geolocalization Ability in Large Language Models","created":"2025-08-03","cited_by_count":12,"area":null},{"id":"2603.00988","title":"Foundation Models in Remote Sensing: Evolving from Unimodality to Multimodality","created":"2026-03-01","cited_by_count":12,"area":null},{"id":"2412.08907","title":"Towards Interactive Global Geolocation Assistant","created":"2024-12-12","cited_by_count":11,"area":null},{"id":"2412.19237","title":"SeaMo: A Season-Aware Multimodal Foundation Model for Remote Sensing","created":"2024-12-26","cited_by_count":11,"area":null},{"id":"2507.10473","title":"GT-Loc: Unifying When and Where in Images Through a Joint Embedding Space","created":"2025-07-14","cited_by_count":11,"area":null},{"id":"2409.19439","title":"Contrastive ground-level image and remote sensing pre-training improves representation learning for natural world imagery","created":"2024-09-28","cited_by_count":10,"area":null},{"id":"2503.16683","title":"GAIR: Location-Aware Self-Supervised Contrastive Pre-Training with Geo-Aligned Implicit Representations","created":"2025-03-20","cited_by_count":10,"area":null},{"id":"2510.26795","title":"Scaling Image Geo-Localization to Continent Level","created":"2025-10-30","cited_by_count":10,"area":null},{"id":"2511.02101","title":"Measuring the Intrinsic Dimension of Earth Representations","created":"2025-11-03","cited_by_count":10,"area":null},{"id":"2408.12133","title":"Self-Supervised Representation Learning for Geospatial Objects: A Survey","created":"2024-08-22","cited_by_count":9,"area":null},{"id":"2503.08722","title":"A Recipe for Improving Remote Sensing VLM Zero Shot Generalization","created":"2025-03-10","cited_by_count":7,"area":null},{"id":"2511.01082","title":"GeoToken: Hierarchical Geolocalization of Images via Next Token Prediction","created":"2025-11-02","cited_by_count":7,"area":null},{"id":"2512.20056","title":"Towards Generative Location Awareness for Disaster Response: A Probabilistic Cross-view Geolocalization Approach","created":"2025-12-23","cited_by_count":7,"area":null},{"id":"2506.02744","title":"Enriching Location Representation with Detailed Semantic Information","created":"2025-06-03","cited_by_count":6,"area":null},{"id":"2405.14135","title":"Space-aware Socioeconomic Indicator Inference with Heterogeneous Graphs","created":"2024-05-23","cited_by_count":5,"area":null},{"id":"2501.12390","title":"GPS as a Control Signal for Image Generation","created":"2025-01-21","cited_by_count":5,"area":null},{"id":"2503.16423","title":"GAEA: A Geolocation Aware Conversational Assistant","created":"2025-03-20","cited_by_count":5,"area":null},{"id":"2504.18256","title":"SSL4Eco: A Global Seasonal Dataset for Geospatial Foundation Models in Ecology","created":"2025-04-25","cited_by_count":5,"area":null},{"id":"2505.08723","title":"TiMo: Spatiotemporal Foundation Model for Satellite Image Time Series","created":"2025-05-13","cited_by_count":5,"area":null},{"id":"2507.13385","title":"Using Multiple Input Modalities Can Improve Data-Efficiency and O.O.D. Generalization for ML with Satellite Imagery","created":"2025-07-15","cited_by_count":5,"area":null},{"id":"2508.03209","title":"GeoShield: Safeguarding Geolocation Privacy from Vision-Language Models via Adversarial Perturbations","created":"2025-08-05","cited_by_count":5,"area":null},{"id":"2602.12617","title":"GeoAgent: Learning to Geolocate Everywhere with Reinforced Geographic Characteristics","created":"2026-02-13","cited_by_count":5,"area":null},{"id":"2411.19475","title":"GalaxAlign: Mimicking Citizen Scientists' Multimodal Guidance for Galaxy Morphology Analysis","created":"2024-11-29","cited_by_count":4,"area":null},{"id":"2504.16942","title":"S2Vec: Self-Supervised Geospatial Embeddings for the Built Environment","created":"2025-04-10","cited_by_count":4,"area":null},{"id":"2504.17177","title":"A Genealogy of Foundation Models in Remote Sensing","created":"2025-04-24","cited_by_count":4,"area":null},{"id":"2505.18461","title":"Performance and Generalizability Impacts of Incorporating Location Encoders into Deep Learning for Dynamic PM2.5 Estimation","created":"2025-05-24","cited_by_count":4,"area":null},{"id":"2506.01297","title":"MoRA: Mobility as the Backbone for Geospatial Representation Learning at Scale","created":"2025-06-02","cited_by_count":4,"area":null},{"id":"2512.08606","title":"Decoupling Template Bias in CLIP: Harnessing Empty Prompts for Enhanced Few-Shot Learning","created":"2025-12-09","cited_by_count":4,"area":null},{"id":"2405.18459","title":"Probing the Information Theoretical Roots of Spatial Dependence Measures","created":"2024-05-28","cited_by_count":3,"area":null},{"id":"2505.05644","title":"The Moon's Many Faces: A Single Unified Transformer for Multimodal Lunar Reconstruction","created":"2025-05-08","cited_by_count":3,"area":null},{"id":"2506.14570","title":"From Points to Places: Towards Human Mobility-Driven Spatiotemporal Foundation Models via Understanding Places","created":"2025-06-17","cited_by_count":3,"area":null},{"id":"2509.01910","title":"Towards Interpretable Geo-localization: a Concept-Aware Global Image-GPS Alignment Framework","created":"2025-09-02","cited_by_count":3,"area":null},{"id":"2510.20095","title":"BioCAP: Exploiting Synthetic Captions Beyond Labels in Biological Foundation Models","created":"2025-10-23","cited_by_count":3,"area":null},{"id":"2602.00392","title":"Localized, High-resolution Geographic Representations with Slepian Functions","created":"2026-01-30","cited_by_count":3,"area":null},{"id":"2603.26128","title":"TaxaAdapter: Vision Taxonomy Models are Key to Fine-grained Image Generation over the Tree of Life","created":"2026-03-27","cited_by_count":3,"area":null},{"id":"2502.11742","title":"Range and Bird's Eye View Fused Cross-Modal Visual Place Recognition","created":"2025-02-17","cited_by_count":2,"area":null},{"id":"2502.15032","title":"GeoAggregator: An Efficient Transformer Model for Geo-Spatial Tabular Data","created":"2025-02-20","cited_by_count":2,"area":null},{"id":"2504.02009","title":"Urban Computing in the Era of Large Language Models","created":"2025-04-02","cited_by_count":2,"area":null},{"id":"2506.03168","title":"Farm-LightSeek: An Edge-centric Multimodal Agricultural IoT Data Analytics Framework with Lightweight LLMs","created":"2025-05-28","cited_by_count":2,"area":null},{"id":"2507.17455","title":"VLM-Guided Visual Place Recognition for Planet-Scale Geo-Localization","created":"2025-07-23","cited_by_count":2,"area":null},{"id":"2509.21573","title":"Enhancing Contrastive Learning for Geolocalization by Discovering Hard Negatives on Semivariograms","created":"2025-09-25","cited_by_count":2,"area":null},{"id":"2510.01448","title":"GeoSURGE: Geo-localization using Semantic Fusion with Hierarchy of Geographic Embeddings","created":"2025-10-01","cited_by_count":2,"area":null},{"id":"2510.09894","title":"Beyond AlphaEarth: Toward Human-Centered Geospatial Foundation Models via POI-Guided Contrastive Learning","created":"2025-10-10","cited_by_count":2,"area":null},{"id":"2603.24749","title":"TIGeR: A Unified Framework for Time, Images and Geo-location Retrieval","created":"2026-03-25","cited_by_count":2,"area":null},{"id":"2604.02719","title":"MOMO: Mars Orbital Model Foundation Model for Mars Orbital Applications","created":"2026-04-03","cited_by_count":2,"area":null},{"id":"2604.07092","title":"Location Is All You Need: Continuous Spatiotemporal Neural Representations of Earth Observation Data","created":"2026-04-08","cited_by_count":2,"area":null},{"id":"2604.11668","title":"UNIGEOCLIP: Unified Geospatial Contrastive Learning","created":"2026-04-13","cited_by_count":2,"area":null},{"id":"2606.27514","title":"Tessellating The Earth","created":"2026-06-25","cited_by_count":2,"area":null},{"id":"2607.14072","title":"MetaPerch: Learning from metadata for bioacoustics foundation models","created":"2026-07-15","cited_by_count":2,"area":null},{"id":"2608.06612","title":"SLED: Scalable Location Encoding via Distillation","created":"2026-08-06","cited_by_count":2,"area":null},{"id":"2409.18102","title":"MALPOLON: A Framework for Deep Species Distribution Modeling","created":"2024-09-26","cited_by_count":1,"area":null},{"id":"2502.04399","title":"Online Location Planning for AI-Defined Vehicles: Optimizing Joint Tasks of Order Serving and Spatio-Temporal Heterogeneous Model Fine-Tuning","created":"2025-02-06","cited_by_count":1,"area":null},{"id":"2503.02036","title":"Latent Domain Modeling Improves Robustness to Geographic Shifts","created":"2025-03-03","cited_by_count":1,"area":null},{"id":"2503.17899","title":"What Time Tells Us? An Explorative Study of Time Awareness Learned from Static Images","created":"2025-03-23","cited_by_count":1,"area":null},{"id":"2506.02868","title":"Pan-Arctic Permafrost Landform and Human-built Infrastructure Feature Detection with Vision Transformers and Location Embeddings","created":"2025-06-03","cited_by_count":1,"area":null},{"id":"2507.00356","title":"CGEarthEye:A High-Resolution Remote Sensing Vision Foundation Model Based on the Jilin-1 Satellite Constellation","created":"2025-07-01","cited_by_count":1,"area":null},{"id":"2508.06832","title":"Remote Sensing Image Intelligent Interpretation with the Language-Centered Perspective: Principles, Methods and Challenges","created":"2025-08-09","cited_by_count":1,"area":null},{"id":"2511.02946","title":"ProM3E: Probabilistic Masked MultiModal Embedding Model for Ecology","created":"2025-11-04","cited_by_count":1,"area":null},{"id":"2511.21194","title":"BotaCLIP: Contrastive Learning for Botany-Aware Representation of Earth Observation Data","created":"2025-11-26","cited_by_count":1,"area":null},{"id":"2512.11811","title":"Enhancing Geo-localization for Crowdsourced Flood Imagery via LLM-Guided Attention","created":"2025-11-25","cited_by_count":1,"area":null},{"id":"2601.19155","title":"LocationAgent: A Hierarchical Agent for Image Geolocation via Decoupling Strategy and Evidence from Parametric Knowledge","created":"2026-01-27","cited_by_count":1,"area":null},{"id":"2601.23064","title":"HierLoc: Hyperbolic Entity Embeddings for Hierarchical Visual Geolocation","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2602.09775","title":"Where Do Images Come From? Analyzing Captions to Geographically Profile Datasets","created":"2026-02-10","cited_by_count":1,"area":null},{"id":"2604.04357","title":"Spatially-Weighted CLIP for Street-View Geo-localization","created":"2026-04-06","cited_by_count":1,"area":null},{"id":"2604.12159","title":"VidTAG: Temporally Aligned Video to GPS Geolocalization with Denoising Sequence Prediction at a Global Scale","created":"2026-04-14","cited_by_count":1,"area":null},{"id":"2604.16220","title":"OT on the Map: Quantifying Domain Shifts in Geographic Space","created":"2026-04-17","cited_by_count":1,"area":null},{"id":"2604.18881","title":"A Proxy Consistency Loss for Grounded Fusion of Earth Observation and Location Encoders","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2604.20623","title":"RSRCC: A Remote Sensing Regional Change Comprehension Benchmark Constructed via Retrieval-Augmented Best-of-N Ranking","created":"2026-04-22","cited_by_count":1,"area":null},{"id":"2604.25533","title":"DualGeo: A Dual-View Framework for Worldwide Image Geo-localization","created":"2026-04-28","cited_by_count":1,"area":null},{"id":"2606.02374","title":"Spatial Representation Learning Beyond Pixels: Unifying Raster Data and Vector Semantics for Human-Centric Geospatial Foundation Models","created":"2026-06-01","cited_by_count":1,"area":null},{"id":"2606.24997","title":"What's in an Earth Embedding? An Explainability Analysis of Location Encoders","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2607.19751","title":"Learning the Arabic Dialect Continuum as a Continuous Space: A Regression Approach to Speaker Origin Prediction","created":"2026-07-22","cited_by_count":1,"area":null},{"id":"2407.13862","title":"Enhancing Worldwide Image Geolocation by Ensembling Satellite-Based Ground-Level Attribute Predictors","created":"2024-07-18","cited_by_count":0,"area":null},{"id":"2411.14560","title":"Enhancing GeoAI and location encoding with spatial point pattern statistics: A Case Study of Terrain Feature Classification","created":"2024-11-21","cited_by_count":0,"area":null},{"id":"2412.12188","title":"Predicting Internet Connectivity in Schools: A Feasibility Study Leveraging Multi-modal Data and Location Encoders in Low-Resource Settings","created":"2024-12-13","cited_by_count":0,"area":null},{"id":"2503.08290","title":"SegDesicNet: Lightweight Semantic Segmentation in Remote Sensing with Geo-Coordinate Embeddings for Domain Adaptation","created":"2025-03-11","cited_by_count":0,"area":null}],"next_cursor":"100"}