{"total":187,"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":"2406.09385","title":"Towards Vision-Language Geo-Foundation Model: A Survey","created":"2024-06-13","cited_by_count":36,"area":"mllm"},{"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":"2506.14674","title":"Recognition through Reasoning: Reinforcing Image Geo-localization with Large Vision-Language Models","created":"2025-06-17","cited_by_count":28,"area":"wm"},{"id":"2406.13945","title":"CityBench: Evaluating the Capabilities of Large Language Models for Urban Tasks","created":"2024-06-20","cited_by_count":27,"area":"wm"},{"id":"2406.18572","title":"GeoReasoner: Geo-localization with Reasoning in Street Views using a Large Vision-Language Model","created":"2024-06-03","cited_by_count":27,"area":"lr"},{"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":"2405.20363","title":"LLMGeo: Benchmarking Large Language Models on Image Geolocation In-the-wild","created":"2024-05-30","cited_by_count":21,"area":"mllm"},{"id":"2407.04952","title":"Granular Privacy Control for Geolocation with Vision Language Models","created":"2024-07-06","cited_by_count":21,"area":"mllm"},{"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":"2505.14361","title":"Vision-Language Modeling Meets Remote Sensing: Models, Datasets and Perspectives","created":"2025-05-20","cited_by_count":18,"area":"mllm"},{"id":"2408.09474","title":"Image-Based Geolocation Using Large Vision-Language Models","created":"2024-08-18","cited_by_count":17,"area":"mllm"},{"id":"2402.09816","title":"Mind the Modality Gap: Towards a Remote Sensing Vision-Language Model via Cross-modal Alignment","created":"2024-02-15","cited_by_count":15,"area":"mllm"},{"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":"2505.16793","title":"REOBench: Benchmarking Robustness of Earth Observation Foundation Models","created":"2025-05-22","cited_by_count":15,"area":"mllm"},{"id":"2505.18700","title":"GRE Suite: Geo-localization Inference via Fine-Tuned Vision-Language Models and Enhanced Reasoning Chains","created":"2025-05-24","cited_by_count":14,"area":"lr"},{"id":"2410.01407","title":"AgriCLIP: Adapting CLIP for Agriculture and Livestock via Domain-Specialized Cross-Model Alignment","created":"2024-10-02","cited_by_count":13,"area":"mllm"},{"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":"2408.11312","title":"Swarm Intelligence in Geo-Localization: A Multi-Agent Large Vision-Language Model Collaborative Framework","created":"2024-08-21","cited_by_count":11,"area":"lr"},{"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":"2502.14638","title":"NAVIG: Natural Language-guided Analysis with Vision Language Models for Image Geo-localization","created":"2025-02-20","cited_by_count":8,"area":"mllm"},{"id":"2502.09598","title":"GAIA: A Global, Multi-modal, Multi-scale Vision-Language Dataset for Remote Sensing Image Analysis","created":"2025-02-13","cited_by_count":7,"area":"mllm"},{"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":"2503.12490","title":"GeoRSMLLM: A Multimodal Large Language Model for Vision-Language Tasks in Geoscience and Remote Sensing","created":"2025-03-16","cited_by_count":6,"area":"mllm"},{"id":"2503.18142","title":"LocDiff: Identifying Locations on Earth by Diffusing in the Hilbert Space","created":"2025-03-23","cited_by_count":6,"area":"diffusion"},{"id":"2506.02744","title":"Enriching Location Representation with Detailed Semantic Information","created":"2025-06-03","cited_by_count":6,"area":null},{"id":"2511.00908","title":"GraphGeo: Multi-Agent Debate Framework for Visual Geo-localization with Heterogeneous Graph Neural Networks","created":"2025-11-02","cited_by_count":6,"area":"agents"},{"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":"2503.19311","title":"DGTRSD & DGTRS-CLIP: A Dual-Granularity Remote Sensing Image-Text Dataset and Vision Language Foundation Model for Alignment","created":"2025-03-25","cited_by_count":4,"area":"mllm"},{"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":"2506.21476","title":"Global and Local Entailment Learning for Natural World Imagery","created":"2025-06-26","cited_by_count":3,"area":"mllm"},{"id":"2506.23481","title":"Evaluation of Geolocation Capabilities of Multimodal Large Language Models and Analysis of Associated Privacy Risks","created":"2025-06-30","cited_by_count":3,"area":"lr"},{"id":"2508.00152","title":"GeoExplorer: Active Geo-localization with Curiosity-Driven Exploration","created":"2025-07-31","cited_by_count":3,"area":"deeprl"},{"id":"2508.10667","title":"AddressVLM: Cross-view Alignment Tuning for Image Address Localization using Large Vision-Language Models","created":"2025-08-14","cited_by_count":3,"area":"mllm"},{"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":"2509.02129","title":"Scale, Don't Fine-tune: Guiding Multimodal LLMs for Efficient Visual Place Recognition at Test-Time","created":"2025-09-02","cited_by_count":3,"area":"mllm"},{"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":"2603.10463","title":"Learning to Wander: Improving the Global Image Geolocation Ability of LMMs via Actionable Reasoning","created":"2026-03-11","cited_by_count":3,"area":"lr"},{"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":"2508.19967","title":"Assessing the Geolocation Capabilities, Limitations and Societal Risks of Generative Vision-Language Models","created":"2025-08-27","cited_by_count":2,"area":"mllm"},{"id":"2509.01341","title":"Street-Level Geolocalization Using Multimodal Large Language Models and Retrieval-Augmented Generation","created":"2025-09-01","cited_by_count":2,"area":"mllm"},{"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":"2601.03713","title":"BREATH-VL: Vision-Language-Guided 6-DoF Bronchoscopy Localization via Semantic-Geometric Fusion","created":"2026-01-07","cited_by_count":2,"area":"mllm"},{"id":"2603.09566","title":"GeoAlignCLIP: Enhancing Fine-Grained Vision-Language Alignment in Remote Sensing via Multi-Granular Consistency Learning","created":"2026-03-10","cited_by_count":2,"area":"mllm"},{"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}],"next_cursor":"100"}