{"total":80,"rows":[{"id":"2410.06234","title":"TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation Data","created":"2024-10-08","cited_by_count":70,"area":null},{"id":"2405.13570","title":"MetaEarth: A Generative Foundation Model for Global-Scale Remote Sensing Image Generation","created":"2024-05-22","cited_by_count":42,"area":null},{"id":"2505.18022","title":"RemoteSAM: Towards Segment Anything for Earth Observation","created":"2025-05-23","cited_by_count":39,"area":null},{"id":"2506.20380","title":"TESSERA: Temporal Embeddings of Surface Spectra for Earth Representation and Analysis","created":"2025-06-25","cited_by_count":39,"area":null},{"id":"2405.04285","title":"On the Foundations of Earth and Climate Foundation Models","created":"2024-05-07","cited_by_count":33,"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":"2404.15500","title":"GeoLLM-Engine: A Realistic Environment for Building Geospatial Copilots","created":"2024-04-23","cited_by_count":30,"area":null},{"id":"2405.09365","title":"SARATR-X: Toward Building A Foundation Model for SAR Target Recognition","created":"2024-05-15","cited_by_count":25,"area":null},{"id":"2507.20776","title":"RingMo-Agent: A Unified Remote Sensing Foundation Model for Multi-Platform and Multi-Modal Reasoning","created":"2025-07-28","cited_by_count":20,"area":null},{"id":"2509.21976","title":"Geo-R1: Improving Few-Shot Geospatial Referring Expression Understanding with Reinforcement Fine-Tuning","created":"2025-09-26","cited_by_count":20,"area":null},{"id":"2502.00392","title":"RefDrone: A Challenging Benchmark for Referring Expression Comprehension in Drone Scenes","created":"2025-02-01","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":"2412.16919","title":"TAR3D: Creating High-Quality 3D Assets via Next-Part Prediction","created":"2024-12-22","cited_by_count":16,"area":null},{"id":"2403.03790","title":"Popeye: A Unified Visual-Language Model for Multi-Source Ship Detection from Remote Sensing Imagery","created":"2024-03-06","cited_by_count":14,"area":null},{"id":"2501.13354","title":"ATRNet-STAR: A Large Dataset and Benchmark Towards Remote Sensing Object Recognition in the Wild","created":"2025-01-23","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":"2605.12678","title":"No One Knows the State of the Art in Geospatial Foundation Models","created":"2026-05-12","cited_by_count":12,"area":null},{"id":"2504.04319","title":"Geo-OLM: Enabling Sustainable Earth Observation Studies with Cost-Efficient Open Language Models & State-Driven Workflows","created":"2025-04-06","cited_by_count":11,"area":null},{"id":"2511.20460","title":"Look Where It Matters: Training-Free Ultra-HR Remote Sensing VQA via Adaptive Zoom Search","created":"2025-11-25","cited_by_count":11,"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":"2505.24528","title":"Geospatial Foundation Models to Enable Progress on Sustainable Development Goals","created":"2025-05-30","cited_by_count":10,"area":null},{"id":"2511.23332","title":"UniGeoSeg: Towards Unified Open-World Segmentation for Geospatial Scenes","created":"2025-11-28","cited_by_count":10,"area":null},{"id":"2512.20013","title":"SegEarth-R2: Towards Comprehensive Language-guided Segmentation for Remote Sensing Images","created":"2025-12-23","cited_by_count":10,"area":null},{"id":"2402.19273","title":"PlanGPT: Enhancing Urban Planning with Tailored Language Model and Efficient Retrieval","created":"2024-02-29","cited_by_count":8,"area":null},{"id":"2501.10075","title":"Robust Change Captioning in Remote Sensing: SECOND-CC Dataset and MModalCC Framework","created":"2025-01-17","cited_by_count":8,"area":null},{"id":"2411.07688","title":"ImageRAG: Enhancing Ultra High Resolution Remote Sensing Imagery Analysis with ImageRAG","created":"2024-11-12","cited_by_count":6,"area":null},{"id":"2502.08168","title":"SARChat-Bench-2M: A Multi-Task Vision-Language Benchmark for SAR Image Interpretation","created":"2025-02-12","cited_by_count":5,"area":null},{"id":"2501.08131","title":"SAR Strikes Back: A New Hope for RSVQA","created":"2025-01-14","cited_by_count":3,"area":null},{"id":"2507.05731","title":"A Satellite-Ground Synergistic Large Vision-Language Model System for Earth Observation","created":"2025-07-08","cited_by_count":3,"area":null},{"id":"2510.22964","title":"Survey of Multimodal Geospatial Foundation Models: Techniques, Applications, and Challenges","created":"2025-10-27","cited_by_count":3,"area":null},{"id":"2602.13305","title":"WildfireVLM: AI-powered Analysis for Early Wildfire Detection and Risk Assessment Using Satellite Imagery","created":"2026-02-09","cited_by_count":3,"area":null},{"id":"2403.18593","title":"Homogeneous Tokenizer Matters: Homogeneous Visual Tokenizer for Remote Sensing Image Understanding","created":"2024-03-27","cited_by_count":2,"area":null},{"id":"2603.16307","title":"NeSy-Route: A Neuro-Symbolic Benchmark for Constrained Route Planning in Remote Sensing","created":"2026-03-17","cited_by_count":2,"area":null},{"id":"2604.10591","title":"GeoMeld: Toward Semantically Grounded Foundation Models for Remote Sensing","created":"2026-04-12","cited_by_count":2,"area":null},{"id":"2501.14546","title":"Leveraging ChatGPT's Multimodal Vision Capabilities to Rank Satellite Images by Poverty Level: Advancing Tools for Social Science Research","created":"2025-01-24","cited_by_count":1,"area":null},{"id":"2508.01555","title":"MGCR-Net:Multimodal Graph-Conditioned Vision-Language Reconstruction Network for Remote Sensing Change Detection","created":"2025-08-03","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":"2508.08974","title":"Text-conditioned State Space Model For Domain-generalized Change Detection Visual Question Answering","created":"2025-08-12","cited_by_count":1,"area":null},{"id":"2512.03025","title":"LORE: A Large Generative Model for Search Relevance","created":"2025-12-02","cited_by_count":1,"area":null},{"id":"2601.17673","title":"Uni-RS: A Spatially Faithful Unified Understanding and Generation Model for Remote Sensing","created":"2026-01-25","cited_by_count":1,"area":null},{"id":"2602.19190","title":"FUSAR-GPT : A Spatiotemporal Feature-Embedded and Two-Stage Decoupled Visual Language Model for SAR Imagery","created":"2026-02-22","cited_by_count":1,"area":null},{"id":"2603.01758","title":"Unifying Heterogeneous Multi-Modal Remote Sensing Detection Via Language-Pivoted Pretraining","created":"2026-03-02","cited_by_count":1,"area":null},{"id":"2603.10722","title":"UAV traffic scene understanding: A regulation embedded multi-modal network and a unified benchmark","created":"2026-03-11","cited_by_count":1,"area":null},{"id":"2605.01250","title":"EO-Gym: A Multimodal, Interactive Environment for Earth Observation Agents","created":"2026-05-02","cited_by_count":1,"area":null},{"id":"2605.07522","title":"WeatherSyn: An Instruction Tuning MLLM For Weather Forecasting Report Generation","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2605.17792","title":"HydroAgent: Closing the Gap Between Frontier LLMs and Human Experts in Hydrologic Model Calibration via Simulator-Grounded RL","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2608.03147","title":"CROSS: Cascaded Distillation and Dual-Constraint Grounding for Remote Sensing Referring Segmentation","created":"2026-08-04","cited_by_count":1,"area":null},{"id":"2408.00967","title":"Extracting Object Heights From LiDAR & Aerial Imagery","created":"2024-08-02","cited_by_count":0,"area":null},{"id":"2501.10144","title":"A Vision-Language Framework for Multispectral Scene Representation Using Language-Grounded Features","created":"2025-01-17","cited_by_count":0,"area":null},{"id":"2502.17000","title":"An Enhanced Large Language Model For Cross Modal Query Understanding System Using DL-KeyBERT Based CAZSSCL-MPGPT","created":"2025-02-24","cited_by_count":0,"area":null},{"id":"2503.14109","title":"Operational Change Detection for Geographical Information: Overview and Challenges","created":"2025-03-18","cited_by_count":0,"area":null},{"id":"2503.24219","title":"MB-ORES: A Multi-Branch Object Reasoner for Visual Grounding in Remote Sensing","created":"2025-03-31","cited_by_count":0,"area":null},{"id":"2506.12324","title":"UniDet-D: A Unified Dynamic Spectral Attention Model for Object Detection under Adverse Weathers","created":"2025-06-14","cited_by_count":0,"area":null},{"id":"2510.06071","title":"Benchmark It Yourself (BIY): Preparing a Dataset and Benchmarking AI Models for Scatterplot-Related Tasks","created":"2025-10-07","cited_by_count":0,"area":null},{"id":"2510.21813","title":"SITS-DECO: A Generative Decoder Is All You Need For Multitask Satellite Image Time Series Modelling","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2512.11490","title":"VLM2GeoVec: Toward Universal Multimodal Embeddings for Remote Sensing","created":"2025-12-12","cited_by_count":0,"area":null},{"id":"2512.15531","title":"An Efficient and Effective Encoder Model for Vision and Language Tasks in the Remote Sensing Domain","created":"2025-12-17","cited_by_count":0,"area":null},{"id":"2512.24943","title":"RAIR: A Rule-Aware Benchmark Uniting Challenging Long-Tail and Visual Salience Subset for E-commerce Relevance Assessment","created":"2025-12-31","cited_by_count":0,"area":null},{"id":"2602.00110","title":"Observing Health Outcomes Using Remote Sensing Imagery and Geo-Context Guided Visual Transformer","created":"2026-01-26","cited_by_count":0,"area":null},{"id":"2602.20652","title":"DANCE: Doubly Adaptive Neighborhood Conformal Estimation","created":"2026-02-24","cited_by_count":0,"area":null},{"id":"2603.14609","title":"GroundSet: A Cadastral-Grounded Dataset for Spatial Understanding with Vector Data","created":"2026-03-15","cited_by_count":0,"area":null},{"id":"2604.22333","title":"ChangeQuery: Advancing Remote Sensing Change Analysis for Natural and Human-Induced Disasters from Visual Detection to Semantic Understanding","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2604.22855","title":"Evaluating Remote Sensing Image Captions Beyond Metric Biases","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2605.06990","title":"TrajGANR: Trajectory-Centric Urban Multimodal Learning via Geospatially Aligned Neural Representations","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.07640","title":"LithoBench: Benchmarking Large Multimodal Models for Remote-Sensing Lithology Interpretation","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.12542","title":"Earth Science Foundation Models: From Perception to Reasoning and Discovery","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2606.10468","title":"Geometric Coastline Localization using Vision-Language Models","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2607.07292","title":"CarbonCLIP: Enhance Carbon Prediction from Satellite Imagery via Integrated Street-View Semantics and Temporal Context Training","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2607.07758","title":"Scalable and Trustworthy Earth Observation Foundation Models","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2608.00012","title":"Obshazard-bench: Benchmarking Multimodal Foundation Models for Real-Time Disaster Intelligence from Raw Earth Observation Streams","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2608.06059","title":"DARAD: Dual Adapters and Ranking-Aware Distillation for Continual Remote Sensing Image-Text Retrieval","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.07015","title":"Understand Before Detect: Vision--Language Learning for Omni-Domain Infrared Small Target Detection","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.09276","title":"Verifiably grounded machine interpretation of lunar geology","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.15456","title":"AlignJEPA: Predictive Vision-Language Alignment for Remote Sensing Foundation Models","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2608.16310","title":"Cross-View Urban Sensing: Mapping Subjective Streetscape Perception via AlphaEarth Embeddings and Urban Context","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2608.24665","title":"Data Leakage Inflates Generalizability of Power Outage Prediction Models","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2608.28567","title":"GeBDA: Building Damage Assessment as Text-Based Sequence Prediction","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.31234","title":"WeaveAgent: A Two-Stage Tool-Routing Agent for Ultra-High-Resolution Remote Sensing Imagery","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2610.00302","title":"Decoding the Disaster: Multi-Task Geospatial Reasoning with Vision-Language Models and Crowdsourced Imagery for Disaster Mapping","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.13535","title":"Knowing Whether, Not Just Where: Anchor-Probing Distillation for Open-Set Remote Sensing Visual Grounding","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}