{"total":18,"rows":[{"id":"2504.12110","title":"Towards LLM Agents for Earth Observation","created":"2025-04-16","cited_by_count":17,"area":null},{"id":"2410.23828","title":"Show Me What and Where has Changed? Question Answering and Grounding for Remote Sensing Change Detection","created":"2024-10-31","cited_by_count":15,"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":"2501.04974","title":"SensorQA: A Question Answering Benchmark for Daily-Life Monitoring","created":"2025-01-09","cited_by_count":8,"area":null},{"id":"2601.02783","title":"EarthVL: A Progressive Earth Vision-Language Understanding and Generation Framework","created":"2026-01-06","cited_by_count":5,"area":null},{"id":"2506.06176","title":"SatelliteFormula: Multi-Modal Symbolic Regression from Remote Sensing Imagery for Physics Discovery","created":"2025-06-06","cited_by_count":3,"area":null},{"id":"2507.12795","title":"City-VLM: Towards Multidomain Perception Scene Understanding via Multimodal Incomplete Learning","created":"2025-07-17","cited_by_count":3,"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":"2505.10714","title":"GeoGrid-Bench: Can Foundation Models Understand Multimodal Gridded Geo-Spatial Data?","created":"2025-05-15","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":"2508.08974","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":"2603.02505","title":"SGMA: Semantic-Guided Modality-Aware Segmentation for Remote Sensing with Incomplete Multimodal Data","created":"2026-03-03","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":"2604.18429","title":"Revisiting Change VQA in Remote Sensing with Structured and Native Multimodal Qwen Models","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2605.04409","title":"UAV as Urban Construction Change Monitor: A New Benchmark and Change Captioning Model","created":"2026-05-06","cited_by_count":1,"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":"2605.07640","title":"LithoBench: Benchmarking Large Multimodal Models for Remote-Sensing Lithology Interpretation","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2609.38603","title":"Aperture: Training-Free Multiscale Concept Bottlenecks for Remote Sensing","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}