{"total":121,"rows":[{"id":"2412.15190","title":"EarthDial: Turning Multi-sensory Earth Observations to Interactive Dialogues","created":"2024-12-19","cited_by_count":85,"area":"mllm"},{"id":"2411.15296","title":"MME-Survey: A Comprehensive Survey on Evaluation of Multimodal LLMs","created":"2024-11-22","cited_by_count":72,"area":"mllm"},{"id":"2412.04204","title":"PANGAEA: A Global and Inclusive Benchmark for Geospatial Foundation Models","created":"2024-12-05","cited_by_count":68,"area":null},{"id":"2411.19325","title":"GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks","created":"2024-11-28","cited_by_count":51,"area":"mllm"},{"id":"2503.23771","title":"XLRS-Bench: Could Your Multimodal LLMs Understand Extremely Large Ultra-High-Resolution Remote Sensing Imagery?","created":"2025-03-31","cited_by_count":51,"area":"mllm"},{"id":"2411.11904","title":"GeoGround: A Unified Large Vision-Language Model for Remote Sensing Visual Grounding","created":"2024-11-16","cited_by_count":47,"area":"mllm"},{"id":"2505.21375","title":"GeoLLaVA-8K: Scaling Remote-Sensing Multimodal Large Language Models to 8K Resolution","created":"2025-05-27","cited_by_count":44,"area":"mllm"},{"id":"2505.21089","title":"DisasterM3: A Remote Sensing Vision-Language Dataset for Disaster Damage Assessment and Response","created":"2025-05-27","cited_by_count":36,"area":"mllm"},{"id":"2412.05679","title":"RSUniVLM: A Unified Vision Language Model for Remote Sensing via Granularity-oriented Mixture of Experts","created":"2024-12-07","cited_by_count":29,"area":"mllm"},{"id":"2408.17267","title":"UrBench: A Comprehensive Benchmark for Evaluating Large Multimodal Models in Multi-View Urban Scenarios","created":"2024-08-30","cited_by_count":28,"area":"mllm"},{"id":"2410.08613","title":"Cross-Modal Bidirectional Interaction Model for Referring Remote Sensing Image Segmentation","created":"2024-10-11","cited_by_count":26,"area":null},{"id":"2411.18145","title":"CHOICE: Benchmarking the Remote Sensing Capabilities of Large Vision-Language Models","created":"2024-11-27","cited_by_count":22,"area":"lr"},{"id":"2508.00265","title":"Multimodal Referring Segmentation: A Survey","created":"2025-08-01","cited_by_count":22,"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":"2501.13953","title":"Redundancy Principles for MLLMs Benchmarks","created":"2025-01-20","cited_by_count":19,"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":"2505.21076","title":"DynamicVL: Benchmarking Multimodal Large Language Models for Dynamic City Understanding","created":"2025-05-27","cited_by_count":18,"area":"mllm"},{"id":"2506.01667","title":"EarthMind: Leveraging Cross-Sensor Data for Advanced Earth Observation Interpretation with a Unified Multimodal LLM","created":"2025-06-02","cited_by_count":18,"area":"mllm"},{"id":"2507.06231","title":"RSRefSeg 2: Decoupling Referring Remote Sensing Image Segmentation with Foundation Models","created":"2025-07-08","cited_by_count":17,"area":null},{"id":"2508.07918","title":"RSVLM-QA: A Benchmark Dataset for Remote Sensing Vision Language Model-based Question Answering","created":"2025-08-11","cited_by_count":17,"area":"mllm"},{"id":"2504.03254","title":"SARLANG-1M: A Benchmark for Vision-Language Modeling in SAR Image Understanding","created":"2025-04-04","cited_by_count":16,"area":"mllm"},{"id":"2505.16793","title":"REOBench: Benchmarking Robustness of Earth Observation Foundation Models","created":"2025-05-22","cited_by_count":15,"area":"mllm"},{"id":"2505.23522","title":"OmniEarth-Bench: Towards Holistic Evaluation of Earth's Six Spheres and Cross-Spheres Interactions with Multimodal Observational Earth Data","created":"2025-05-29","cited_by_count":14,"area":null},{"id":"2509.01907","title":"RSCC: A Large-Scale Remote Sensing Change Caption Dataset for Disaster Events","created":"2025-09-02","cited_by_count":14,"area":null},{"id":"2511.22645","title":"GeoZero: Incentivizing Reasoning from Scratch on Geospatial Scenes","created":"2025-11-27","cited_by_count":14,"area":"lr"},{"id":"2505.02829","title":"LISAT: Language-Instructed Segmentation Assistant for Satellite Imagery","created":"2025-05-05","cited_by_count":13,"area":"mllm"},{"id":"2512.17319","title":"A Benchmark for Ultra-High-Resolution Remote Sensing MLLMs","created":"2025-12-19","cited_by_count":11,"area":"lr"},{"id":"2501.06828","title":"GeoPix: Multi-Modal Large Language Model for Pixel-level Image Understanding in Remote Sensing","created":"2025-01-12","cited_by_count":10,"area":"mllm"},{"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":"2509.17562","title":"Visual Instruction Pretraining for Domain-Specific Foundation Models","created":"2025-09-22","cited_by_count":9,"area":null},{"id":"2505.15818","title":"InstructSAM: A Training-Free Framework for Instruction-Oriented Remote Sensing Object Recognition","created":"2025-05-21","cited_by_count":8,"area":null},{"id":"2503.06312","title":"DOFA-CLIP: Multimodal Vision-Language Foundation Models for Earth Observation","created":"2025-03-08","cited_by_count":7,"area":"mllm"},{"id":"2512.02517","title":"SkyMoE: A Vision-Language Foundation Model for Enhancing Geospatial Interpretation with Mixture of Experts","created":"2025-12-02","cited_by_count":7,"area":"mllm"},{"id":"2603.19039","title":"TerraScope: Pixel-Grounded Visual Reasoning for Earth Observation","created":"2026-03-19","cited_by_count":7,"area":"lr"},{"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":"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":"2507.10449","title":"CoralVQA: A Large-Scale Visual Question Answering Dataset for Coral Reef Image Understanding","created":"2025-07-14","cited_by_count":6,"area":null},{"id":"2511.22396","title":"Asking like Socrates: Socrates helps VLMs understand remote sensing images","created":"2025-11-27","cited_by_count":6,"area":"lr"},{"id":"2602.07045","title":"VLRS-Bench: A Vision-Language Reasoning Benchmark for Remote Sensing","created":"2026-02-04","cited_by_count":6,"area":"lr"},{"id":"2604.08896","title":"GeoMMBench and GeoMMAgent: Toward Expert-Level Multimodal Intelligence in Geoscience and Remote Sensing","created":"2026-04-10","cited_by_count":6,"area":"mllm"},{"id":"2508.03127","title":"Landsat30-AU: A Vision-Language Dataset for Australian Landsat Imagery","created":"2025-08-05","cited_by_count":4,"area":"mllm"},{"id":"2510.18262","title":"UWBench: A Comprehensive Vision-Language Benchmark for Underwater Understanding","created":"2025-10-21","cited_by_count":4,"area":"mllm"},{"id":"2512.02715","title":"GeoViS: Geospatially Rewarded Visual Search for Remote Sensing Visual Grounding","created":"2025-12-02","cited_by_count":4,"area":"mllm"},{"id":"2601.00998","title":"DVGBench: Implicit-to-Explicit Visual Grounding Benchmark in UAV Imagery with Large Vision-Language Models","created":"2026-01-02","cited_by_count":4,"area":"mllm"},{"id":"2603.02754","title":"Seeing Clearly without Training: Mitigating Hallucinations in Multimodal LLMs for Remote Sensing","created":"2026-03-03","cited_by_count":4,"area":"mllm"},{"id":"2606.10819","title":"Earth-OneVision: Extending Remote Sensing Multimodal Large Language Models to More Sensor Modalities and Tasks","created":"2026-06-09","cited_by_count":4,"area":"lr"},{"id":"2408.00932","title":"Towards Zero-Shot Annotation of the Built Environment with Vision-Language Models (Vision Paper)","created":"2024-08-01","cited_by_count":3,"area":"mllm"},{"id":"2505.08325","title":"FedRS-Bench: Realistic Federated Learning Datasets and Benchmarks in Remote Sensing","created":"2025-05-13","cited_by_count":3,"area":null},{"id":"2508.05202","title":"SPEX: A Vision-Language Model for Land Cover Extraction on Spectral Remote Sensing Images","created":"2025-08-07","cited_by_count":3,"area":"mllm"},{"id":"2511.21272","title":"Co-Training Vision Language Models for Remote Sensing Multi-task Learning","created":"2025-11-26","cited_by_count":3,"area":"mllm"},{"id":"2512.24022","title":"FUSE-RSVLM: Feature Fusion Vision-Language Model for Remote Sensing","created":"2025-12-30","cited_by_count":3,"area":"mllm"},{"id":"2602.00593","title":"Pix2Fact: When Vision Is Not Enough -- Benchmarking Fine-Grained VQA with Web Verification on High-Resolution Real-World Scenes","created":"2026-01-31","cited_by_count":3,"area":"mllm"},{"id":"2603.09471","title":"OmniEarth: A Benchmark for Evaluating Vision-Language Models in Geospatial Tasks","created":"2026-03-10","cited_by_count":3,"area":"lr"},{"id":"2603.11804","title":"OSMDA: OpenStreetMap-based Domain Adaptation for Remote Sensing VLMs","created":"2026-03-12","cited_by_count":3,"area":"mllm"},{"id":"2506.00883","title":"Improve MLLM Benchmark Efficiency through Interview","created":"2025-06-01","cited_by_count":2,"area":"mllm"},{"id":"2601.01416","title":"AirSpatialBot: A Spatially-Aware Aerial Agent for Fine-Grained Vehicle Attribute Recognization and Retrieval","created":"2026-01-04","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":"2603.14941","title":"RS-WorldModel: a Unified Model for Remote Sensing Understanding and Future Sense Forecasting","created":"2026-03-16","cited_by_count":2,"area":"wm"},{"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":"2604.17243","title":"RemoteShield: Enable Robust Multimodal Large Language Models for Earth Observation","created":"2026-04-19","cited_by_count":2,"area":"mllm"},{"id":"2606.20177","title":"Evaluating and Enhancing Negation Comprehension in Remote Sensing MLLMs","created":"2026-06-18","cited_by_count":2,"area":"mllm"},{"id":"2606.28266","title":"RSICCLLM: A Multimodal Large Language Model for Remote Sensing Image Change Captioning","created":"2026-06-26","cited_by_count":2,"area":"mllm"},{"id":"2410.17283","title":"Advancements in Visual Language Models for Remote Sensing: Datasets, Capabilities, and Enhancement Techniques","created":"2024-10-15","cited_by_count":1,"area":"mllm"},{"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":"2509.10059","title":"Multimodal Mathematical Reasoning Embedded in Aerial Vehicle Imagery: Benchmarking, Analysis, and Exploration","created":"2025-09-12","cited_by_count":1,"area":"lr"},{"id":"2509.18897","title":"RS3DBench: A Comprehensive Benchmark for 3D Spatial Perception in Remote Sensing","created":"2025-09-23","cited_by_count":1,"area":null},{"id":"2512.02505","title":"GeoDiT: A Diffusion-based Vision-Language Model for Geospatial Understanding","created":"2025-12-02","cited_by_count":1,"area":"mllm"},{"id":"2512.07276","title":"Geo3DVQA: Evaluating Vision-Language Models for 3D Geospatial Reasoning from Aerial Imagery","created":"2025-12-08","cited_by_count":1,"area":"lr"},{"id":"2512.07302","title":"Towards Accurate UAV Image Perception: Guiding Vision-Language Models with Stronger Task Prompts","created":"2025-12-08","cited_by_count":1,"area":"mllm"},{"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":"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":"2604.13565","title":"UHR-BAT: Budget-Aware Token Compression Vision-Language model for Ultra-High-Resolution Remote Sensing","created":"2026-04-15","cited_by_count":1,"area":"mllm"},{"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":"2605.01250","title":"EO-Gym: A Multimodal, Interactive Environment for Earth Observation Agents","created":"2026-05-02","cited_by_count":1,"area":null},{"id":"2605.08245","title":"When Language Overwrites Vision: Over-Alignment and Geometric Debiasing in Vision-Language Models","created":"2026-05-07","cited_by_count":1,"area":"mllm"},{"id":"2605.12237","title":"UHR-Micro: Diagnosing and Mitigating the Resolution Illusion in Earth Observation VLMs","created":"2026-05-12","cited_by_count":1,"area":"mllm"},{"id":"2605.22034","title":"AgroVG: A Large-Scale Multi-Source Benchmark for Agricultural Visual Grounding","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2607.01050","title":"GeoSearcher: Anchor-Guided Progressive Reasoning for Remote Sensing Visual Grounding with Process Supervision","created":"2026-07-01","cited_by_count":1,"area":"lr"},{"id":"2607.25993","title":"Beyond Zooming: Learning Multi-Tool Visual Reasoning for Ultra-High-Resolution Remote Sensing","created":"2026-07-28","cited_by_count":1,"area":"lr"},{"id":"2504.09528","title":"AeroLite: Tag-Guided Lightweight Generation of Aerial Image Captions","created":"2025-04-13","cited_by_count":0,"area":null},{"id":"2509.16343","title":"Visual Reasoning Agent: Robust Vision Systems in Remote Sensing via Inference-Time Scaling","created":"2025-09-19","cited_by_count":0,"area":"lr"},{"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":"2601.12076","title":"CroBIM-V: Memory-Quality Controlled Remote Sensing Referring Video Object Segmentation","created":"2026-01-17","cited_by_count":0,"area":null},{"id":"2603.06687","title":"TimeSpot: Benchmarking Geo-Temporal Understanding in Vision-Language Models in Real-World Settings","created":"2026-03-04","cited_by_count":0,"area":"wm"},{"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":"2603.28058","title":"Is One-Shot In-Context Learning Helpful for Data Selection in Task-Specific Fine-Tuning of Multimodal LLMs?","created":"2026-03-30","cited_by_count":0,"area":"mllm"},{"id":"2604.00820","title":"Continual Vision-Language Learning for Remote Sensing: Benchmarking and Analysis","created":"2026-04-01","cited_by_count":0,"area":"mllm"},{"id":"2604.01941","title":"Captioning Daily Activity Images in Early Childhood Education: Benchmark and Algorithm","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.17504","title":"RS-HyRe-R1: A Hybrid Reward Mechanism to Overcome Perceptual Inertia for Remote Sensing Images Understanding","created":"2026-04-19","cited_by_count":0,"area":"lr"},{"id":"2604.18201","title":"DiffuSAM: Diffusion Guided Zero-Shot Object Grounding for Remote Sensing Imagery","created":"2026-04-20","cited_by_count":0,"area":"diffusion"},{"id":"2604.20190","title":"WildFireVQA: A Large-Scale Radiometric Thermal VQA Benchmark for Aerial Wildfire Monitoring","created":"2026-04-22","cited_by_count":0,"area":"lr"},{"id":"2605.07273","title":"From Clouds to Hallucinations: Atmospheric Retrieval Hijacking in Remote Sensing Vision-Language RAG","created":"2026-05-08","cited_by_count":0,"area":"rag"},{"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":"2605.10576","title":"SenseBench: A Benchmark for Remote Sensing Low-Level Visual Perception and Description in Large Vision-Language Models","created":"2026-05-11","cited_by_count":0,"area":"mllm"},{"id":"2605.17949","title":"SkyNative: A Native Multimodal Architecture for Remote Sensing Vision-Language Understanding","created":"2026-05-18","cited_by_count":0,"area":"mllm"},{"id":"2605.25784","title":"Beyond Appearance: Can Multimodal Large Language Models Exploit Vertical Structure for Remote Sensing Natural Scene Understanding?","created":"2026-05-25","cited_by_count":0,"area":"mllm"},{"id":"2606.00556","title":"Improving Visual Grounding in Remote Sensing via Cluster-Guided Refinement and Model Ensemble Voting","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2606.09871","title":"SD-GRPO: Verifiable Segment Decomposition for Long-Form Vision-Language Generation","created":"2026-06-02","cited_by_count":0,"area":"lr"},{"id":"2606.10194","title":"MMClima: A Framework for Multimodal Climate Science Data and Evaluation","created":"2026-06-08","cited_by_count":0,"area":null}],"next_cursor":"100"}