{"total":31,"rows":[{"id":"2406.09385","title":"Towards Vision-Language Geo-Foundation Model: A Survey","created":"2024-06-13","cited_by_count":36,"area":"mllm"},{"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":"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":"2505.16793","title":"REOBench: Benchmarking Robustness of Earth Observation Foundation Models","created":"2025-05-22","cited_by_count":15,"area":"mllm"},{"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":"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":"2503.12490","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":"2503.19311","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":"2506.21476","title":"Global and Local Entailment Learning for Natural World Imagery","created":"2025-06-26","cited_by_count":3,"area":"mllm"},{"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":"2509.02129","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":"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":"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":"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":"2508.11919","title":"TimeSenCLIP: A Time Series Vision-Language Model for Remote Sensing","created":"2025-08-16","cited_by_count":1,"area":"mllm"},{"id":"2511.22441","title":"GEO-Detective: Unveiling Location Privacy Risks in Images with LLM Agents","created":"2025-11-27","cited_by_count":1,"area":"mllm"},{"id":"2512.21337","title":"Beyond Memorization: A Multi-Modal Ordinal Regression Benchmark to Expose Popularity Bias in Vision-Language Models","created":"2025-12-24","cited_by_count":1,"area":"mllm"},{"id":"2603.05708","title":"Interpretable Perception and Reasoning for Audiovisual Geolocation","created":"2026-03-05","cited_by_count":1,"area":"mllm"},{"id":"2603.12659","title":"AVION: Aerial Vision-Language Instruction from Offline Teacher to Prompt-Tuned Network","created":"2026-03-13","cited_by_count":1,"area":"mllm"},{"id":"2604.09025","title":"Skill-Conditioned Visual Geolocation for Vision-Language Models","created":"2026-04-10","cited_by_count":1,"area":"mllm"},{"id":"2608.04244","title":"SIGNPOST-Bench: Benchmarking Text-Vision Conflict Resolution in Multimodal Large Language Models","created":"2026-08-04","cited_by_count":1,"area":"mllm"},{"id":"2409.15806","title":"CLSP: High-Fidelity Contrastive Language-State Pre-training for Agent State Representation","created":"2024-09-24","cited_by_count":0,"area":"mllm"},{"id":"2601.08420","title":"MMLGNet: Cross-Modal Alignment of Remote Sensing Data using CLIP","created":"2026-01-13","cited_by_count":0,"area":"mllm"},{"id":"2608.11838","title":"GeoBridge: Decoupled Semantic Conditioning for Generative Image Geolocalization","created":"2026-08-12","cited_by_count":0,"area":"mllm"},{"id":"2610.20055","title":"GeoCloak: An Agentic Framework for Semantics-Preserving Geolocation Privacy via Peripheral Clue Manipulation","created":"2026-10-14","cited_by_count":0,"area":"mllm"}],"next_cursor":null}