{"list":"other","total":53,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"2308.12966","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","created":"2023-08-24","cited_by_count":2224},{"id":"2109.01903","title":"Robust fine-tuning of zero-shot models","created":"2021-09-04","cited_by_count":797},{"id":"2311.03079","title":"CogVLM: Visual Expert for Pretrained Language Models","created":"2023-11-06","cited_by_count":708},{"id":"2310.09478","title":"MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning","created":"2023-10-14","cited_by_count":625},{"id":"2402.00838","title":"OLMo: Accelerating the Science of Language Models","created":"2024-02-01","cited_by_count":613},{"id":"1803.10704","title":"End-to-End Multi-Task Learning with Attention","created":"2018-03-28","cited_by_count":534},{"id":"2111.02358","title":"VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts","created":"2021-11-03","cited_by_count":425},{"id":"2207.08051","title":"SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery","created":"2022-07-17","cited_by_count":408},{"id":"2403.18814","title":"Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models","created":"2024-03-27","cited_by_count":365},{"id":"2306.11029","title":"RemoteCLIP: A Vision Language Foundation Model for Remote Sensing","created":"2023-06-19","cited_by_count":363},{"id":"2311.15826","title":"GeoChat: Grounded Large Vision-Language Model for Remote Sensing","created":"2023-11-24","cited_by_count":328},{"id":"2307.15266","title":"RSGPT: A Remote Sensing Vision Language Model and Benchmark","created":"2023-07-28","cited_by_count":207},{"id":"2003.07333","title":"RSVQA: Visual Question Answering for Remote Sensing Data","created":"2020-03-16","cited_by_count":203},{"id":"1712.07835","title":"Exploring Models and Data for Remote Sensing Image Caption Generation","created":"2017-12-21","cited_by_count":197},{"id":"2401.16822","title":"EarthGPT: A Universal Multi-modal Large Language Model for Multi-sensor Image Comprehension in Remote Sensing Domain","created":"2024-01-30","cited_by_count":184},{"id":"2012.02951","title":"FloodNet: A High Resolution Aerial Imagery Dataset for Post Flood Scene Understanding","created":"2020-12-05","cited_by_count":181},{"id":"2408.12637","title":"Building and better understanding vision-language models: insights and future directions","created":"2024-08-22","cited_by_count":173},{"id":"2306.11300","title":"RS5M and GeoRSCLIP: A Large Scale Vision-Language Dataset and A Large Vision-Language Model for Remote Sensing","created":"2023-06-20","cited_by_count":151},{"id":"2208.03987","title":"Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model","created":"2022-08-08","cited_by_count":149},{"id":"2402.02544","title":"LHRS-Bot: Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Model","created":"2024-02-04","cited_by_count":138},{"id":"2210.12634","title":"RSVG: Exploring Data and Models for Visual Grounding on Remote Sensing Data","created":"2022-10-23","cited_by_count":123},{"id":"2406.12384","title":"VRSBench: A Versatile Vision-Language Benchmark Dataset for Remote Sensing Image Understanding","created":"2024-06-18","cited_by_count":121},{"id":"2401.09712","title":"SkyEyeGPT: Unifying Remote Sensing Vision-Language Tasks via Instruction Tuning with Large Language Model","created":"2024-01-18","cited_by_count":113},{"id":"2305.05726","title":"Vision-Language Models in Remote Sensing: Current Progress and Future Trends","created":"2023-05-09","cited_by_count":93},{"id":"2010.08168","title":"A Generalizable and Accessible Approach to Machine Learning with Global Satellite Imagery","created":"2020-10-16","cited_by_count":88},{"id":"2403.20213","title":"VHM: Versatile and Honest Vision Language Model for Remote Sensing Image Analysis","created":"2024-03-29","cited_by_count":86},{"id":"2412.15190","title":"EarthDial: Turning Multi-sensory Earth Observations to Interactive Dialogues","created":"2024-12-19","cited_by_count":85},{"id":"2209.15323","title":"SmallCap: Lightweight Image Captioning Prompted with Retrieval Augmentation","created":"2022-09-30","cited_by_count":82},{"id":"2204.09868","title":"Exploring a Fine-Grained Multiscale Method for Cross-Modal Remote Sensing Image Retrieval","created":"2022-04-21","cited_by_count":77},{"id":"2410.06234","title":"TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation Data","created":"2024-10-08","cited_by_count":70},{"id":"2204.09860","title":"Remote Sensing Cross-Modal Text-Image Retrieval Based on Global and Local Information","created":"2022-04-21","cited_by_count":40},{"id":"2205.03147","title":"From Easy to Hard: Learning Language-guided Curriculum for Visual Question Answering on Remote Sensing Data","created":"2022-05-06","cited_by_count":39},{"id":"2305.08413","title":"Artificial intelligence to advance Earth observation: : A review of models, recent trends, and pathways forward","created":"2023-05-15","cited_by_count":28},{"id":"2308.12509","title":"Parameter-Efficient Transfer Learning for Remote Sensing Image-Text Retrieval","created":"2023-08-24","cited_by_count":24},{"id":"2501.06809","title":"RSRefSeg: Referring Remote Sensing Image Segmentation with Foundation Models","created":"2025-01-12","cited_by_count":22},{"id":"2312.01191","title":"Bootstrapping Interactive Image-Text Alignment for Remote Sensing Image Captioning","created":"2023-12-02","cited_by_count":18},{"id":"2106.10548","title":"VQA-Aid: Visual Question Answering for Post-Disaster Damage Assessment and Analysis","created":"2021-06-19","cited_by_count":15},{"id":"2509.25026","title":"GeoVLM-R1: Reinforcement Fine-Tuning for Improved Remote Sensing Reasoning","created":"2025-09-29","cited_by_count":15},{"id":"2405.15587","title":"Composed Image Retrieval for Remote Sensing","created":"2024-05-24","cited_by_count":14},{"id":"2405.03373","title":"Knowledge-aware Text-Image Retrieval for Remote Sensing Images","created":"2024-05-06","cited_by_count":9},{"id":"2506.19585","title":"SMARTIES: Spectrum-Aware Multi-Sensor Auto-Encoder for Remote Sensing Images","created":"2025-06-24","cited_by_count":9},{"id":"2410.23370","title":"Multilingual Vision-Language Pre-training for the Remote Sensing Domain","created":"2024-10-30","cited_by_count":7},{"id":"2507.05731","title":"A Satellite-Ground Synergistic Large Vision-Language Model System for Earth Observation","created":"2025-07-08","cited_by_count":3},{"id":"2512.07338","title":"Generalized Referring Expression Segmentation on Aerial Photos","created":"2025-12-08","cited_by_count":2}],"next_cursor":null}