{"list":"other","total":51,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"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":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2503.14476","title":"DAPO: An Open-Source LLM Reinforcement Learning System at Scale","created":"2025-03-18","cited_by_count":2810},{"id":"2403.13372","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","created":"2024-03-20","cited_by_count":1464},{"id":"1505.04870","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","created":"2015-05-19","cited_by_count":1362},{"id":"2308.00692","title":"LISA: Reasoning Segmentation via Large Language Model","created":"2023-08-01","cited_by_count":776},{"id":"2503.06749","title":"Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models","created":"2025-03-09","cited_by_count":665},{"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":"2504.07615","title":"VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model","created":"2025-04-10","cited_by_count":526},{"id":"2503.01785","title":"Visual-RFT: Visual Reinforcement Fine-Tuning","created":"2025-03-03","cited_by_count":513},{"id":"2503.10615","title":"R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization","created":"2025-03-13","cited_by_count":370},{"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":"2003.06957","title":"Frustratingly Simple Few-Shot Object Detection","created":"2020-03-16","cited_by_count":282},{"id":"2306.00968","title":"GRES: Generalized Referring Expression Segmentation","created":"2023-06-01","cited_by_count":254},{"id":"2503.07536","title":"LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL","created":"2025-03-10","cited_by_count":248},{"id":"2503.06520","title":"Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement","created":"2025-03-09","cited_by_count":239},{"id":"1805.10002","title":"Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learning","created":"2018-05-25","cited_by_count":211},{"id":"2307.15266","title":"RSGPT: A Remote Sensing Vision Language Model and Benchmark","created":"2023-07-28","cited_by_count":207},{"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":"2306.15880","title":"Towards Open Vocabulary Learning: A Survey","created":"2023-06-28","cited_by_count":166},{"id":"2503.05132","title":"R1-Zero's \"Aha Moment\" in Visual Reasoning on a 2B Non-SFT Model","created":"2025-03-07","cited_by_count":165},{"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":"2406.10100","title":"SkySenseGPT: A Fine-Grained Instruction Tuning Dataset and Model for Remote Sensing Vision-Language Understanding","created":"2024-06-14","cited_by_count":104},{"id":"2305.05726","title":"Vision-Language Models in Remote Sensing: Current Progress and Future Trends","created":"2023-05-09","cited_by_count":93},{"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":"2003.14247","title":"DPGN: Distribution Propagation Graph Network for Few-shot Learning","created":"2020-03-31","cited_by_count":79},{"id":"2312.12470","title":"Rotated Multi-Scale Interaction Network for Referring Remote Sensing Image Segmentation","created":"2023-12-19","cited_by_count":76},{"id":"2306.08625","title":"RRSIS: Referring Remote Sensing Image Segmentation","created":"2023-06-14","cited_by_count":59},{"id":"2408.09110","title":"Locate Anything on Earth: Advancing Open-Vocabulary Object Detection for Remote Sensing Community","created":"2024-08-17","cited_by_count":50},{"id":"2411.11904","title":"GeoGround: A Unified Large Vision-Language Model for Remote Sensing Visual Grounding","created":"2024-11-16","cited_by_count":47},{"id":"2308.16182","title":"GREC: Generalized Referring Expression Comprehension","created":"2023-08-30","cited_by_count":42},{"id":"2504.09644","title":"SegEarth-R1: Geospatial Pixel Reasoning via Large Language Model","created":"2025-04-13","cited_by_count":42},{"id":"2505.18022","title":"RemoteSAM: Towards Segment Anything for Earth Observation","created":"2025-05-23","cited_by_count":39},{"id":"2406.09385","title":"Towards Vision-Language Geo-Foundation Model: A Survey","created":"2024-06-13","cited_by_count":36},{"id":"2006.07826","title":"Few-shot Object Detection on Remote Sensing Images","created":"2020-06-14","cited_by_count":23},{"id":"2311.11646","title":"Toward Open Vocabulary Aerial Object Detection with CLIP-Activated Student-Teacher Learning","created":"2023-11-20","cited_by_count":22},{"id":"2411.18145","title":"CHOICE: Benchmarking the Remote Sensing Capabilities of Large Vision-Language Models","created":"2024-11-27","cited_by_count":22},{"id":"2505.14361","title":"Vision-Language Modeling Meets Remote Sensing: Models, Datasets and Perspectives","created":"2025-05-20","cited_by_count":18},{"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},{"id":"2310.08619","title":"Unlocking the capabilities of explainable fewshot learning in remote sensing","created":"2023-10-12","cited_by_count":4}],"next_cursor":null}