{"list":"other","total":62,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"id":"1612.00837","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","created":"2016-12-02","cited_by_count":2516},{"id":"2307.06281","title":"MMBench: Is Your Multi-modal Model an All-around Player?","created":"2023-07-12","cited_by_count":2141},{"id":"2508.18265","title":"InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency","created":"2025-08-25","cited_by_count":1510},{"id":"2508.10104","title":"DINOv3","created":"2025-08-13","cited_by_count":1414},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"2409.12186","title":"Qwen2.5-Coder Technical Report","created":"2024-09-18","cited_by_count":1203},{"id":"1906.00067","title":"OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge","created":"2019-05-31","cited_by_count":1121},{"id":"2406.12793","title":"ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools","created":"2024-06-18","cited_by_count":1121},{"id":"2307.16125","title":"SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension","created":"2023-07-30","cited_by_count":940},{"id":"2306.13549","title":"A Survey on Multimodal Large Language Models","created":"2023-06-23","cited_by_count":909},{"id":"2304.00685","title":"Vision-Language Models for Vision Tasks: A Survey","created":"2023-04-03","cited_by_count":839},{"id":"2303.00915","title":"BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs","created":"2023-03-02","cited_by_count":520},{"id":"2311.05608","title":"FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts","created":"2023-11-09","cited_by_count":398},{"id":"1901.07441","title":"PadChest: A large chest x-ray image dataset with multi-label annotated reports","created":"2019-01-22","cited_by_count":309},{"id":"2307.06350","title":"T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-image Generation","created":"2023-07-12","cited_by_count":260},{"id":"1901.05495","title":"An Underwater Image Enhancement Benchmark Dataset and Beyond","created":"2019-01-11","cited_by_count":253},{"id":"2306.09265","title":"LVLM-eHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Models","created":"2023-06-15","cited_by_count":217},{"id":"1903.09766","title":"Fast Underwater Image Enhancement for Improved Visual Perception","created":"2019-03-23","cited_by_count":183},{"id":"2410.08260","title":"Koala-36M: A Large-scale Video Dataset Improving Consistency between Fine-grained Conditions and Video Content","created":"2024-10-10","cited_by_count":135},{"id":"2402.18476","title":"IBD: Alleviating Hallucinations in Large Vision-Language Models via Image-Biased Decoding","created":"2024-02-28","cited_by_count":118},{"id":"1702.07392","title":"WaterGAN: Unsupervised Generative Network to Enable Real-time Color Correction of Monocular Underwater Images","created":"2017-02-23","cited_by_count":112},{"id":"2111.11843","title":"U-shape Transformer for Underwater Image Enhancement","created":"2021-11-23","cited_by_count":112},{"id":"2502.17387","title":"Big-Math: A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models","created":"2025-02-24","cited_by_count":109},{"id":"2004.01241","title":"Semantic Segmentation of Underwater Imagery: Dataset and Benchmark","created":"2020-04-02","cited_by_count":95},{"id":"1901.05320","title":"Real-world Underwater Enhancement: Challenges, Benchmarks, and Solutions","created":"2019-01-15","cited_by_count":90},{"id":"2412.00115","title":"OpenHumanVid: A Large-Scale High-Quality Dataset for Enhancing Human-Centric Video Generation","created":"2024-11-28","cited_by_count":77},{"id":"2403.17007","title":"DreamLIP: Language-Image Pre-training with Long Captions","created":"2024-03-25","cited_by_count":72},{"id":"2406.16866","title":"Revisiting Referring Expression Comprehension Evaluation in the Era of Large Multimodal Models","created":"2024-06-24","cited_by_count":53},{"id":"2412.20206","title":"Toward Visual Grounding: A Survey","created":"2024-12-28","cited_by_count":52},{"id":"2405.01792","title":"Learning Robust Autonomous Navigation and Locomotion for Wheeled-Legged Robots","created":"2024-05-03","cited_by_count":48},{"id":"2404.19326","title":"LVOS: A Benchmark for Large-scale Long-term Video Object Segmentation","created":"2024-04-30","cited_by_count":44},{"id":"2310.02567","title":"Improving Automatic VQA Evaluation Using Large Language Models","created":"2023-10-04","cited_by_count":37},{"id":"2108.09650","title":"Domain Adaptation for Underwater Image Enhancement","created":"2021-08-22","cited_by_count":35},{"id":"2106.05681","title":"A Dataset And Benchmark Of Underwater Object Detection For Robot Picking","created":"2021-06-10","cited_by_count":31},{"id":"2502.18695","title":"Policy-as-Prompt: Rethinking Content Moderation in the Age of Large Language Models","created":"2025-02-25","cited_by_count":31},{"id":"2411.15411","title":"FINECAPTION: Compositional Image Captioning Focusing on Wherever You Want at Any Granularity","created":"2024-11-23","cited_by_count":27},{"id":"2406.05785","title":"A Survey on Text-guided 3D Visual Grounding: Elements, Recent Advances, and Future Directions","created":"2024-06-09","cited_by_count":25},{"id":"2310.13596","title":"MarineGPT: Unlocking Secrets of Ocean to the Public","created":"2023-10-20","cited_by_count":23},{"id":"2312.11967","title":"Context Disentangling and Prototype Inheriting for Robust Visual Grounding","created":"2023-12-19","cited_by_count":23},{"id":"2212.12808","title":"A Comprehensive Review on Autonomous Navigation","created":"2022-12-24","cited_by_count":19},{"id":"2503.14604","title":"Image Captioning Evaluation in the Age of Multimodal LLMs: Challenges and Future Perspectives","created":"2025-03-18","cited_by_count":18},{"id":"2302.07344","title":"Semi-Supervised Visual Tracking of Marine Animals using Autonomous Underwater Vehicles","created":"2023-02-14","cited_by_count":16},{"id":"2404.04066","title":"VoicePilot: Harnessing LLMs as Speech Interfaces for Physically Assistive Robots","created":"2024-04-05","cited_by_count":16},{"id":"2405.19818","title":"WebUOT-1M: Advancing Deep Underwater Object Tracking with A Million-Scale Benchmark","created":"2024-05-30","cited_by_count":15},{"id":"2205.02692","title":"Gait Recognition in the Wild: A Large-scale Benchmark and NAS-based Baseline","created":"2022-05-05","cited_by_count":11},{"id":"2503.01019","title":"MedUnifier: Unifying Vision-and-Language Pre-training on Medical Data with Vision Generation Task using Discrete Visual Representations","created":"2025-03-02","cited_by_count":11},{"id":"2506.19472","title":"USIS16K: High-Quality Dataset for Underwater Salient Instance Segmentation","created":"2025-06-24","cited_by_count":10},{"id":"2407.04230","title":"A Physical Model-Guided Framework for Underwater Image Enhancement and Depth Estimation","created":"2024-07-05","cited_by_count":9},{"id":"2506.17455","title":"AQUA20: A Benchmark Dataset for Underwater Species Classification under Challenging Conditions","created":"2025-06-20","cited_by_count":9},{"id":"2302.10645","title":"BrackishMOT: The Brackish Multi-Object Tracking Dataset","created":"2023-02-21","cited_by_count":7},{"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},{"id":"2505.21755","title":"FRAMES-VQA: Benchmarking Fine-Tuning Robustness across Multi-Modal Shifts in Visual Question Answering","created":"2025-05-27","cited_by_count":5},{"id":"2507.02373","title":"UVLM: Benchmarking Video Language Model for Underwater World Understanding","created":"2025-07-03","cited_by_count":3},{"id":"2410.20624","title":"Towards an LLM-Based Speech Interface for Robot-Assisted Feeding","created":"2024-10-27","cited_by_count":2},{"id":"2503.03640","title":"An Adaptive Underwater Image Enhancement Framework via Multi-Domain Fusion and Color Compensation","created":"2025-03-05","cited_by_count":1}],"next_cursor":null}