{"list":"other","total":94,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"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":"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":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2311.16502","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","created":"2023-11-27","cited_by_count":2080},{"id":"2412.05271","title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","created":"2024-12-06","cited_by_count":1599},{"id":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"id":"2102.08981","title":"Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts","created":"2021-02-17","cited_by_count":1216},{"id":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"2306.14824","title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","created":"2023-06-26","cited_by_count":1089},{"id":"2408.01800","title":"MiniCPM-V: A GPT-4V Level MLLM on Your Phone","created":"2024-08-03","cited_by_count":1079},{"id":"2306.05424","title":"Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models","created":"2023-06-08","cited_by_count":1062},{"id":"2311.12793","title":"ShareGPT4V: Improving Large Multi-Modal Models with Better Captions","created":"2023-11-21","cited_by_count":1005},{"id":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857},{"id":"1603.07396","title":"A Diagram Is Worth A Dozen Images","created":"2016-03-24","cited_by_count":804},{"id":"2309.12284","title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","created":"2023-09-21","cited_by_count":735},{"id":"2311.03079","title":"CogVLM: Visual Expert for Pretrained Language Models","created":"2023-11-06","cited_by_count":708},{"id":"2312.07533","title":"VILA: On Pre-training for Visual Language Models","created":"2023-12-12","cited_by_count":692},{"id":"1703.09788","title":"Towards Automatic Learning of Procedures from Web Instructional Videos","created":"2017-03-28","cited_by_count":619},{"id":"2407.07895","title":"LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models","created":"2024-07-10","cited_by_count":584},{"id":"2410.02713","title":"LLaVA-Video: Video Instruction Tuning With Synthetic Data","created":"2024-10-03","cited_by_count":583},{"id":"2412.10302","title":"DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding","created":"2024-12-13","cited_by_count":572},{"id":"2307.16449","title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","created":"2023-07-31","cited_by_count":542},{"id":"2501.13106","title":"VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding","created":"2025-01-22","cited_by_count":518},{"id":"2307.06942","title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","created":"2023-07-13","cited_by_count":497},{"id":"2402.19479","title":"Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers","created":"2024-02-29","cited_by_count":393},{"id":"2406.04325","title":"ShareGPT4Video: Improving Video Understanding and Generation with Better Captions","created":"2024-06-06","cited_by_count":388},{"id":"2403.00476","title":"TempCompass: Do Video LLMs Really Understand Videos?","created":"2024-03-01","cited_by_count":363},{"id":"2407.12772","title":"LMMs-Eval: Reality Check on the Evaluation of Large Multimodal Models","created":"2024-07-17","cited_by_count":353},{"id":"2407.02371","title":"OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation","created":"2024-07-02","cited_by_count":341},{"id":"2306.16527","title":"OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents","created":"2023-06-21","cited_by_count":316},{"id":"2305.13786","title":"Perception Test: A Diagnostic Benchmark for Multimodal Video Models","created":"2023-05-23","cited_by_count":314},{"id":"1907.06987","title":"A Short Note on the Kinetics-700 Human Action Dataset","created":"2019-07-15","cited_by_count":310},{"id":"2103.01913","title":"WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning","created":"2021-03-02","cited_by_count":287},{"id":"2408.16500","title":"CogVLM2: Visual Language Models for Image and Video Understanding","created":"2024-08-29","cited_by_count":217},{"id":"2405.01483","title":"MANTIS: Interleaved Multi-Image Instruction Tuning","created":"2024-05-02","cited_by_count":216},{"id":"2412.04468","title":"NVILA: Efficient Frontier Visual Language Models","created":"2024-12-05","cited_by_count":209},{"id":"2410.01560","title":"OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data","created":"2024-10-02","cited_by_count":200},{"id":"2501.01957","title":"VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction","created":"2025-01-03","cited_by_count":197},{"id":"1605.03705","title":"Movie Description","created":"2016-05-12","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":"2311.03054","title":"AnyText: Multilingual Visual Text Generation And Editing","created":"2023-11-06","cited_by_count":170},{"id":"2409.12961","title":"Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution","created":"2024-09-19","cited_by_count":159},{"id":"1909.07145","title":"ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text (RRC-ArT)","created":"2019-09-16","cited_by_count":147},{"id":"2404.01258","title":"Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward","created":"2024-04-01","cited_by_count":147},{"id":"2404.03384","title":"LongVLM: Efficient Long Video Understanding via Large Language Models","created":"2024-04-04","cited_by_count":147},{"id":"2407.06358","title":"MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captions","created":"2024-07-08","cited_by_count":146},{"id":"2407.00634","title":"Tarsier: Recipes for Training and Evaluating Large Video Description Models","created":"2024-06-30","cited_by_count":141},{"id":"2411.13093","title":"Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension","created":"2024-11-20","cited_by_count":138},{"id":"1909.07741","title":"ICDAR 2019 Competition on Large-scale Street View Text with Partial Labeling -- RRC-LSVT","created":"2019-09-17","cited_by_count":122},{"id":"2409.10695","title":"Playground v3: Improving Text-to-Image Alignment with Deep-Fusion Large Language Models","created":"2024-09-16","cited_by_count":116},{"id":"2202.06767","title":"Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmark","created":"2022-02-14","cited_by_count":114},{"id":"2405.08813","title":"CinePile: A Long Video Question Answering Dataset and Benchmark","created":"2024-05-14","cited_by_count":114},{"id":"2303.14717","title":"CelebV-Text: A Large-Scale Facial Text-Video Dataset","created":"2023-03-26","cited_by_count":104},{"id":"2410.03290","title":"Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models","created":"2024-10-04","cited_by_count":91},{"id":"2402.19474","title":"The All-Seeing Project V2: Towards General Relation Comprehension of the Open World","created":"2024-02-29","cited_by_count":90},{"id":"2406.11833","title":"MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMs","created":"2024-06-17","cited_by_count":90},{"id":"2502.10391","title":"MM-RLHF: The Next Step Forward in Multimodal LLM Alignment","created":"2025-02-14","cited_by_count":83},{"id":"1911.11206","title":"Oops! Predicting Unintentional Action in Video","created":"2019-11-25","cited_by_count":82},{"id":"2406.18522","title":"ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation","created":"2024-06-26","cited_by_count":75},{"id":"2407.08303","title":"DenseFusion-1M: Merging Vision Experts for Comprehensive Multimodal Perception","created":"2024-07-11","cited_by_count":73},{"id":"2406.06040","title":"Vript: A Video Is Worth Thousands of Words","created":"2024-06-10","cited_by_count":71},{"id":"2006.15418","title":"Counting Out Time: Class Agnostic Video Repetition Counting in the Wild","created":"2020-06-27","cited_by_count":68},{"id":"2410.18558","title":"Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction Data","created":"2024-10-24","cited_by_count":67},{"id":"2501.15891","title":"Any2AnyTryon: Leveraging Adaptive Position Embeddings for Versatile Virtual Clothing Tasks","created":"2025-01-27","cited_by_count":63},{"id":"2408.02629","title":"VidGen-1M: A Large-Scale Dataset for Text-to-video Generation","created":"2024-08-05","cited_by_count":62},{"id":"2404.04346","title":"Koala: Key frame-conditioned long video-LLM","created":"2024-04-05","cited_by_count":57},{"id":"2409.16597","title":"EventHallusion: Diagnosing Event Hallucinations in Video LLMs","created":"2024-09-25","cited_by_count":57},{"id":"2312.10300","title":"Shot2Story: A New Benchmark for Comprehensive Understanding of Multi-shot Videos","created":"2023-12-16","cited_by_count":54},{"id":"2105.04489","title":"Spoken Moments: Learning Joint Audio-Visual Representations from Video Descriptions","created":"2021-05-10","cited_by_count":53},{"id":"2204.01018","title":"TransRAC: Encoding Multi-scale Temporal Correlation with Transformers for Repetitive Action Counting","created":"2022-04-03","cited_by_count":44},{"id":"2406.08407","title":"MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videos","created":"2024-06-12","cited_by_count":43},{"id":"2409.05840","title":"MMEvol: Empowering Multimodal Large Language Models with Evol-Instruct","created":"2024-09-09","cited_by_count":42},{"id":"2402.07220","title":"KVQ: Kwai Video Quality Assessment for Short-form Videos","created":"2024-02-11","cited_by_count":38},{"id":"2407.15838","title":"MMInstruct: A High-Quality Multi-Modal Instruction Tuning Dataset with Extensive Diversity","created":"2024-07-22","cited_by_count":38},{"id":"1911.00232","title":"Multi-Moments in Time: Learning and Interpreting Models for Multi-Action Video Understanding","created":"2019-11-01","cited_by_count":37},{"id":"2410.10816","title":"LVD-2M: A Long-take Video Dataset with Temporally Dense Captions","created":"2024-10-14","cited_by_count":25},{"id":"2410.23144","title":"Public Domain 12M: A Highly Aesthetic Image-Text Dataset with Novel Governance Mechanisms","created":"2024-10-30","cited_by_count":15},{"id":"2407.15295","title":"VideoGameBunny: Towards vision assistants for video games","created":"2024-07-21","cited_by_count":11},{"id":"2411.07461","title":"BLIP3-KALE: Knowledge Augmented Large-Scale Dense Captions","created":"2024-11-12","cited_by_count":9},{"id":"2412.05243","title":"CompCap: Improving Multimodal Large Language Models with Composite Captions","created":"2024-12-06","cited_by_count":8},{"id":"2406.13923","title":"PIN: A Knowledge-Intensive Dataset for Paired and Interleaved Multimodal Documents","created":"2024-06-20","cited_by_count":7},{"id":"2407.06723","title":"Graph-Based Captioning: Enhancing Visual Descriptions by Interconnecting Region Captions","created":"2024-07-09","cited_by_count":7}],"next_cursor":null}