{"total":187,"rows":[{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471,"area":"mllm"},{"id":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040,"area":null},{"id":"2308.01390","title":"OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models","created":"2023-08-02","cited_by_count":565,"area":"mllm"},{"id":"2205.14100","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","created":"2022-05-27","cited_by_count":537,"area":null},{"id":"2403.05135","title":"ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment","created":"2024-03-08","cited_by_count":475,"area":"diffusion"},{"id":"2303.11897","title":"TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering","created":"2023-03-21","cited_by_count":428,"area":null},{"id":"2206.08916","title":"Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks","created":"2022-06-17","cited_by_count":421,"area":null},{"id":"2310.18235","title":"Davidsonian Scene Graph: Improving Reliability in Fine-grained Evaluation for Text-to-Image Generation","created":"2023-10-27","cited_by_count":171,"area":null},{"id":"2307.02499","title":"mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding","created":"2023-07-04","cited_by_count":168,"area":"mllm"},{"id":"2302.00402","title":"mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video","created":"2023-02-01","cited_by_count":154,"area":null},{"id":"2308.10741","title":"On the Adversarial Robustness of Multi-Modal Foundation Models","created":"2023-08-21","cited_by_count":145,"area":"safety"},{"id":"2502.21257","title":"RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concrete","created":"2025-02-28","cited_by_count":135,"area":"mllm"},{"id":"2210.09263","title":"Vision-Language Pre-training: Basics, Recent Advances, and Future Trends","created":"2022-10-17","cited_by_count":117,"area":"mllm"},{"id":"2211.01335","title":"Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese","created":"2022-11-02","cited_by_count":109,"area":"mllm"},{"id":"2309.14859","title":"Navigating Text-To-Image Customization: From LyCORIS Fine-Tuning to Model Evaluation","created":"2023-09-26","cited_by_count":109,"area":"diffusion"},{"id":"2505.05472","title":"Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generation","created":"2025-05-08","cited_by_count":109,"area":null},{"id":"2212.05767","title":"A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multimodal","created":"2022-12-12","cited_by_count":106,"area":null},{"id":"2312.11556","title":"StarVector: Generating Scalable Vector Graphics Code from Images and Text","created":"2023-12-17","cited_by_count":102,"area":null},{"id":"2304.06720","title":"Expressive Text-to-Image Generation with Rich Text","created":"2023-04-13","cited_by_count":89,"area":null},{"id":"2307.10864","title":"Divide & Bind Your Attention for Improved Generative Semantic Nursing","created":"2023-07-20","cited_by_count":81,"area":"diffusion"},{"id":"2311.18799","title":"X-InstructBLIP: A Framework for aligning X-Modal instruction-aware representations to LLMs and Emergent Cross-modal Reasoning","created":"2023-11-30","cited_by_count":80,"area":"lr"},{"id":"2305.19195","title":"PanoGen: Text-Conditioned Panoramic Environment Generation for Vision-and-Language Navigation","created":"2023-05-30","cited_by_count":77,"area":null},{"id":"2212.14546","title":"HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training","created":"2022-12-30","cited_by_count":72,"area":null},{"id":"2406.06040","title":"Vript: A Video Is Worth Thousands of Words","created":"2024-06-10","cited_by_count":71,"area":null},{"id":"2506.02161","title":"TIIF-Bench: How Does Your T2I Model Follow Your Instructions?","created":"2025-06-02","cited_by_count":69,"area":null},{"id":"2404.07990","title":"OpenBias: Open-set Bias Detection in Text-to-Image Generative Models","created":"2024-04-11","cited_by_count":61,"area":null},{"id":"2206.08657","title":"BridgeTower: Building Bridges Between Encoders in Vision-Language Representation Learning","created":"2022-06-17","cited_by_count":56,"area":null},{"id":"2404.02747","title":"Faster Diffusion via Temporal Attention Decomposition","created":"2024-04-03","cited_by_count":54,"area":"diffusion"},{"id":"2412.20206","title":"Toward Visual Grounding: A Survey","created":"2024-12-28","cited_by_count":52,"area":null},{"id":"2401.07781","title":"Towards A Better Metric for Text-to-Video Generation","created":"2024-01-15","cited_by_count":51,"area":null},{"id":"2311.01477","title":"FaithScore: Fine-grained Evaluations of Hallucinations in Large Vision-Language Models","created":"2023-11-02","cited_by_count":46,"area":"mllm"},{"id":"2305.13308","title":"If at First You Don't Succeed, Try, Try Again: Faithful Diffusion-based Text-to-Image Generation by Selection","created":"2023-05-22","cited_by_count":40,"area":"diffusion"},{"id":"2405.16785","title":"PromptFix: You Prompt and We Fix the Photo","created":"2024-05-27","cited_by_count":40,"area":"diffusion"},{"id":"2410.10855","title":"Core Knowledge Deficits in Multi-Modal Language Models","created":"2024-10-06","cited_by_count":38,"area":"mllm"},{"id":"2306.04362","title":"Youku-mPLUG: A 10 Million Large-scale Chinese Video-Language Dataset for Pre-training and Benchmarks","created":"2023-06-07","cited_by_count":36,"area":"mllm"},{"id":"2306.14899","title":"FunQA: Towards Surprising Video Comprehension","created":"2023-06-26","cited_by_count":35,"area":null},{"id":"2310.04900","title":"HowToCaption: Prompting LLMs to Transform Video Annotations at Scale","created":"2023-10-07","cited_by_count":34,"area":null},{"id":"2312.01571","title":"How to Configure Good In-Context Sequence for Visual Question Answering","created":"2023-12-04","cited_by_count":33,"area":"mllm"},{"id":"2410.18013","title":"Scalable Ranked Preference Optimization for Text-to-Image Generation","created":"2024-10-23","cited_by_count":33,"area":"alignment"},{"id":"2505.07538","title":"Selftok: Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoning","created":"2025-05-12","cited_by_count":33,"area":"lr"},{"id":"2402.05472","title":"Question Aware Vision Transformer for Multimodal Reasoning","created":"2024-02-08","cited_by_count":32,"area":"lr"},{"id":"2303.00534","title":"RAMM: Retrieval-augmented Biomedical Visual Question Answering with Multi-modal Pre-training","created":"2023-03-01","cited_by_count":31,"area":"rag"},{"id":"2306.02080","title":"Benchmarking Robustness of Adaptation Methods on Pre-trained Vision-Language Models","created":"2023-06-03","cited_by_count":31,"area":"mllm"},{"id":"2402.02460","title":"Review of multimodal machine learning approaches in healthcare","created":"2024-02-04","cited_by_count":31,"area":null},{"id":"2407.15051","title":"Prior Knowledge Integration via LLM Encoding and Pseudo Event Regulation for Video Moment Retrieval","created":"2024-07-21","cited_by_count":30,"area":null},{"id":"2403.11835","title":"Agent3D-Zero: An Agent for Zero-shot 3D Understanding","created":"2024-03-18","cited_by_count":29,"area":"agents"},{"id":"2307.07063","title":"Bootstrapping Vision-Language Learning with Decoupled Language Pre-training","created":"2023-07-13","cited_by_count":28,"area":"synth"},{"id":"2501.10913","title":"Know \"No\" Better: A Data-Driven Approach for Enhancing Negation Awareness in CLIP","created":"2025-01-19","cited_by_count":28,"area":null},{"id":"2410.06699","title":"Break the Visual Perception: Adversarial Attacks Targeting Encoded Visual Tokens of Large Vision-Language Models","created":"2024-10-09","cited_by_count":27,"area":"mllm"},{"id":"2412.09619","title":"SnapGen: Taming High-Resolution Text-to-Image Models for Mobile Devices with Efficient Architectures and Training","created":"2024-12-12","cited_by_count":27,"area":"diffusion"},{"id":"2212.01612","title":"Named Entity and Relation Extraction with Multi-Modal Retrieval","created":"2022-12-03","cited_by_count":26,"area":null},{"id":"2503.00936","title":"IteRPrimE: Zero-shot Referring Image Segmentation with Iterative Grad-CAM Refinement and Primary Word Emphasis","created":"2025-03-02","cited_by_count":26,"area":null},{"id":"2305.06002","title":"InfoMetIC: An Informative Metric for Reference-free Image Caption Evaluation","created":"2023-05-10","cited_by_count":25,"area":null},{"id":"2311.00308","title":"From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunities","created":"2023-11-01","cited_by_count":25,"area":null},{"id":"2305.08381","title":"Parameter-efficient Tuning of Large-scale Multimodal Foundation Model","created":"2023-05-15","cited_by_count":23,"area":null},{"id":"2212.13563","title":"Noise-aware Learning from Web-crawled Image-Text Data for Image Captioning","created":"2022-12-27","cited_by_count":22,"area":null},{"id":"2312.01697","title":"Hulk: A Universal Knowledge Translator for Human-Centric Tasks","created":"2023-12-04","cited_by_count":22,"area":null},{"id":"2303.01903","title":"Prophet: Prompting Large Language Models with Complementary Answer Heuristics for Knowledge-based Visual Question Answering","created":"2023-03-03","cited_by_count":21,"area":null},{"id":"2305.04474","title":"TRIPS: Efficient Vision-and-Language Pre-training with Text-Relevant Image Patch Selection","created":"2023-05-08","cited_by_count":18,"area":null},{"id":"2401.08815","title":"Adversarial Supervision Makes Layout-to-Image Diffusion Models Thrive","created":"2024-01-16","cited_by_count":18,"area":"diffusion"},{"id":"2403.11821","title":"A Survey on Quality Metrics for Text-to-Image Generation","created":"2024-03-18","cited_by_count":18,"area":null},{"id":"2404.04251","title":"Who Evaluates the Evaluations? Objectively Scoring Text-to-Image Prompt Coherence Metrics with T2IScoreScore (TS2)","created":"2024-04-05","cited_by_count":18,"area":null},{"id":"2403.18493","title":"VersaT2I: Improving Text-to-Image Models with Versatile Reward","created":"2024-03-27","cited_by_count":17,"area":null},{"id":"2409.12784","title":"Evaluating Image Hallucination in Text-to-Image Generation with Question-Answering","created":"2024-09-19","cited_by_count":16,"area":null},{"id":"2301.07389","title":"Towards Models that Can See and Read","created":"2023-01-18","cited_by_count":15,"area":null},{"id":"2305.02177","title":"Transforming Visual Scene Graphs to Image Captions","created":"2023-05-03","cited_by_count":15,"area":"moe"},{"id":"2311.17095","title":"Emergent Open-Vocabulary Semantic Segmentation from Off-the-shelf Vision-Language Models","created":"2023-11-28","cited_by_count":15,"area":"mllm"},{"id":"2509.19244","title":"Lavida-O: Elastic Large Masked Diffusion Models for Unified Multimodal Understanding and Generation","created":"2025-09-23","cited_by_count":15,"area":"diffusion"},{"id":"2304.08821","title":"TTIDA: Controllable Generative Data Augmentation via Text-to-Text and Text-to-Image Models","created":"2023-04-18","cited_by_count":14,"area":null},{"id":"2403.06952","title":"SELMA: Learning and Merging Skill-Specific Text-to-Image Experts with Auto-Generated Data","created":"2024-03-11","cited_by_count":14,"area":null},{"id":"2209.15214","title":"Construction and Applications of Billion-Scale Pre-Trained Multimodal Business Knowledge Graph","created":"2022-09-30","cited_by_count":13,"area":null},{"id":"2411.15236","title":"Text Embedding is Not All You Need: Attention Control for Text-to-Image Semantic Alignment with Text Self-Attention Maps","created":"2024-11-21","cited_by_count":12,"area":"diffusion"},{"id":"2210.04559","title":"CLIP-Diffusion-LM: Apply Diffusion Model on Image Captioning","created":"2022-10-10","cited_by_count":11,"area":"diffusion"},{"id":"2403.04321","title":"Discriminative Probing and Tuning for Text-to-Image Generation","created":"2024-03-07","cited_by_count":11,"area":null},{"id":"2303.03761","title":"Graph Neural Networks in Vision-Language Image Understanding: A Survey","created":"2023-03-07","cited_by_count":10,"area":null},{"id":"2303.17376","title":"A Study of Autoregressive Decoders for Multi-Tasking in Computer Vision","created":"2023-03-30","cited_by_count":10,"area":null},{"id":"2507.05056","title":"INTER: Mitigating Hallucination in Large Vision-Language Models by Interaction Guidance Sampling","created":"2025-07-07","cited_by_count":10,"area":"mllm"},{"id":"2306.05240","title":"Dealing with Semantic Underspecification in Multimodal NLP","created":"2023-06-08","cited_by_count":9,"area":null},{"id":"2404.13370","title":"Movie101v2: Improved Movie Narration Benchmark","created":"2024-04-20","cited_by_count":9,"area":null},{"id":"2503.20502","title":"MLLM-Selector: Necessity and Diversity-driven High-Value Data Selection for Enhanced Visual Instruction Tuning","created":"2025-03-26","cited_by_count":9,"area":"mllm"},{"id":"2404.18397","title":"ViOCRVQA: Novel Benchmark Dataset and Vision Reader for Visual Question Answering by Understanding Vietnamese Text in Images","created":"2024-04-29","cited_by_count":8,"area":null},{"id":"2508.06350","title":"Aligning Effective Tokens with Video Anomaly in Large Language Models","created":"2025-08-08","cited_by_count":8,"area":null},{"id":"2209.06954","title":"Correlation Information Bottleneck: Towards Adapting Pretrained Multimodal Models for Robust Visual Question Answering","created":"2022-09-14","cited_by_count":7,"area":"mllm"},{"id":"2307.03153","title":"MultiVENT: Multilingual Videos of Events with Aligned Natural Text","created":"2023-07-06","cited_by_count":7,"area":null},{"id":"2308.04288","title":"Cloth2Tex: A Customized Cloth Texture Generation Pipeline for 3D Virtual Try-On","created":"2023-08-08","cited_by_count":7,"area":null},{"id":"2310.14670","title":"Dataset Bias Mitigation in Multiple-Choice Visual Question Answering and Beyond","created":"2023-10-23","cited_by_count":7,"area":null},{"id":"2404.10652","title":"ViTextVQA: A Large-Scale Visual Question Answering Dataset and a Novel Multimodal Feature Fusion Method for Vietnamese Text Comprehension in Images","created":"2024-04-16","cited_by_count":7,"area":null},{"id":"2505.00502","title":"Towards Scalable Human-aligned Benchmark for Text-guided Image Editing","created":"2025-05-01","cited_by_count":7,"area":null},{"id":"2508.11011","title":"Are Large Pre-trained Vision Language Models Effective Construction Safety Inspectors?","created":"2025-08-14","cited_by_count":7,"area":"mllm"},{"id":"2509.05208","title":"Symbolic Graphics Programming with Large Language Models","created":"2025-09-05","cited_by_count":7,"area":null},{"id":"2308.16689","title":"ViLTA: Enhancing Vision-Language Pre-training through Textual Augmentation","created":"2023-08-31","cited_by_count":6,"area":"mllm"},{"id":"2309.08022","title":"Empowering Visually Impaired Individuals: A Novel Use of Apple Live Photos and Android Motion Photos","created":"2023-09-14","cited_by_count":6,"area":null},{"id":"2410.02773","title":"Mind the Uncertainty in Human Disagreement: Evaluating Discrepancies between Model Predictions and Human Responses in VQA","created":"2024-09-17","cited_by_count":6,"area":"mllm"},{"id":"2410.13754","title":"MixEval-X: Any-to-Any Evaluations from Real-World Data Mixtures","created":"2024-10-17","cited_by_count":6,"area":null},{"id":"2411.15435","title":"What Makes a Scene ? Scene Graph-based Evaluation and Feedback for Controllable Generation","created":"2024-11-23","cited_by_count":6,"area":null},{"id":"2504.18856","title":"Multi-Resolution Pathology-Language Pre-training Model with Text-Guided Visual Representation","created":"2025-04-26","cited_by_count":6,"area":"mllm"},{"id":"2505.16915","title":"DetailMaster: Can Your Text-to-Image Model Handle Long Prompts?","created":"2025-05-22","cited_by_count":6,"area":null},{"id":"2305.12144","title":"DiffCap: Exploring Continuous Diffusion on Image Captioning","created":"2023-05-20","cited_by_count":5,"area":null},{"id":"2307.03254","title":"Vision Language Transformers: A Survey","created":"2023-07-06","cited_by_count":5,"area":"mllm"},{"id":"2307.08504","title":"BUS:Efficient and Effective Vision-language Pre-training with Bottom-Up Patch Summarization","created":"2023-07-17","cited_by_count":5,"area":"mllm"}],"next_cursor":"100"}