{"total":104,"rows":[{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1111,"area":"mllm"},{"id":"2305.03726","title":"Otter: A Multi-Modal Model with In-Context Instruction Tuning","created":"2023-05-05","cited_by_count":551,"area":"mllm"},{"id":"2311.06242","title":"Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks","created":"2023-11-10","cited_by_count":413,"area":null},{"id":"2309.11499","title":"DreamLLM: Synergistic Multimodal Comprehension and Creation","created":"2023-09-20","cited_by_count":297,"area":"mllm"},{"id":"2412.04468","title":"NVILA: Efficient Frontier Visual Language Models","created":"2024-12-05","cited_by_count":211,"area":"mllm"},{"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":175,"area":null},{"id":"2309.02591","title":"Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning","created":"2023-09-05","cited_by_count":171,"area":"mllm"},{"id":"2106.06963","title":"Exploring and Distilling Posterior and Prior Knowledge for Radiology Report Generation","created":"2021-06-13","cited_by_count":162,"area":null},{"id":"2101.06894","title":"Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene Graphs","created":"2021-01-18","cited_by_count":148,"area":null},{"id":"2410.03051","title":"AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark","created":"2024-10-04","cited_by_count":143,"area":null},{"id":"2107.06912","title":"From Show to Tell: A Survey on Deep Learning-based Image Captioning","created":"2021-07-14","cited_by_count":138,"area":null},{"id":"2404.19753","title":"DOCCI: Descriptions of Connected and Contrasting Images","created":"2024-04-30","cited_by_count":133,"area":null},{"id":"2306.04387","title":"M$^3$IT: A Large-Scale Dataset towards Multi-Modal Multilingual Instruction Tuning","created":"2023-06-07","cited_by_count":128,"area":null},{"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":"2401.10208","title":"MM-Interleaved: Interleaved Image-Text Generative Modeling via Multi-modal Feature Synchronizer","created":"2024-01-18","cited_by_count":81,"area":null},{"id":"2206.14579","title":"Competence-based Multimodal Curriculum Learning for Medical Report Generation","created":"2022-06-24","cited_by_count":76,"area":null},{"id":"2106.06965","title":"Contrastive Attention for Automatic Chest X-ray Report Generation","created":"2021-06-13","cited_by_count":71,"area":null},{"id":"2412.03548","title":"Perception Tokens Enhance Visual Reasoning in Multimodal Language Models","created":"2024-12-04","cited_by_count":71,"area":"lr"},{"id":"2401.12915","title":"Red Teaming Visual Language Models","created":"2024-01-23","cited_by_count":66,"area":"mllm"},{"id":"2203.10095","title":"AlignTransformer: Hierarchical Alignment of Visual Regions and Disease Tags for Medical Report Generation","created":"2022-03-18","cited_by_count":65,"area":null},{"id":"2203.05081","title":"NLX-GPT: A Model for Natural Language Explanations in Vision and Vision-Language Tasks","created":"2022-03-09","cited_by_count":60,"area":null},{"id":"2207.04818","title":"Cross-modal Prototype Driven Network for Radiology Report Generation","created":"2022-07-11","cited_by_count":59,"area":null},{"id":"2311.17946","title":"DreamSync: Aligning Text-to-Image Generation with Image Understanding Feedback","created":"2023-11-29","cited_by_count":58,"area":null},{"id":"2102.03247","title":"GaitSet: Cross-view Gait Recognition through Utilizing Gait as a Deep Set","created":"2021-02-05","cited_by_count":57,"area":null},{"id":"2405.02793","title":"ImageInWords: Unlocking Hyper-Detailed Image Descriptions","created":"2024-05-05","cited_by_count":57,"area":null},{"id":"2503.04130","title":"STORM: Token-Efficient Long Video Understanding for Multimodal LLMs","created":"2025-03-06","cited_by_count":49,"area":"mllm"},{"id":"2402.15487","title":"RoboEXP: Action-Conditioned Scene Graph via Interactive Exploration for Robotic Manipulation","created":"2024-02-23","cited_by_count":48,"area":null},{"id":"2111.04318","title":"Auto-Encoding Knowledge Graph for Unsupervised Medical Report Generation","created":"2021-11-08","cited_by_count":47,"area":null},{"id":"2404.16820","title":"Revisiting Text-to-Image Evaluation with Gecko: On Metrics, Prompts, and Human Ratings","created":"2024-04-25","cited_by_count":45,"area":null},{"id":"2307.01003","title":"Visual Instruction Tuning with Polite Flamingo","created":"2023-07-03","cited_by_count":38,"area":"mllm"},{"id":"2405.15232","title":"DEEM: Diffusion Models Serve as the Eyes of Large Language Models for Image Perception","created":"2024-05-24","cited_by_count":32,"area":"mllm"},{"id":"2410.20482","title":"What Factors Affect Multi-Modal In-Context Learning? An In-Depth Exploration","created":"2024-10-27","cited_by_count":32,"area":"lr"},{"id":"2405.13581","title":"Safety Alignment for Vision Language Models","created":"2024-05-22","cited_by_count":29,"area":"mllm"},{"id":"2109.04988","title":"Panoptic Narrative Grounding","created":"2021-09-10","cited_by_count":27,"area":null},{"id":"2407.17453","title":"VILA$^2$: VILA Augmented VILA","created":"2024-07-24","cited_by_count":26,"area":"mllm"},{"id":"2108.05067","title":"Medical-VLBERT: Medical Visual Language BERT for COVID-19 CT Report Generation With Alternate Learning","created":"2021-08-11","cited_by_count":24,"area":null},{"id":"2108.12126","title":"Automated Generation of Accurate \\& Fluent Medical X-ray Reports","created":"2021-08-27","cited_by_count":24,"area":null},{"id":"2302.11217","title":"Connecting Vision and Language with Video Localized Narratives","created":"2023-02-22","cited_by_count":24,"area":null},{"id":"2303.15932","title":"Unify, Align and Refine: Multi-Level Semantic Alignment for Radiology Report Generation","created":"2023-03-28","cited_by_count":23,"area":null},{"id":"2105.14477","title":"Towards Diverse Paragraph Captioning for Untrimmed Videos","created":"2021-05-30","cited_by_count":22,"area":null},{"id":"2211.01412","title":"CAMANet: Class Activation Map Guided Attention Network for Radiology Report Generation","created":"2022-11-02","cited_by_count":22,"area":null},{"id":"2206.01843","title":"Visual Clues: Bridging Vision and Language Foundations for Image Paragraph Captioning","created":"2022-06-03","cited_by_count":21,"area":null},{"id":"2405.17927","title":"The Evolution of Multimodal Model Architectures","created":"2024-05-28","cited_by_count":21,"area":null},{"id":"2302.01328","title":"IC3: Image Captioning by Committee Consensus","created":"2023-02-02","cited_by_count":20,"area":null},{"id":"2106.07207","title":"Straight to the Gradient: Learning to Use Novel Tokens for Neural Text Generation","created":"2021-06-14","cited_by_count":19,"area":null},{"id":"2207.01208","title":"Attributed Abnormality Graph Embedding for Clinically Accurate X-Ray Report Generation","created":"2022-07-04","cited_by_count":17,"area":null},{"id":"2408.14622","title":"What Makes a Good Story and How Can We Measure It? A Comprehensive Survey of Story Evaluation","created":"2024-08-26","cited_by_count":17,"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":15,"area":null},{"id":"2502.15786","title":"MindLLM: A Subject-Agnostic and Versatile Model for fMRI-to-Text Decoding","created":"2025-02-18","cited_by_count":14,"area":null},{"id":"2104.01703","title":"FixMyPose: Pose Correctional Captioning and Retrieval","created":"2021-04-04","cited_by_count":12,"area":null},{"id":"2308.09033","title":"Uni-NLX: Unifying Textual Explanations for Vision and Vision-Language Tasks","created":"2023-08-17","cited_by_count":12,"area":null},{"id":"2403.16167","title":"ESREAL: Exploiting Semantic Reconstruction to Mitigate Hallucinations in Vision-Language Models","created":"2024-03-24","cited_by_count":12,"area":"mllm"},{"id":"2405.00485","title":"What Makes for Good Image Captions?","created":"2024-05-01","cited_by_count":12,"area":null},{"id":"2305.09758","title":"A Video Is Worth 4096 Tokens: Verbalize Videos To Understand Them In Zero Shot","created":"2023-05-16","cited_by_count":11,"area":null},{"id":"2401.05054","title":"Generating Diverse and High-Quality Texts by Minimum Bayes Risk Decoding","created":"2024-01-10","cited_by_count":11,"area":null},{"id":"2404.10763","title":"LaDiC: Are Diffusion Models Really Inferior to Autoregressive Counterparts for Image-to-Text Generation?","created":"2024-04-16","cited_by_count":9,"area":"diffusion"},{"id":"2506.10286","title":"HalLoc: Token-level Localization of Hallucinations for Vision Language Models","created":"2025-06-12","cited_by_count":9,"area":"mllm"},{"id":"2507.02591","title":"AuroraLong: Bringing RNNs Back to Efficient Open-Ended Video Understanding","created":"2025-07-03","cited_by_count":9,"area":null},{"id":"2502.16427","title":"Fine-Grained Captioning of Long Videos through Scene Graph Consolidation","created":"2025-02-23","cited_by_count":8,"area":"mllm"},{"id":"2101.03287","title":"Unifying Relational Sentence Generation and Retrieval for Medical Image Report Composition","created":"2021-01-09","cited_by_count":7,"area":null},{"id":"2305.12943","title":"Album Storytelling with Iterative Story-aware Captioning and Large Language Models","created":"2023-05-22","cited_by_count":7,"area":null},{"id":"2307.14634","title":"Fact-Checking of AI-Generated Reports","created":"2023-07-27","cited_by_count":7,"area":null},{"id":"2305.14281","title":"Weakly-Supervised Learning of Visual Relations in Multimodal Pretraining","created":"2023-05-23","cited_by_count":6,"area":null},{"id":"2311.07285","title":"Multi Sentence Description of Complex Manipulation Action Videos","created":"2023-11-13","cited_by_count":6,"area":null},{"id":"2405.04175","title":"Topicwise Separable Sentence Retrieval for Medical Report Generation","created":"2024-05-07","cited_by_count":5,"area":null},{"id":"2509.25818","title":"VELA: An LLM-Hybrid-as-a-Judge Approach for Evaluating Long Image Captions","created":"2025-09-30","cited_by_count":5,"area":"mllm"},{"id":"2103.05131","title":"Few-Shot Learning of an Interleaved Text Summarization Model by Pretraining with Synthetic Data","created":"2021-03-08","cited_by_count":4,"area":null},{"id":"2211.14835","title":"CLID: Controlled-Length Image Descriptions with Limited Data","created":"2022-11-27","cited_by_count":4,"area":null},{"id":"2306.13460","title":"Learning Descriptive Image Captioning via Semipermeable Maximum Likelihood Estimation","created":"2023-06-23","cited_by_count":4,"area":null},{"id":"2403.04343","title":"Adaptive Task Balancing for Visual Instruction Tuning via Inter-Task Contribution and Intra-Task Difficulty","created":"2024-03-07","cited_by_count":4,"area":"mllm"},{"id":"2305.01928","title":"Visual Transformation Telling","created":"2023-05-03","cited_by_count":3,"area":null},{"id":"2308.03767","title":"Enhancing image captioning with depth information using a Transformer-based framework","created":"2023-07-24","cited_by_count":3,"area":null},{"id":"2308.10447","title":"Explore and Tell: Embodied Visual Captioning in 3D Environments","created":"2023-08-21","cited_by_count":3,"area":null},{"id":"2311.13307","title":"Rethinking Radiology Report Generation via Causal Inspired Counterfactual Augmentation","created":"2023-11-22","cited_by_count":3,"area":null},{"id":"2401.08968","title":"COCO is \"ALL'' You Need for Visual Instruction Fine-tuning","created":"2024-01-17","cited_by_count":3,"area":"mllm"},{"id":"2407.11449","title":"Controllable Contextualized Image Captioning: Directing the Visual Narrative through User-Defined Highlights","created":"2024-07-16","cited_by_count":3,"area":null},{"id":"2508.18904","title":"Event-Enriched Image Analysis Grand Challenge at ACM Multimedia 2025","created":"2025-08-26","cited_by_count":3,"area":null},{"id":"2103.08298","title":"Knowledge driven Description Synthesis for Floor Plan Interpretation","created":"2021-03-15","cited_by_count":2,"area":null},{"id":"2105.04143","title":"Matching Visual Features to Hierarchical Semantic Topics for Image Paragraph Captioning","created":"2021-05-10","cited_by_count":2,"area":null},{"id":"2210.01338","title":"Learning to Collocate Visual-Linguistic Neural Modules for Image Captioning","created":"2022-10-04","cited_by_count":2,"area":null},{"id":"2409.19676","title":"See Detail Say Clear: Towards Brain CT Report Generation via Pathological Clue-driven Representation Learning","created":"2024-09-29","cited_by_count":2,"area":null},{"id":"2505.18115","title":"Instructify: Demystifying Metadata to Visual Instruction Tuning Data Conversion","created":"2025-05-23","cited_by_count":2,"area":null},{"id":"2505.22943","title":"Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates","created":"2025-05-28","cited_by_count":2,"area":null},{"id":"2506.15649","title":"Dual-Stage Value-Guided Inference with Margin-Based Reward Adjustment for Fast and Faithful VLM Captioning","created":"2025-06-18","cited_by_count":2,"area":"mllm"},{"id":"2108.12575","title":"Goal-driven text descriptions for images","created":"2021-08-28","cited_by_count":1,"area":null},{"id":"2110.09756","title":"A Picture is Worth a Thousand Words: A Unified System for Diverse Captions and Rich Images Generation","created":"2021-10-19","cited_by_count":1,"area":null},{"id":"2308.01035","title":"TS-RGBD Dataset: a Novel Dataset for Theatre Scenes Description for People with Visual Impairments","created":"2023-08-02","cited_by_count":1,"area":null},{"id":"2310.00503","title":"Black-box Attacks on Image Activity Prediction and its Natural Language Explanations","created":"2023-09-30","cited_by_count":1,"area":null},{"id":"2310.09767","title":"VLIS: Unimodal Language Models Guide Multimodal Language Generation","created":"2023-10-15","cited_by_count":1,"area":"mllm"},{"id":"2410.19307","title":"Semi-supervised Chinese Poem-to-Painting Generation via Cycle-consistent Adversarial Networks","created":"2024-10-25","cited_by_count":1,"area":null},{"id":"2410.22648","title":"SimpsonsVQA: Enhancing Inquiry-Based Learning with a Tailored Dataset","created":"2024-10-30","cited_by_count":1,"area":null},{"id":"2102.11526","title":"Enhanced Modality Transition for Image Captioning","created":"2021-02-23","cited_by_count":0,"area":null},{"id":"2202.05331","title":"Describing image focused in cognitive and visual details for visually impaired people: An approach to generating inclusive paragraphs","created":"2022-02-10","cited_by_count":0,"area":null},{"id":"2203.06458","title":"Factored Attention and Embedding for Unstructured-view Topic-related Ultrasound Report Generation","created":"2022-03-12","cited_by_count":0,"area":null},{"id":"2206.10059","title":"Bypass Network for Semantics Driven Image Paragraph Captioning","created":"2022-06-21","cited_by_count":0,"area":null},{"id":"2209.01996","title":"Bridging Music and Text with Crowdsourced Music Comments: A Sequence-to-Sequence Framework for Thematic Music Comments Generation","created":"2022-09-05","cited_by_count":0,"area":null},{"id":"2311.12799","title":"A Fine-Grained Image Description Generation Method Based on Joint Objectives","created":"2023-09-02","cited_by_count":0,"area":null},{"id":"2503.09443","title":"Scaling Laws for Conditional Emergence of Multilingual Image Captioning via Generalization from Translation","created":"2025-03-12","cited_by_count":0,"area":"mllm"},{"id":"2512.23185","title":"EIR: Enhanced Image Representations for Medical Report Generation","created":"2025-12-29","cited_by_count":0,"area":null},{"id":"2606.09846","title":"CANVAS: Captioning Art with Narrative Visual-Audio AI Systems","created":"2026-04-30","cited_by_count":0,"area":null}],"next_cursor":"100"}