{"total":170,"rows":[{"id":"2210.01936","title":"When and why vision-language models behave like bags-of-words, and what to do about it?","created":"2022-10-04","cited_by_count":610,"area":"mllm"},{"id":"2312.13286","title":"Generative Multimodal Models are In-Context Learners","created":"2023-12-20","cited_by_count":446,"area":"mllm"},{"id":"2206.02779","title":"Blended Latent Diffusion","created":"2022-06-06","cited_by_count":432,"area":"mllm"},{"id":"2306.16527","title":"OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents","created":"2023-06-21","cited_by_count":316,"area":"mllm"},{"id":"2309.11499","title":"DreamLLM: Synergistic Multimodal Comprehension and Creation","created":"2023-09-20","cited_by_count":297,"area":"mllm"},{"id":"2303.02153","title":"Unleashing Text-to-Image Diffusion Models for Visual Perception","created":"2023-03-03","cited_by_count":269,"area":"mllm"},{"id":"2305.17216","title":"Generating Images with Multimodal Language Models","created":"2023-05-26","cited_by_count":260,"area":"mllm"},{"id":"2401.11708","title":"Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs","created":"2024-01-22","cited_by_count":224,"area":"mllm"},{"id":"2307.00716","title":"JourneyDB: A Benchmark for Generative Image Understanding","created":"2023-07-03","cited_by_count":205,"area":"mllm"},{"id":"2302.12066","title":"Teaching CLIP to Count to Ten","created":"2023-02-23","cited_by_count":198,"area":"mllm"},{"id":"2311.13165","title":"Multimodal Large Language Models: A Survey","created":"2023-11-22","cited_by_count":195,"area":"mllm"},{"id":"2309.17102","title":"Guiding Instruction-based Image Editing via Multimodal Large Language Models","created":"2023-09-29","cited_by_count":185,"area":"mllm"},{"id":"2212.07796","title":"CREPE: Can Vision-Language Foundation Models Reason Compositionally?","created":"2022-12-13","cited_by_count":181,"area":"mllm"},{"id":"2312.06739","title":"SmartEdit: Exploring Complex Instruction-based Image Editing with Multimodal Large Language Models","created":"2023-12-11","cited_by_count":177,"area":"mllm"},{"id":"2309.02591","title":"Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning","created":"2023-09-05","cited_by_count":170,"area":"mllm"},{"id":"2308.06038","title":"Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuning","created":"2023-08-11","cited_by_count":154,"area":"mllm"},{"id":"2302.00070","title":"Debiasing Vision-Language Models via Biased Prompts","created":"2023-01-31","cited_by_count":149,"area":"mllm"},{"id":"2407.05600","title":"GenArtist: Multimodal LLM as an Agent for Unified Image Generation and Editing","created":"2024-07-08","cited_by_count":133,"area":"mllm"},{"id":"2402.11574","title":"Visual In-Context Learning for Large Vision-Language Models","created":"2024-02-18","cited_by_count":128,"area":"mllm"},{"id":"2310.14414","title":"Vision Language Models in Autonomous Driving: A Survey and Outlook","created":"2023-10-22","cited_by_count":126,"area":"mllm"},{"id":"2211.12561","title":"Retrieval-Augmented Multimodal Language Modeling","created":"2022-11-22","cited_by_count":125,"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":"2305.10400","title":"What You See is What You Read? Improving Text-Image Alignment Evaluation","created":"2023-05-17","cited_by_count":108,"area":"mllm"},{"id":"2310.02992","title":"Kosmos-G: Generating Images in Context with Multimodal Large Language Models","created":"2023-10-04","cited_by_count":105,"area":"mllm"},{"id":"2402.03161","title":"Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization","created":"2024-02-05","cited_by_count":100,"area":"mllm"},{"id":"2307.10350","title":"Improving Multimodal Datasets with Image Captioning","created":"2023-07-19","cited_by_count":93,"area":"mllm"},{"id":"2211.12737","title":"RoentGen: Vision-Language Foundation Model for Chest X-ray Generation","created":"2022-11-23","cited_by_count":89,"area":"mllm"},{"id":"2210.04133","title":"Adapting Pretrained Vision-Language Foundational Models to Medical Imaging Domains","created":"2022-10-09","cited_by_count":86,"area":"mllm"},{"id":"2305.01278","title":"VPGTrans: Transfer Visual Prompt Generator across LLMs","created":"2023-05-02","cited_by_count":80,"area":"mllm"},{"id":"2501.00289","title":"Dual Diffusion for Unified Image Generation and Understanding","created":"2024-12-31","cited_by_count":76,"area":"mllm"},{"id":"2402.03190","title":"Unified Hallucination Detection for Multimodal Large Language Models","created":"2024-02-05","cited_by_count":75,"area":"mllm"},{"id":"2310.17419","title":"AntifakePrompt: Prompt-Tuned Vision-Language Models are Fake Image Detectors","created":"2023-10-26","cited_by_count":64,"area":"mllm"},{"id":"2209.14927","title":"Spotlight: Mobile UI Understanding using Vision-Language Models with a Focus","created":"2022-09-29","cited_by_count":62,"area":"mllm"},{"id":"2312.16794","title":"ZONE: Zero-Shot Instruction-Guided Local Editing","created":"2023-12-28","cited_by_count":62,"area":"mllm"},{"id":"2303.14465","title":"Equivariant Similarity for Vision-Language Foundation Models","created":"2023-03-25","cited_by_count":52,"area":"mllm"},{"id":"2308.12038","title":"Large Multilingual Models Pivot Zero-Shot Multimodal Learning across Languages","created":"2023-08-23","cited_by_count":52,"area":"mllm"},{"id":"2402.12927","title":"CLIPping the Deception: Adapting Vision-Language Models for Universal Deepfake Detection","created":"2024-02-20","cited_by_count":47,"area":"mllm"},{"id":"2312.00081","title":"Synthesize, Diagnose, and Optimize: Towards Fine-Grained Vision-Language Understanding","created":"2023-11-30","cited_by_count":46,"area":"mllm"},{"id":"2411.19722","title":"JetFormer: An Autoregressive Generative Model of Raw Images and Text","created":"2024-11-29","cited_by_count":46,"area":"mllm"},{"id":"2502.06130","title":"Self-Correcting Decoding with Generative Feedback for Mitigating Hallucinations in Large Vision-Language Models","created":"2025-02-10","cited_by_count":44,"area":"mllm"},{"id":"2405.10255","title":"When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Models","created":"2024-05-16","cited_by_count":43,"area":"mllm"},{"id":"2406.11171","title":"SUGARCREPE++ Dataset: Vision-Language Model Sensitivity to Semantic and Lexical Alterations","created":"2024-06-17","cited_by_count":42,"area":"mllm"},{"id":"2304.03086","title":"ChatGPT for Shaping the Future of Dentistry: The Potential of Multi-Modal Large Language Model","created":"2023-03-23","cited_by_count":40,"area":"mllm"},{"id":"2404.05674","title":"MoMA: Multimodal LLM Adapter for Fast Personalized Image Generation","created":"2024-04-08","cited_by_count":35,"area":"mllm"},{"id":"2305.14897","title":"Text encoders bottleneck compositionality in contrastive vision-language models","created":"2023-05-24","cited_by_count":34,"area":"mllm"},{"id":"2407.05342","title":"Mind the Interference: Retaining Pre-trained Knowledge in Parameter Efficient Continual Learning of Vision-Language Models","created":"2024-07-07","cited_by_count":34,"area":"mllm"},{"id":"2401.10226","title":"Towards Language-Driven Video Inpainting via Multimodal Large Language Models","created":"2024-01-18","cited_by_count":33,"area":"mllm"},{"id":"2411.02537","title":"INQUIRE: A Natural World Text-to-Image Retrieval Benchmark","created":"2024-11-04","cited_by_count":33,"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":"2504.14666","title":"Generative Multimodal Pretraining with Discrete Diffusion Timestep Tokens","created":"2025-04-20","cited_by_count":28,"area":"mllm"},{"id":"2305.15407","title":"Balancing the Picture: Debiasing Vision-Language Datasets with Synthetic Contrast Sets","created":"2023-05-24","cited_by_count":27,"area":"mllm"},{"id":"2507.19024","title":"A Survey of Multimodal Hallucination Evaluation and Detection","created":"2025-07-25","cited_by_count":27,"area":"mllm"},{"id":"2311.16500","title":"LLMGA: Multimodal Large Language Model based Generation Assistant","created":"2023-11-27","cited_by_count":25,"area":"mllm"},{"id":"2304.04512","title":"Defense-Prefix for Preventing Typographic Attacks on CLIP","created":"2023-04-10","cited_by_count":24,"area":"mllm"},{"id":"2310.06311","title":"Improving Compositional Text-to-image Generation with Large Vision-Language Models","created":"2023-10-10","cited_by_count":24,"area":"mllm"},{"id":"2212.12043","title":"When are Lemons Purple? The Concept Association Bias of Vision-Language Models","created":"2022-12-22","cited_by_count":23,"area":"mllm"},{"id":"2409.17958","title":"The Hard Positive Truth about Vision-Language Compositionality","created":"2024-09-26","cited_by_count":22,"area":"mllm"},{"id":"2505.05528","title":"X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP","created":"2025-05-08","cited_by_count":21,"area":"mllm"},{"id":"2406.16562","title":"EVALALIGN: Supervised Fine-Tuning Multimodal LLMs with Human-Aligned Data for Evaluating Text-to-Image Models","created":"2024-06-24","cited_by_count":20,"area":"mllm"},{"id":"2504.20998","title":"YoChameleon: Personalized Vision and Language Generation","created":"2025-04-29","cited_by_count":20,"area":"mllm"},{"id":"2407.06842","title":"Chat-Edit-3D: Interactive 3D Scene Editing via Text Prompts","created":"2024-07-09","cited_by_count":19,"area":"mllm"},{"id":"2409.19967","title":"Magnet: We Never Know How Text-to-Image Diffusion Models Work, Until We Learn How Vision-Language Models Function","created":"2024-09-30","cited_by_count":19,"area":"mllm"},{"id":"2503.10127","title":"PlanGen: Towards Unified Layout Planning and Image Generation in Auto-Regressive Vision Language Models","created":"2025-03-13","cited_by_count":18,"area":"mllm"},{"id":"2505.14361","title":"Vision-Language Modeling Meets Remote Sensing: Models, Datasets and Perspectives","created":"2025-05-20","cited_by_count":18,"area":"mllm"},{"id":"2206.07699","title":"Write and Paint: Generative Vision-Language Models are Unified Modal Learners","created":"2022-06-15","cited_by_count":17,"area":"mllm"},{"id":"2408.11305","title":"UniFashion: A Unified Vision-Language Model for Multimodal Fashion Retrieval and Generation","created":"2024-08-21","cited_by_count":17,"area":"mllm"},{"id":"2411.04420","title":"BendVLM: Test-Time Debiasing of Vision-Language Embeddings","created":"2024-11-07","cited_by_count":17,"area":"mllm"},{"id":"2306.10169","title":"Meta-Personalizing Vision-Language Models to Find Named Instances in Video","created":"2023-06-16","cited_by_count":16,"area":"mllm"},{"id":"2310.07027","title":"Utilizing Synthetic Data for Medical Vision-Language Pre-training: Bypassing the Need for Real Images","created":"2023-10-10","cited_by_count":16,"area":"mllm"},{"id":"2310.02239","title":"MiniGPT-5: Interleaved Vision-and-Language Generation via Generative Vokens","created":"2023-10-03","cited_by_count":15,"area":"mllm"},{"id":"2402.18068","title":"SynArtifact: Classifying and Alleviating Artifacts in Synthetic Images via Vision-Language Model","created":"2024-02-28","cited_by_count":15,"area":"mllm"},{"id":"2404.15100","title":"Multimodal Large Language Model is a Human-Aligned Annotator for Text-to-Image Generation","created":"2024-04-23","cited_by_count":15,"area":"mllm"},{"id":"2412.05818","title":"SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation","created":"2024-12-08","cited_by_count":15,"area":"mllm"},{"id":"2509.16197","title":"MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer","created":"2025-09-19","cited_by_count":15,"area":"mllm"},{"id":"2502.08642","title":"SwiftSketch: A Diffusion Model for Image-to-Vector Sketch Generation","created":"2025-02-12","cited_by_count":14,"area":"mllm"},{"id":"2210.04506","title":"Bridging CLIP and StyleGAN through Latent Alignment for Image Editing","created":"2022-10-10","cited_by_count":12,"area":"mllm"},{"id":"2406.05814","title":"TIGeR: Unifying Text-to-Image Generation and Retrieval with Large Multimodal Models","created":"2024-06-09","cited_by_count":12,"area":"mllm"},{"id":"2406.19593","title":"SK-VQA: Synthetic Knowledge Generation at Scale for Training Context-Augmented Multimodal LLMs","created":"2024-06-28","cited_by_count":12,"area":"mllm"},{"id":"2408.05019","title":"Instruction Tuning-free Visual Token Complement for Multimodal LLMs","created":"2024-08-09","cited_by_count":12,"area":"mllm"},{"id":"2412.06774","title":"Visual Lexicon: Rich Image Features in Language Space","created":"2024-12-09","cited_by_count":12,"area":"mllm"},{"id":"2412.12087","title":"Instruction-based Image Manipulation by Watching How Things Move","created":"2024-12-16","cited_by_count":12,"area":"mllm"},{"id":"2502.14113","title":"Object-centric Binding in Contrastive Language-Image Pretraining","created":"2025-02-19","cited_by_count":12,"area":"mllm"},{"id":"2305.16999","title":"Three Towers: Flexible Contrastive Learning with Pretrained Image Models","created":"2023-05-26","cited_by_count":11,"area":"mllm"},{"id":"2401.14688","title":"Taiyi-Diffusion-XL: Advancing Bilingual Text-to-Image Generation with Large Vision-Language Model Support","created":"2024-01-26","cited_by_count":11,"area":"mllm"},{"id":"2402.13636","title":"A Unified Framework and Dataset for Assessing Societal Bias in Vision-Language Models","created":"2024-02-21","cited_by_count":11,"area":"mllm"},{"id":"2503.06134","title":"X2I: Seamless Integration of Multimodal Understanding into Diffusion Transformer via Attention Distillation","created":"2025-03-08","cited_by_count":11,"area":"mllm"},{"id":"2504.05445","title":"Probing the Visualization Literacy of Vision Language Models: the Good, the Bad, and the Ugly","created":"2025-04-07","cited_by_count":11,"area":"mllm"},{"id":"2303.01615","title":"ConTEXTual Net: A Multimodal Vision-Language Model for Segmentation of Pneumothorax","created":"2023-03-02","cited_by_count":10,"area":"mllm"},{"id":"2308.03151","title":"Food-500 Cap: A Fine-Grained Food Caption Benchmark for Evaluating Vision-Language Models","created":"2023-08-06","cited_by_count":10,"area":"mllm"},{"id":"2408.14435","title":"Social Perception of Faces in a Vision-Language Model","created":"2024-08-26","cited_by_count":10,"area":"mllm"},{"id":"2505.16763","title":"Self-Rewarding Large Vision-Language Models for Optimizing Prompts in Text-to-Image Generation","created":"2025-05-22","cited_by_count":10,"area":"mllm"},{"id":"2507.21391","title":"Multimodal LLMs as Customized Reward Models for Text-to-Image Generation","created":"2025-07-28","cited_by_count":10,"area":"mllm"},{"id":"2306.08226","title":"CLIPXPlore: Coupled CLIP and Shape Spaces for 3D Shape Exploration","created":"2023-06-14","cited_by_count":9,"area":"mllm"},{"id":"2404.12139","title":"Omniview-Tuning: Boosting Viewpoint Invariance of Vision-Language Pre-training Models","created":"2024-04-18","cited_by_count":9,"area":"mllm"},{"id":"2404.13784","title":"Iteratively Prompting Multimodal LLMs to Reproduce Natural and AI-Generated Images","created":"2024-04-21","cited_by_count":9,"area":"mllm"},{"id":"2410.07133","title":"EvolveDirector: Approaching Advanced Text-to-Image Generation with Large Vision-Language Models","created":"2024-10-09","cited_by_count":9,"area":"mllm"},{"id":"2307.11315","title":"GIST: Generating Image-Specific Text for Fine-grained Object Classification","created":"2023-07-21","cited_by_count":8,"area":"mllm"},{"id":"2406.06730","title":"TRINS: Towards Multimodal Language Models that Can Read","created":"2024-06-10","cited_by_count":8,"area":"mllm"},{"id":"2409.14993","title":"Multi-modal Generative AI: Multi-modal LLMs, Diffusions, and the Unification","created":"2024-09-23","cited_by_count":8,"area":"mllm"},{"id":"2504.14245","title":"Towards Explainable Fake Image Detection with Multi-Modal Large Language Models","created":"2025-04-19","cited_by_count":8,"area":"mllm"}],"next_cursor":"100"}