{"total":354,"rows":[{"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,"area":"mllm"},{"id":"2308.12966","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","created":"2023-08-24","cited_by_count":2224,"area":"mllm"},{"id":"2304.00685","title":"Vision-Language Models for Vision Tasks: A Survey","created":"2023-04-03","cited_by_count":839,"area":"mllm"},{"id":"2311.03356","title":"GLaMM: Pixel Grounding Large Multimodal Model","created":"2023-11-06","cited_by_count":455,"area":"mllm"},{"id":"2404.18930","title":"Hallucination of Multimodal Large Language Models: A Survey","created":"2024-04-29","cited_by_count":388,"area":"mllm"},{"id":"2306.11029","title":"RemoteCLIP: A Vision Language Foundation Model for Remote Sensing","created":"2023-06-19","cited_by_count":363,"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":"2302.12242","title":"Side Adapter Network for Open-Vocabulary Semantic Segmentation","created":"2023-02-23","cited_by_count":300,"area":"mllm"},{"id":"2309.11499","title":"DreamLLM: Synergistic Multimodal Comprehension and Creation","created":"2023-09-20","cited_by_count":297,"area":"mllm"},{"id":"2302.14115","title":"Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning","created":"2023-02-27","cited_by_count":263,"area":"mllm"},{"id":"2305.17216","title":"Generating Images with Multimodal Language Models","created":"2023-05-26","cited_by_count":260,"area":"mllm"},{"id":"2410.05160","title":"VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks","created":"2024-10-07","cited_by_count":228,"area":"mllm"},{"id":"2312.06742","title":"Honeybee: Locality-enhanced Projector for Multimodal LLM","created":"2023-12-11","cited_by_count":197,"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":"2306.11300","title":"RS5M and GeoRSCLIP: A Large Scale Vision-Language Dataset and A Large Vision-Language Model for Remote Sensing","created":"2023-06-20","cited_by_count":151,"area":"mllm"},{"id":"2312.14115","title":"LingoQA: Visual Question Answering for Autonomous Driving","created":"2023-12-21","cited_by_count":145,"area":"mllm"},{"id":"2310.09199","title":"PaLI-3 Vision Language Models: Smaller, Faster, Stronger","created":"2023-10-13","cited_by_count":126,"area":"mllm"},{"id":"2212.05221","title":"REVEAL: Retrieval-Augmented Visual-Language Pre-Training with Multi-Source Multimodal Knowledge Memory","created":"2022-12-10","cited_by_count":123,"area":"mllm"},{"id":"2211.16198","title":"SuS-X: Training-Free Name-Only Transfer of Vision-Language Models","created":"2022-11-28","cited_by_count":119,"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":"2407.12442","title":"ClearCLIP: Decomposing CLIP Representations for Dense Vision-Language Inference","created":"2024-07-17","cited_by_count":113,"area":"mllm"},{"id":"2206.07643","title":"Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone","created":"2022-06-15","cited_by_count":109,"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":"2307.10350","title":"Improving Multimodal Datasets with Image Captioning","created":"2023-07-19","cited_by_count":93,"area":"mllm"},{"id":"2301.02280","title":"Filtering, Distillation, and Hard Negatives for Vision-Language Pre-Training","created":"2023-01-05","cited_by_count":91,"area":"mllm"},{"id":"2312.00878","title":"Grounding Everything: Emerging Localization Properties in Vision-Language Transformers","created":"2023-12-01","cited_by_count":91,"area":"mllm"},{"id":"2306.07915","title":"Image Captioners Are Scalable Vision Learners Too","created":"2023-06-13","cited_by_count":89,"area":"mllm"},{"id":"2303.07226","title":"Scaling Vision-Language Models with Sparse Mixture of Experts","created":"2023-03-13","cited_by_count":88,"area":"mllm"},{"id":"2303.05657","title":"Tag2Text: Guiding Vision-Language Model via Image Tagging","created":"2023-03-10","cited_by_count":86,"area":"mllm"},{"id":"2210.09996","title":"Perceptual Grouping in Contrastive Vision-Language Models","created":"2022-10-18","cited_by_count":82,"area":"mllm"},{"id":"2305.19270","title":"Learning without Forgetting for Vision-Language Models","created":"2023-05-30","cited_by_count":79,"area":"mllm"},{"id":"2308.03685","title":"Learning Concise and Descriptive Attributes for Visual Recognition","created":"2023-08-07","cited_by_count":73,"area":"mllm"},{"id":"2207.01297","title":"Revisiting Classifier: Transferring Vision-Language Models for Video Recognition","created":"2022-07-04","cited_by_count":71,"area":"mllm"},{"id":"2310.07699","title":"VeCLIP: Improving CLIP Training via Visual-enriched Captions","created":"2023-10-11","cited_by_count":70,"area":"mllm"},{"id":"2404.07204","title":"BRAVE: Broadening the visual encoding of vision-language models","created":"2024-04-10","cited_by_count":69,"area":"mllm"},{"id":"2209.15517","title":"Medical Image Understanding with Pretrained Vision Language Models: A Comprehensive Study","created":"2022-09-30","cited_by_count":66,"area":"mllm"},{"id":"2310.13355","title":"SILC: Improving Vision Language Pretraining with Self-Distillation","created":"2023-10-20","cited_by_count":66,"area":"mllm"},{"id":"2303.14302","title":"VILA: Learning Image Aesthetics from User Comments with Vision-Language Pretraining","created":"2023-03-24","cited_by_count":65,"area":"mllm"},{"id":"2312.11420","title":"Tuning LayerNorm in Attention: Towards Efficient Multi-Modal LLM Finetuning","created":"2023-12-18","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":"2403.14599","title":"MyVLM: Personalizing VLMs for User-Specific Queries","created":"2024-03-21","cited_by_count":58,"area":"mllm"},{"id":"2404.07983","title":"Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Models","created":"2024-04-11","cited_by_count":57,"area":"mllm"},{"id":"2303.17561","title":"SoftCLIP: Softer Cross-modal Alignment Makes CLIP Stronger","created":"2023-03-30","cited_by_count":56,"area":"mllm"},{"id":"2301.06309","title":"UATVR: Uncertainty-Adaptive Text-Video Retrieval","created":"2023-01-16","cited_by_count":55,"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":"2211.11720","title":"Multitask Vision-Language Prompt Tuning","created":"2022-11-21","cited_by_count":51,"area":"mllm"},{"id":"2305.10799","title":"MedBLIP: Bootstrapping Language-Image Pre-training from 3D Medical Images and Texts","created":"2023-05-18","cited_by_count":51,"area":"mllm"},{"id":"2306.01879","title":"Revisiting the Role of Language Priors in Vision-Language Models","created":"2023-06-02","cited_by_count":50,"area":"mllm"},{"id":"2301.00182","title":"Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language Models","created":"2022-12-31","cited_by_count":49,"area":"mllm"},{"id":"2307.09018","title":"Multimodal LLMs for health grounded in individual-specific data","created":"2023-07-18","cited_by_count":49,"area":"mllm"},{"id":"2406.04236","title":"Understanding Information Storage and Transfer in Multi-modal Large Language Models","created":"2024-06-06","cited_by_count":49,"area":"mllm"},{"id":"2412.03561","title":"FLAIR: VLM with Fine-grained Language-informed Image Representations","created":"2024-12-04","cited_by_count":48,"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":"2305.17455","title":"CrossGET: Cross-Guided Ensemble of Tokens for Accelerating Vision-Language Transformers","created":"2023-05-27","cited_by_count":44,"area":"mllm"},{"id":"2211.11152","title":"You Need Multiple Exiting: Dynamic Early Exiting for Accelerating Unified Vision Language Model","created":"2022-11-21","cited_by_count":43,"area":"mllm"},{"id":"2502.04263","title":"Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion","created":"2025-02-06","cited_by_count":43,"area":"mllm"},{"id":"2302.04858","title":"Re-ViLM: Retrieval-Augmented Visual Language Model for Zero and Few-Shot Image Captioning","created":"2023-02-09","cited_by_count":41,"area":"mllm"},{"id":"2306.08832","title":"Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional Understanding","created":"2023-06-15","cited_by_count":41,"area":"mllm"},{"id":"2307.06930","title":"mBLIP: Efficient Bootstrapping of Multilingual Vision-LLMs","created":"2023-07-13","cited_by_count":41,"area":"mllm"},{"id":"2402.04630","title":"LLMs Meet VLMs: Boost Open Vocabulary Object Detection with Fine-grained Descriptors","created":"2024-02-07","cited_by_count":40,"area":"mllm"},{"id":"2206.01127","title":"VL-BEiT: Generative Vision-Language Pretraining","created":"2022-06-02","cited_by_count":39,"area":"mllm"},{"id":"2304.01752","title":"Black Box Few-Shot Adaptation for Vision-Language models","created":"2023-04-04","cited_by_count":39,"area":"mllm"},{"id":"2403.14774","title":"Few-Shot Adversarial Prompt Learning on Vision-Language Models","created":"2024-03-21","cited_by_count":39,"area":"mllm"},{"id":"2404.02132","title":"ViTamin: Designing Scalable Vision Models in the Vision-Language Era","created":"2024-04-02","cited_by_count":39,"area":"mllm"},{"id":"2303.02483","title":"FAME-ViL: Multi-Tasking Vision-Language Model for Heterogeneous Fashion Tasks","created":"2023-03-04","cited_by_count":38,"area":"mllm"},{"id":"2401.02418","title":"Learning to Prompt with Text Only Supervision for Vision-Language Models","created":"2024-01-04","cited_by_count":38,"area":"mllm"},{"id":"2406.01920","title":"CODE: Contrasting Self-generated Description to Combat Hallucination in Large Multi-modal Models","created":"2024-06-04","cited_by_count":38,"area":"mllm"},{"id":"2410.12790","title":"Dual Prototype Evolving for Test-Time Generalization of Vision-Language Models","created":"2024-10-16","cited_by_count":38,"area":"mllm"},{"id":"2305.06152","title":"Structure-CLIP: Towards Scene Graph Knowledge to Enhance Multi-modal Structured Representations","created":"2023-05-06","cited_by_count":37,"area":"mllm"},{"id":"2510.27280","title":"FOCUS: Efficient Keyframe Selection for Long Video Understanding","created":"2025-10-31","cited_by_count":37,"area":"mllm"},{"id":"2309.05950","title":"Language Models as Black-Box Optimizers for Vision-Language Models","created":"2023-09-12","cited_by_count":36,"area":"mllm"},{"id":"2304.01457","title":"Exploring Vision-Language Models for Imbalanced Learning","created":"2023-04-04","cited_by_count":35,"area":"mllm"},{"id":"2306.00917","title":"Vocabulary-free Image Classification","created":"2023-06-01","cited_by_count":35,"area":"mllm"},{"id":"2210.03794","title":"SVL-Adapter: Self-Supervised Adapter for Vision-Language Pretrained Models","created":"2022-10-07","cited_by_count":34,"area":"mllm"},{"id":"2410.16267","title":"xGen-MM-Vid (BLIP-3-Video): You Only Need 32 Tokens to Represent a Video Even in VLMs","created":"2024-10-21","cited_by_count":34,"area":"mllm"},{"id":"2411.15869","title":"Self-Calibrated CLIP for Training-Free Open-Vocabulary Segmentation","created":"2024-11-24","cited_by_count":34,"area":"mllm"},{"id":"2412.12077","title":"CPath-Omni: A Unified Multimodal Foundation Model for Patch and Whole Slide Image Analysis in Computational Pathology","created":"2024-12-16","cited_by_count":34,"area":"mllm"},{"id":"2501.07171","title":"BIOMEDICA: An Open Biomedical Image-Caption Archive, Dataset, and Vision-Language Models Derived from Scientific Literature","created":"2025-01-13","cited_by_count":34,"area":"mllm"},{"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":"2411.02537","title":"INQUIRE: A Natural World Text-to-Image Retrieval Benchmark","created":"2024-11-04","cited_by_count":33,"area":"mllm"},{"id":"2311.03774","title":"Meta-Adapter: An Online Few-shot Learner for Vision-Language Model","created":"2023-11-07","cited_by_count":31,"area":"mllm"},{"id":"2503.19900","title":"CAFe: Unifying Representation and Generation with Contrastive-Autoregressive Finetuning","created":"2025-03-25","cited_by_count":31,"area":"mllm"},{"id":"2305.14014","title":"CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model","created":"2023-05-23","cited_by_count":30,"area":"mllm"},{"id":"2305.14095","title":"S-CLIP: Semi-supervised Vision-Language Learning using Few Specialist Captions","created":"2023-05-23","cited_by_count":30,"area":"mllm"},{"id":"2310.00647","title":"Beyond Task Performance: Evaluating and Reducing the Flaws of Large Multimodal Models with In-Context Learning","created":"2023-10-01","cited_by_count":30,"area":"mllm"},{"id":"2406.19578","title":"PathAlign: A vision-language model for whole slide images in histopathology","created":"2024-06-27","cited_by_count":30,"area":"mllm"},{"id":"2504.10462","title":"The Scalability of Simplicity: Empirical Analysis of Vision-Language Learning with a Single Transformer","created":"2025-04-14","cited_by_count":30,"area":"mllm"},{"id":"2308.07146","title":"CTP: Towards Vision-Language Continual Pretraining via Compatible Momentum Contrast and Topology Preservation","created":"2023-08-14","cited_by_count":29,"area":"mllm"},{"id":"2411.15421","title":"OphCLIP: Hierarchical Retrieval-Augmented Learning for Ophthalmic Surgical Video-Language Pretraining","created":"2024-11-23","cited_by_count":29,"area":"mllm"},{"id":"2411.15851","title":"ResCLIP: Residual Attention for Training-free Dense Vision-language Inference","created":"2024-11-24","cited_by_count":29,"area":"mllm"},{"id":"2303.02506","title":"Prismer: A Vision-Language Model with Multi-Task Experts","created":"2023-03-04","cited_by_count":28,"area":"mllm"},{"id":"2304.02560","title":"VicTR: Video-conditioned Text Representations for Activity Recognition","created":"2023-04-05","cited_by_count":28,"area":"mllm"},{"id":"2503.14911","title":"Derm1M: A Million-scale Vision-Language Dataset Aligned with Clinical Ontology Knowledge for Dermatology","created":"2025-03-19","cited_by_count":28,"area":"mllm"},{"id":"2212.09737","title":"Position-guided Text Prompt for Vision-Language Pre-training","created":"2022-12-19","cited_by_count":27,"area":"mllm"},{"id":"2301.02241","title":"CiT: Curation in Training for Effective Vision-Language Data","created":"2023-01-05","cited_by_count":27,"area":"mllm"},{"id":"2310.19752","title":"Intra-Modal Proxy Learning for Zero-Shot Visual Categorization with CLIP","created":"2023-10-30","cited_by_count":27,"area":"mllm"},{"id":"2403.07636","title":"Decomposing Disease Descriptions for Enhanced Pathology Detection: A Multi-Aspect Vision-Language Pre-training Framework","created":"2024-03-12","cited_by_count":27,"area":"mllm"},{"id":"2305.20087","title":"Too Large; Data Reduction for Vision-Language Pre-Training","created":"2023-05-31","cited_by_count":26,"area":"mllm"}],"next_cursor":"100"}