{"total":150,"rows":[{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281,"area":"mllm"},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433,"area":"mllm"},{"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":"2306.11029","title":"RemoteCLIP: A Vision Language Foundation Model for Remote Sensing","created":"2023-06-19","cited_by_count":363,"area":"mllm"},{"id":"2205.03340","title":"Prompt Distribution Learning","created":"2022-05-06","cited_by_count":235,"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":"2211.12737","title":"RoentGen: Vision-Language Foundation Model for Chest X-ray Generation","created":"2022-11-23","cited_by_count":89,"area":"mllm"},{"id":"2308.07898","title":"A Foundation Language-Image Model of the Retina (FLAIR): Encoding Expert Knowledge in Text Supervision","created":"2023-08-15","cited_by_count":78,"area":"mllm"},{"id":"2203.06386","title":"Enabling Multimodal Generation on CLIP via Vision-Language Knowledge Distillation","created":"2022-03-12","cited_by_count":70,"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":"2305.19894","title":"Med-UniC: Unifying Cross-Lingual Medical Vision-Language Pre-Training by Diminishing Bias","created":"2023-05-31","cited_by_count":57,"area":"mllm"},{"id":"2208.08340","title":"Dual Modality Prompt Tuning for Vision-Language Pre-Trained Model","created":"2022-08-17","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":"2306.04811","title":"Generative Text-Guided 3D Vision-Language Pretraining for Unified Medical Image Segmentation","created":"2023-06-07","cited_by_count":47,"area":"mllm"},{"id":"2503.20047","title":"Med3DVLM: An Efficient Vision-Language Model for 3D Medical Image Analysis","created":"2025-03-25","cited_by_count":46,"area":"mllm"},{"id":"2307.08347","title":"M-FLAG: Medical Vision-Language Pre-training with Frozen Language Models and Latent Space Geometry Optimization","created":"2023-07-17","cited_by_count":43,"area":"mllm"},{"id":"2405.12255","title":"Mammo-CLIP: A Vision Language Foundation Model to Enhance Data Efficiency and Robustness in Mammography","created":"2024-05-20","cited_by_count":38,"area":"mllm"},{"id":"2309.03406","title":"Distribution-Aware Prompt Tuning for Vision-Language Models","created":"2023-09-06","cited_by_count":35,"area":"mllm"},{"id":"2309.05904","title":"Enhancing Representation in Radiography-Reports Foundation Model: A Granular Alignment Algorithm Using Masked Contrastive Learning","created":"2023-09-12","cited_by_count":34,"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":"2405.14137","title":"RET-CLIP: A Retinal Image Foundation Model Pre-trained with Clinical Diagnostic Reports","created":"2024-05-23","cited_by_count":30,"area":"mllm"},{"id":"2308.07706","title":"Exploring Transfer Learning in Medical Image Segmentation using Vision-Language Models","created":"2023-08-15","cited_by_count":28,"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":"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":"2411.00997","title":"Identifying Implicit Social Biases in Vision-Language Models","created":"2024-11-01","cited_by_count":27,"area":"mllm"},{"id":"2312.06224","title":"Medical Vision Language Pretraining: A survey","created":"2023-12-11","cited_by_count":24,"area":"mllm"},{"id":"2409.03868","title":"Few-shot Adaptation of Medical Vision-Language Models","created":"2024-09-05","cited_by_count":24,"area":"mllm"},{"id":"2310.07355","title":"IMITATE: Clinical Prior Guided Hierarchical Vision-Language Pre-training","created":"2023-10-11","cited_by_count":23,"area":"mllm"},{"id":"2305.07920","title":"Multi-task Paired Masking with Alignment Modeling for Medical Vision-Language Pre-training","created":"2023-05-13","cited_by_count":22,"area":"mllm"},{"id":"2510.15042","title":"Comprehensive language-image pre-training for 3D medical image understanding","created":"2025-10-16","cited_by_count":22,"area":"mllm"},{"id":"2312.11038","title":"UniChest: Conquer-and-Divide Pre-training for Multi-Source Chest X-Ray Classification","created":"2023-12-18","cited_by_count":21,"area":"mllm"},{"id":"2403.09294","title":"Anatomical Structure-Guided Medical Vision-Language Pre-training","created":"2024-03-14","cited_by_count":18,"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":"2303.17644","title":"Vision-Language Modelling For Radiological Imaging and Reports In The Low Data Regime","created":"2023-03-30","cited_by_count":15,"area":"mllm"},{"id":"2302.11084","title":"Test-Time Distribution Normalization for Contrastively Learned Vision-language Models","created":"2023-02-22","cited_by_count":14,"area":"mllm"},{"id":"2312.01529","title":"T3D: Advancing 3D Medical Vision-Language Pre-training by Learning Multi-View Visual Consistency","created":"2023-12-03","cited_by_count":14,"area":"mllm"},{"id":"2404.16804","title":"AAPL: Adding Attributes to Prompt Learning for Vision-Language Models","created":"2024-04-25","cited_by_count":14,"area":"mllm"},{"id":"2505.00744","title":"Localizing Before Answering: A Hallucination Evaluation Benchmark for Grounded Medical Multimodal LLMs","created":"2025-04-30","cited_by_count":14,"area":"mllm"},{"id":"2307.07246","title":"Knowledge Boosting: Rethinking Medical Contrastive Vision-Language Pre-Training","created":"2023-07-14","cited_by_count":13,"area":"mllm"},{"id":"2405.19654","title":"Unlocking the Power of Spatial and Temporal Information in Medical Multimodal Pre-training","created":"2024-05-30","cited_by_count":13,"area":"mllm"},{"id":"2312.01522","title":"G2D: From Global to Dense Radiography Representation Learning via Vision-Language Pre-training","created":"2023-12-03","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":"2503.01863","title":"Vision Language Models in Medicine","created":"2025-02-24","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":"2412.00142","title":"Enhancing Few-Shot Vision-Language Classification with Large Multimodal Model Features","created":"2024-11-28","cited_by_count":11,"area":"mllm"},{"id":"2503.01019","title":"MedUnifier: Unifying Vision-and-Language Pre-training on Medical Data with Vision Generation Task using Discrete Visual Representations","created":"2025-03-02","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":"2402.03783","title":"Exploring Low-Resource Medical Image Classification with Weakly Supervised Prompt Learning","created":"2024-02-06","cited_by_count":10,"area":"mllm"},{"id":"2404.03618","title":"DeViDe: Faceted medical knowledge for improved medical vision-language pre-training","created":"2024-04-04","cited_by_count":10,"area":"mllm"},{"id":"2308.11194","title":"ViLLA: Fine-Grained Vision-Language Representation Learning from Real-World Data","created":"2023-08-22","cited_by_count":9,"area":"mllm"},{"id":"2410.23822","title":"Parameter-Efficient Fine-Tuning Medical Multimodal Large Language Models for Medical Visual Grounding","created":"2024-10-31","cited_by_count":9,"area":"mllm"},{"id":"2506.06076","title":"Full Conformal Adaptation of Medical Vision-Language Models","created":"2025-06-06","cited_by_count":9,"area":"mllm"},{"id":"2403.09948","title":"RadCLIP: Enhancing Radiologic Image Analysis through Contrastive Language-Image Pre-training","created":"2024-03-15","cited_by_count":8,"area":"mllm"},{"id":"2409.01883","title":"Boosting Vision-Language Models for Histopathology Classification: Predict all at once","created":"2024-09-03","cited_by_count":8,"area":"mllm"},{"id":"2501.10775","title":"MedFILIP: Medical Fine-grained Language-Image Pre-training","created":"2025-01-18","cited_by_count":8,"area":"mllm"},{"id":"2506.17503","title":"Trustworthy Few-Shot Transfer of Medical VLMs through Split Conformal Prediction","created":"2025-06-20","cited_by_count":8,"area":"mllm"},{"id":"2311.02236","title":"Robust Fine-Tuning of Vision-Language Models for Domain Generalization","created":"2023-11-03","cited_by_count":7,"area":"mllm"},{"id":"2401.02044","title":"A multi-modal vision-language model for generalizable annotation-free pathology localization","created":"2024-01-04","cited_by_count":7,"area":"mllm"},{"id":"2408.10894","title":"ViLReF: An Expert Knowledge Enabled Vision-Language Retinal Foundation Model","created":"2024-08-20","cited_by_count":7,"area":"mllm"},{"id":"2410.13523","title":"Can Medical Vision-Language Pre-training Succeed with Purely Synthetic Data?","created":"2024-10-17","cited_by_count":7,"area":"mllm"},{"id":"2411.15673","title":"Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment","created":"2024-11-23","cited_by_count":7,"area":"mllm"},{"id":"2506.17500","title":"Few-Shot, Now for Real: Medical VLMs Adaptation without Balanced Sets or Validation","created":"2025-06-20","cited_by_count":7,"area":"mllm"},{"id":"2506.18504","title":"Generalizing vision-language models to novel domains: A comprehensive survey","created":"2025-06-23","cited_by_count":7,"area":"mllm"},{"id":"2401.01179","title":"Freeze the backbones: A Parameter-Efficient Contrastive Approach to Robust Medical Vision-Language Pre-training","created":"2024-01-02","cited_by_count":6,"area":"mllm"},{"id":"2403.19811","title":"X-MIC: Cross-Modal Instance Conditioning for Egocentric Action Generalization","created":"2024-03-28","cited_by_count":6,"area":"mllm"},{"id":"2407.18941","title":"LEMoN: Label Error Detection using Multimodal Neighbors","created":"2024-07-10","cited_by_count":6,"area":"mllm"},{"id":"2407.21368","title":"Prompting Medical Large Vision-Language Models to Diagnose Pathologies by Visual Question Answering","created":"2024-07-31","cited_by_count":6,"area":"mllm"},{"id":"2409.07480","title":"EEG-Language Pretraining for Highly Label-Efficient Clinical Phenotyping","created":"2024-09-02","cited_by_count":6,"area":"mllm"},{"id":"2410.21969","title":"BenchX: A Unified Benchmark Framework for Medical Vision-Language Pretraining on Chest X-Rays","created":"2024-10-29","cited_by_count":6,"area":"mllm"},{"id":"2503.07487","title":"LLaVA-RadZ: Can Multimodal Large Language Models Effectively Tackle Zero-shot Radiology Recognition?","created":"2025-03-10","cited_by_count":6,"area":"mllm"},{"id":"2306.06494","title":"Multi-modal Pre-training for Medical Vision-language Understanding and Generation: An Empirical Study with A New Benchmark","created":"2023-06-10","cited_by_count":5,"area":"mllm"},{"id":"2311.14851","title":"Unified Medical Image Pre-training in Language-Guided Common Semantic Space","created":"2023-11-24","cited_by_count":5,"area":"mllm"},{"id":"2401.11421","title":"Enhancing the vision-language foundation model with key semantic knowledge-emphasized report refinement","created":"2024-01-21","cited_by_count":5,"area":"mllm"},{"id":"2412.07119","title":"DiffCLIP: Few-shot Language-driven Multimodal Classifier","created":"2024-12-10","cited_by_count":4,"area":"mllm"},{"id":"2602.21428","title":"PSF-Med: Measuring and Explaining Paraphrase Sensitivity in Medical Vision Language Models","created":"2026-02-24","cited_by_count":4,"area":"mllm"},{"id":"2212.04267","title":"Vision and Structured-Language Pretraining for Cross-Modal Food Retrieval","created":"2022-12-08","cited_by_count":3,"area":"mllm"},{"id":"2312.11171","title":"UniDCP: Unifying Multiple Medical Vision-language Tasks via Dynamic Cross-modal Learnable Prompts","created":"2023-12-18","cited_by_count":3,"area":"mllm"},{"id":"2401.01583","title":"Enhancing Representation in Medical Vision-Language Foundation Models via Multi-Scale Information Extraction Techniques","created":"2024-01-03","cited_by_count":3,"area":"mllm"},{"id":"2410.05239","title":"TuneVLSeg: Prompt Tuning Benchmark for Vision-Language Segmentation Models","created":"2024-10-07","cited_by_count":3,"area":"mllm"},{"id":"2505.17982","title":"Few-Shot Learning from Gigapixel Images via Hierarchical Vision-Language Alignment and Modeling","created":"2025-05-23","cited_by_count":3,"area":"mllm"},{"id":"2602.19058","title":"Do LLMs and VLMs Share Neurons for Inference? Evidence and Mechanisms of Cross-Modal Transfer","created":"2026-02-22","cited_by_count":3,"area":"mllm"},{"id":"2403.18996","title":"Envisioning MedCLIP: A Deep Dive into Explainability for Medical Vision-Language Models","created":"2024-03-27","cited_by_count":2,"area":"mllm"},{"id":"2404.14750","title":"Grounded Knowledge-Enhanced Medical Vision-Language Pre-training for Chest X-Ray","created":"2024-04-23","cited_by_count":2,"area":"mllm"},{"id":"2409.00543","title":"How Does Diverse Interpretability of Textual Prompts Impact Medical Vision-Language Zero-Shot Tasks?","created":"2024-08-31","cited_by_count":2,"area":"mllm"},{"id":"2410.17827","title":"RE-tune: Incremental Fine Tuning of Biomedical Vision-Language Models for Multi-label Chest X-ray Classification","created":"2024-10-23","cited_by_count":2,"area":"mllm"},{"id":"2503.08229","title":"Modeling Variants of Prompts for Vision-Language Models","created":"2025-03-11","cited_by_count":2,"area":"mllm"},{"id":"2504.05227","title":"A Reality Check of Vision-Language Pre-training in Radiology: Have We Progressed Using Text?","created":"2025-04-07","cited_by_count":2,"area":"mllm"},{"id":"2507.12236","title":"Generate to Ground: Multimodal Text Conditioning Boosts Phrase Grounding in Medical Vision-Language Models","created":"2025-07-16","cited_by_count":2,"area":"mllm"},{"id":"2507.15480","title":"One Last Attention for Your Vision-Language Model","created":"2025-07-21","cited_by_count":2,"area":"mllm"},{"id":"2602.17535","title":"LATA: Laplacian-Assisted Transductive Adaptation for Conformal Uncertainty in Medical VLMs","created":"2026-02-19","cited_by_count":2,"area":"mllm"},{"id":"2603.06467","title":"GreenRFM: Learning a resource-efficient radiology vision-language foundation model via supervision-centric pre-training","created":"2026-03-06","cited_by_count":2,"area":"mllm"},{"id":"2208.05140","title":"Self-supervised Multi-modal Training from Uncurated Image and Reports Enables Zero-shot Oversight Artificial Intelligence in Radiology","created":"2022-08-10","cited_by_count":1,"area":"mllm"},{"id":"2401.06331","title":"Application Of Vision-Language Models For Assessing Osteoarthritis Disease Severity","created":"2024-01-12","cited_by_count":1,"area":"mllm"},{"id":"2404.03854","title":"Distributionally Robust Alignment for Medical Federated Vision-Language Pre-training Under Data Heterogeneity","created":"2024-04-05","cited_by_count":1,"area":"mllm"},{"id":"2405.06468","title":"Pseudo-Prompt Generating in Pre-trained Vision-Language Models for Multi-Label Medical Image Classification","created":"2024-05-10","cited_by_count":1,"area":"mllm"},{"id":"2405.19675","title":"Knowledge-grounded Adaptation Strategy for Vision-language Models: Building Unique Case-set for Screening Mammograms for Residents Training","created":"2024-05-30","cited_by_count":1,"area":"mllm"},{"id":"2407.15731","title":"The Inter-Intra Modal Measure: A Predictive Lens on Fine-Tuning Outcomes in Vision-Language Models","created":"2024-07-22","cited_by_count":1,"area":"mllm"},{"id":"2409.02418","title":"MOSMOS: Multi-organ segmentation facilitated by medical report supervision","created":"2024-09-04","cited_by_count":1,"area":"mllm"},{"id":"2410.00448","title":"Advancing Medical Radiograph Representation Learning: A Hybrid Pre-training Paradigm with Multilevel Semantic Granularity","created":"2024-10-01","cited_by_count":1,"area":"mllm"},{"id":"2412.16148","title":"Frequency Is What You Need: Considering Word Frequency When Text Masking Benefits Vision-Language Model Pre-training","created":"2024-12-20","cited_by_count":1,"area":"mllm"}],"next_cursor":"100"}