{"total":16,"rows":[{"id":"2202.06767","title":"Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmark","created":"2022-02-14","cited_by_count":114,"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":"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":"2305.17718","title":"FuseCap: Leveraging Large Language Models for Enriched Fused Image Captions","created":"2023-05-28","cited_by_count":33,"area":"mllm"},{"id":"2502.07617","title":"Scaling Pre-training to One Hundred Billion Data for Vision Language Models","created":"2025-02-11","cited_by_count":19,"area":"mllm"},{"id":"2404.00860","title":"Lipsum-FT: Robust Fine-Tuning of Zero-Shot Models Using Random Text Guidance","created":"2024-04-01","cited_by_count":14,"area":"mllm"},{"id":"2312.04960","title":"MIMIR: Masked Image Modeling for Mutual Information-based Adversarial Robustness","created":"2023-12-08","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":"2307.00910","title":"CoPL: Contextual Prompt Learning for Vision-Language Understanding","created":"2023-07-03","cited_by_count":10,"area":"mllm"},{"id":"2311.17851","title":"Leveraging VLM-Based Pipelines to Annotate 3D Objects","created":"2023-11-29","cited_by_count":10,"area":"mllm"},{"id":"2402.15307","title":"Representing Online Handwriting for Recognition in Large Vision-Language Models","created":"2024-02-23","cited_by_count":7,"area":"mllm"},{"id":"2312.14149","title":"TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification","created":"2023-12-21","cited_by_count":5,"area":"mllm"},{"id":"2206.03354","title":"cViL: Cross-Lingual Training of Vision-Language Models using Knowledge Distillation","created":"2022-06-07","cited_by_count":1,"area":"mllm"},{"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":"2512.21414","title":"A Tool Bottleneck Framework for Clinically-Informed and Interpretable Medical Image Understanding","created":"2025-12-24","cited_by_count":0,"area":"mllm"},{"id":"2609.01757","title":"AlphaRAD: Grounded Zero-Shot Classification in Chest Radiology via $\\alpha$-Corrected Binary Cross Entropy and Factorized Latent Supervision","created":"2026-09-01","cited_by_count":0,"area":"mllm"}],"next_cursor":null}