{"total":16,"rows":[{"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":"2502.07855","title":"Vision-Language Models for Edge Networks: A Comprehensive Survey","created":"2025-02-11","cited_by_count":29,"area":"mllm"},{"id":"2305.07528","title":"WEDGE: A multi-weather autonomous driving dataset built from generative vision-language models","created":"2023-05-12","cited_by_count":28,"area":"mllm"},{"id":"2504.03254","title":"SARLANG-1M: A Benchmark for Vision-Language Modeling in SAR Image Understanding","created":"2025-04-04","cited_by_count":16,"area":"mllm"},{"id":"2504.13861","title":"3MDBench: Medical Multimodal Multi-agent Dialogue Benchmark","created":"2025-03-26","cited_by_count":16,"area":"mllm"},{"id":"2410.01534","title":"Toward a Holistic Evaluation of Robustness in CLIP Models","created":"2024-10-02","cited_by_count":13,"area":"mllm"},{"id":"2602.13662","title":"LeafNet: A Large-Scale Dataset and Comprehensive Benchmark for Foundational Vision-Language Understanding of Plant Diseases","created":"2026-02-14","cited_by_count":5,"area":"mllm"},{"id":"2509.09311","title":"Image Recognition with Vision and Language Embeddings of VLMs","created":"2025-09-11","cited_by_count":2,"area":"mllm"},{"id":"2603.06578","title":"Multimodal Large Language Models as Image Classifiers","created":"2026-03-06","cited_by_count":2,"area":"mllm"},{"id":"2508.13068","title":"Eyes on the Image: Gaze Supervised Multimodal Learning for Chest X-ray Diagnosis and Report Generation","created":"2025-08-18","cited_by_count":1,"area":"mllm"},{"id":"2601.13238","title":"A Semantic Decoupling-Based Two-Stage Rainy-Day Attack for Revealing Weather Robustness Deficiencies in Vision-Language Models","created":"2026-01-19","cited_by_count":1,"area":"mllm"},{"id":"2310.16148","title":"Yin Yang Convolutional Nets: Image Manifold Extraction by the Analysis of Opposites","created":"2023-10-24","cited_by_count":0,"area":"mllm"},{"id":"2512.21529","title":"Hierarchy-Aware Fine-Tuning of Vision-Language Models","created":"2025-12-25","cited_by_count":0,"area":"mllm"},{"id":"2602.18614","title":"Effect of Patch Size on Fine-Tuning Vision Transformers in Two-Dimensional and Three-Dimensional Medical Image Classification","created":"2026-02-20","cited_by_count":0,"area":"mllm"},{"id":"2604.21102","title":"Leveraging Multimodal LLMs for Built Environment and Housing Attribute Assessment from Street-View Imagery","created":"2026-04-22","cited_by_count":0,"area":"mllm"},{"id":"2607.18819","title":"In-Context Learning for Wound Classification with Small Multimodal Language Models","created":"2026-07-21","cited_by_count":0,"area":"mllm"}],"next_cursor":null}