{"total":16,"rows":[{"id":"2410.17250","title":"JMMMU: A Japanese Massive Multi-discipline Multimodal Understanding Benchmark for Culture-aware Evaluation","created":"2024-10-22","cited_by_count":19,"area":"mllm"},{"id":"2508.09945","title":"VisCodex: Unified Multimodal Code Generation via Merging Vision and Coding Models","created":"2025-08-13","cited_by_count":16,"area":"mllm"},{"id":"2404.07824","title":"Heron-Bench: A Benchmark for Evaluating Vision Language Models in Japanese","created":"2024-04-11","cited_by_count":12,"area":"mllm"},{"id":"2412.13702","title":"Typhoon 2: A Family of Open Text and Multimodal Thai Large Language Models","created":"2024-12-18","cited_by_count":12,"area":"mllm"},{"id":"2405.19076","title":"Cephalo: Multi-Modal Vision-Language Models for Bio-Inspired Materials Analysis and Design","created":"2024-05-29","cited_by_count":9,"area":"mllm"},{"id":"2407.19034","title":"MangaUB: A Manga Understanding Benchmark for Large Multimodal Models","created":"2024-07-26","cited_by_count":8,"area":"mllm"},{"id":"2410.07571","title":"How Does Vision-Language Adaptation Impact the Safety of Vision Language Models?","created":"2024-10-10","cited_by_count":8,"area":"mllm"},{"id":"2503.06312","title":"DOFA-CLIP: Multimodal Vision-Language Foundation Models for Earth Observation","created":"2025-03-08","cited_by_count":7,"area":"mllm"},{"id":"2410.22736","title":"Constructing Multimodal Datasets from Scratch for Rapid Development of a Japanese Visual Language Model","created":"2024-10-30","cited_by_count":6,"area":"mllm"},{"id":"2604.00909","title":"JAMMEval: A Refined Collection of Japanese Benchmarks for Reliable VLM Evaluation","created":"2026-04-01","cited_by_count":3,"area":"mllm"},{"id":"2406.01914","title":"HPE-CogVLM: Advancing Vision Language Models with a Head Pose Grounding Task","created":"2024-06-04","cited_by_count":1,"area":"mllm"},{"id":"2502.14778","title":"Harnessing PDF Data for Improving Japanese Large Multimodal Models","created":"2025-02-20","cited_by_count":1,"area":"mllm"},{"id":"2504.09620","title":"Metropolis-Hastings Captioning Game: Knowledge Fusion of Vision Language Models via Decentralized Bayesian Inference","created":"2025-04-13","cited_by_count":1,"area":"mllm"},{"id":"2407.08196","title":"SoupLM: Model Integration in Large Language and Multi-Modal Models","created":"2024-07-11","cited_by_count":0,"area":"mllm"},{"id":"2507.00700","title":"Contrasting Cognitive Styles in Vision-Language Models: Holistic Attention in Japanese Versus Analytical Focus in English","created":"2025-07-01","cited_by_count":0,"area":"mllm"},{"id":"2604.02048","title":"Jagle: Building a Large-Scale Japanese Multimodal Post-Training Dataset for Vision-Language Models","created":"2026-04-02","cited_by_count":0,"area":"mllm"}],"next_cursor":null}