AI 大模型

视觉大模型 / VLM

视觉语言模型、视觉推理、视觉问答、图文理解和视觉 grounding。

2025-10-13 至 2025-10-13 共收录 2 篇信号源：cs.CV, cs.AI, cs.LG

1. 文档图表理解 2 篇

2508.20582 2025-10-13 cs.IR 71%

SUMMA: A Multimodal Large Language Model for Advertisement Summarization

Weitao Jia, Shuo Yin, Zhoufutu Wen, Han Wang, Zehui Dai, Kun Zhang, Zhenyu Li, Tao Zeng, Xiaohui Lv

专题命中文档图表理解：multimodal large language model(title)

2510.07545 2025-10-13 cs.CL cs.LG 70%

Deploying Tiny LVLM Judges for Real-World Evaluation of Chart Models: Lessons Learned and Best Practices

Md Tahmid Rahman Laskar, Mohammed Saidul Islam, Ridwan Mahbub, Mizanur Rahman, Amran Bhuiyan, Israt Jahan, Mir Tafseer Nayeem, Shafiq Joty, Enamul Hoque, Jimmy Huang

机构 * York University（约克大学）； University of Alberta（阿尔伯塔大学）； Salesforce AI Research（Salesforce AI研究）

专题命中文档图表理解：vision-language model(abstract)；LLaVA(abstract)；分类 cs.LG

Comments Accepted to the EMNLP 2025 Industry Track