视觉大模型 / VLM

LUMEN: Longitudinal Multi-Modal Radiology Model for Prognosis and Diagnosis

LUMEN: 长期多模态放射学模型用于预后和诊断

Zhifan Jiang, Dong Yang, Vishwesh Nath, Abhijeet Parida, Nishad P. Kulkarni, Ziyue Xu, Daguang Xu, Syed Muhammad Anwar, Holger R. Roth, Marius George Linguraru

机构 * 1 Sheikh Zayed Institute for Pediatric Surgical Innovation, Children's National Hospital, Washington DC, USA 2 Nvidia Corporation, Santa Clara, CA, USA 3 ETSI Telecomunicaci\' o n, Universidad Polit\' e cnica de Madrid, Madrid, Spain 4 School of Medicine ； Health Sciences, George Washington University, Washington DC, USA 纠错

专题命中 视觉问答 ：vision-language model(abstract)；分类 cs.CV、cs.LG

AI总结 LUMEN模型通过多任务指令微调提升纵向放射影像的诊断与预后能力。

Comments Accepted to IEEE International Symposium on Biomedical Imaging (ISBI) 2026

UDVideoQA: A Traffic Video Question Answering Dataset for Multi-Object Spatio-Temporal Reasoning in Urban Dynamics

UDVideoQA: 一个用于城市动态多对象时空推理的交通视频问答数据集

Joseph Raj Vishal, Nagasiri Poluri, Katha Naik, Rutuja Patil, Kashyap Hegde Kota, Krishna Vinod, Prithvi Jai Ramesh, Mohammad Farhadi, Yezhou Yang, Bharatesh Chakravarthi

机构 * Arizona State University（亚利桑那州立大学） 纠错

专题命中 视觉问答 ：grounding(abstract)；分类 cs.CV

AI总结 UDVideoQA是一个用于城市动态多对象时空推理的交通视频问答数据集，通过统一标注流程生成28K问题-答案对，评估视觉定位和因果推理能力。