Recent advances in multimodal large language models enable new possibilities for image-based decision support. However, their reliability and operational trade-offs in neuroimaging remain insufficiently understood. We present a comprehensive benchmarking study of vision-enabled large language models for 2D neuroimaging using curated MRI and CT datasets covering multiple sclerosis, stroke, brain tumors, other abnormalities, and normal controls. Models are required to generate multiple outputs simultaneously, including diagnosis, diagnosis subtype, imaging modality, specialized sequence, and anatomical plane. Performance is evaluated across four directions: discriminative classification with abstention, calibration, structured-output validity, and computational efficiency. A multi-phase framework ensures fair comparison while controlling for selection bias. Across twenty frontier multimodal models, the results show that technical imaging attributes such as modality and plane are nearly solved, whereas diagnostic reasoning, especially subtype prediction, remains challenging. Tumor classification emerges as the most reliable task, stroke is moderately solvable, while multiple sclerosis and rare abnormalities remain difficult. Few-shot prompting improves performance for several models but increases token usage, latency, and cost. Gemini-2.5-Pro and GPT-5-Chat achieve the strongest overall diagnostic performance, while Gemini-2.5-Flash offers the best efficiency-performance trade-off. Among open-weight architectures, MedGemma-1.5-4B demonstrates the most promising results, as under few-shot prompting, it approaches the zero-shot performance of several proprietary models, while maintaining perfect structured output. These findings provide practical insights into performance, reliability, and efficiency trade-offs, supporting standardized evaluation of multimodal LLMs in neuroimaging.
Deep Learning-Powered Electrical Brain Signals Analysis: Advancing Neurological Diagnostics
College of Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术学院);DiFint Technology (Shanghai) Co(上海迪芬特技术有限公司);Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences(中国科学院上海微系统与信息技术研究所);School of Graduate Study, University of Chinese Academy of Sciences(中国科学院大学研究生院);The INSIDE Institute for Biological and Artificial Intelligence(生物与人工智能研究所)
Predicting Length of Stay in Neurological ICU Patients Using Classical Machine Learning and Neural Network Models: A Benchmark Study on MIMIC-IV
Data and Web Science Group School of Business Informatics and Mathematics University of Mannheim(数据与网络科学组 商务信息与数学学院 瑞士曼海姆大学);Human-Technology Interaction Lab Department of Neurosurgery University of Freiburg - Medical Center(人机交互实验室 神经外科系 瑞士弗赖堡医学院)
Clinically Calibrated Machine Learning Benchmarks for Large-Scale Multi-Disorder EEG Classification
Department of Electronics;Electrical Communication Engineering Indian Institute of Technology, Kharagpur West Bengal, India;Department of Computer Science;Engineering Indian Institute of Technology, Kharagpur West Bengal, India;Subir Chowdhury School of Quality;Reliability Indian Institute of Technology, Kharagpur West Bengal, India
GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
University of Georgia(佐治亚大学);University of Chicago(芝加哥大学);UIUC(伊利诺伊大学香槟分校);University of Texas at Austin(德克萨斯大学奥斯汀分校);University of California, Berkeley(加州大学伯克利分校);Emory University(埃默里大学);Virtue AI
Learning Multi-resolution Graph Edge Embedding for Discovering Brain Network Dysfunction in Neurological Disorders
University of Texas at Arlington(德克萨斯大学阿灵顿分校);University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校);University of Pittsburgh(匹兹堡大学);POSTECH(浦项科技大学)
PICasso: An AI-Enabled Design Framework for Autonomous Optimization of Silicon Photonic Devices
New Jersey Institute of Technology(新泽西理工学院);University of Michigan(密歇根大学);Colorado State University(科罗拉多州立大学);AMD(超威半导体公司);Case Western Reserve(凯斯西储大学);University of Illinois, Chicago(伊利诺伊大学芝加哥分校)
Computer-Vision-Enabled Worker Video Analysis for Motion Amount Quantification
The Polytechnic School at Arizona State University(亚利桑那州立大学理工学院);The School of Manufacturing Systems and Networks at Arizona State University(亚利桑那州立大学制造系统与网络学院)
本文提出一种基于计算机视觉的工人运动量量化框架,利用姿态估计和 Hotelling $T^2$ 统计量监测上下肢运动并预警,结合 Random Forest 实现跨环境人体工效学风险识别,准确率最高达 94%。