检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Wu, Jiageng Gu, Bowen Zhou, Ren Xie, Kevin Snyder, Doug Jiang, Yixing Carducci, Valentina Wyss, Richard Desai, Rishi J. Alsentzer, Emily Celi, Leo Anthony Rodman, Adam Schneeweiss, Sebastian Chen, Jonathan H. Romero-Brufau, Santiago Lin, Kueiyu Joshua Yang, Jie Division of Pharmacoepidemiology and Pharmacoeconomics Department of Medicine Brigham and Women’s Hospital Harvard Medical School BostonMA United States Siebel School of Computing and Data Science The Grainger College of Engineering University of Illinois Urbana-Champaign UrbanaIL United States Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology CambridgeMA United States Department of Otorhinolaryngology – Head & Neck Surgery Mayo Clinic RochesterMN United States Department of Biostatistics Harvard T.H. Chan School of Public Health Harvard University BostonMA United States Department of Biomedical Data Science Stanford University Palo AltoCA United States Laboratory for Computational Physiology Massachusetts Institute of Technology CambridgeMA United States Division of Pulmonary Critical Care and Sleep Medicine Beth Israel Deaconess Medical Center BostonMA United States Division of General Internal Medicine Department of Medicine Beth Israel Deaconess Medical Center BostonMA United States Stanford Center for Biomedical Informatics Research Stanford University StanfordCA United States Division of Hospital Medicine Stanford University StanfordCA United States Stanford Clinical Excellence Research Center Stanford University StanfordCA United States Kempner Institute for the Study of Natural and Artificial Intelligence Harvard University MA United States Broad Institute of MIT and Harvard CambridgeMA United States Harvard Data Science Initiative Harvard University CambridgeMA United States

Large language models (LLMs) hold great promise for medical applications and are evolving rapidly, with new models being released at an accelerated pace. However, current evaluations of LLMs in clinical contexts remain limited. Most existing benchmarks rely on medical exam-style questions or PubMed-derived text, failing to capture the complexity of real-world electronic health record (EHR) data. Others focus narrowly on specific application scenarios, limiting their generalizability across broader clinical use. To address this gap, we present BRIDGE, a comprehensive multilingual benchmark comprising 87 tasks sourced from real-world clinical data sources across nine languages. We systematically evaluated 52 state-of-the-art LLMs (including DeepSeek-R1, GPT-4o, Gemini, and Llama 4) under various inference strategies. With a total of 13,572 experiments, our results reveal substantial performance variation across model sizes, languages, natural language processing tasks, and clinical specialties. Notably, we demonstrate that open-source LLMs can achieve performance comparable to proprietary models, while medically fine-tuned LLMs based on older architectures often underperform versus updated general-purpose models. The BRIDGE and its corresponding leaderboard serve as a foundational resource and a unique reference for the development and evaluation of new LLMs in real-world clinical text understanding. © 2025, CC BY-NC-SA.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

ImgSensingNet: UAV vision guided aerial-ground air quality sensing system

arXiv

引用

arXiv 2019年

作者： Yang, Yuzhe Hu, Zhiwen Bian, Kaigui Song, Lingyang Computer Science and Artificial Intelligence Laboratory MIT CambridgeMA02139 United States School of Electrical Engineering and Computer Science Peking University Beijing China

Given the increasingly serious air pollution problem, the monitoring of air quality index (AQI) in urban areas has drawn considerable attention. This paper presents ImgSensingNet, a vision guided aerial-ground sensing system, for finegrained air quality monitoring and forecasting using the fusion of haze images taken by the unmanned-aerial-vehicle (UAV) and the AQI data collected by an on-ground three-dimensional (3D) wireless sensor network (WSN). Specifically, ImgSensingNet first leverages the computer vision technique to tell the AQI scale in different regions from the taken haze images, where haze-relevant features and a deep convolutional neural network (CNN) are designed for direct learning between haze images and corresponding AQI scale. Based on the learnt AQI scale, ImgSensingNet determines whether to wake up on-ground wireless sensors for small-scale AQI monitoring and inference, which can greatly reduce the energy consumption of the system. An entropybased model is employed for accurate real-time AQI inference at unmeasured locations and future air quality distribution forecasting. We implement and evaluate ImgSensingNet on two university campuses since Feb. 2018, and has collected 17,630 photos and 2.6 millions of AQI data samples. Experimental results confirm that ImgSensingNet can achieve higher inference accuracy while greatly reduce the energy consumption, compared to state-of-the-art AQI monitoring approaches. Copyright © 2019, The Authors. All rights reserved.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Author Correction: Enhancing the immunogenicity of lipid-nanoparticle mRNA vaccines by adjuvanting the ionizable lipid and the mRNA

引用

Nature biomedical engineering 2025年第2期9卷 280页

作者： Bowen Li Allen Yujie Jiang Idris Raji Caroline Atyeo Theresa M Raimondo Akiva G R Gordon Luke H Rhym Tahoura Samad Corina MacIsaac Jacob Witten Haseeb Mughal Taras M Chicz Yue Xu Ryan P McNamara Sangeeta Bhatia Galit Alter Robert Langer Daniel G Anderson David H. Koch Institute for Integrative Cancer Research Massachusetts Institute of Technology Cambridge MA USA. Department of Chemical Engineering Massachusetts Institute of Technology Cambridge MA USA. Department of Pharmaceutical Sciences Leslie Dan Faculty of Pharmacy University of Toronto Toronto Ontario Canada. Institute of Biomedical Engineering University of Toronto Toronto Ontario Canada. Princess Margaret Cancer Centre University Health Network Toronto Ontario Canada. Ragon Institute of MGH MIT and Harvard Cambridge MA USA. Division of Medical Sciences Harvard University Boston MA USA. Institute for Medical Engineering and Science Massachusetts Institute of Technology Cambridge MA USA. Harvard-MIT Division of Health Science and Technology Massachusetts Institute of Technology Cambridge MA USA. Department of Chemistry Massachusetts Institute of Technology Cambridge MA USA. Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge MA USA. Department of Medicine Brigham and Women's Hospital Harvard Medical School Boston MA USA. Broad Institute of Massachusetts Institute of Technology and Harvard Cambridge MA USA. Wyss Institute at Harvard Cambridge MA USA. Howard Hughes Medical Institute Cambridge MA USA. David H. Koch Institute for Integrative Cancer Research Massachusetts Institute of Technology Cambridge MA USA. dgander@mit.edu. Department of Chemical Engineering Massachusetts Institute of Technology Cambridge MA USA. dgander@mit.edu. Ragon Institute of MGH MIT and Harvard Cambridge MA USA. dgander@mit.edu. Institute for Medical Engineering and Science Massachusetts Institute of Technology Cambridge MA USA. dgander@mit.edu. Harvard-MIT Division of Health Science and Technology Massachusetts Institute of Technology Cambridge MA USA. dgander@mit.edu.

来源：评论

学校读者我要写书评

暂无评论

Physion: Evaluating Physical Prediction from Vision in Humans and Machines

arXiv

引用

arXiv 2021年

作者： Bear, Daniel M. Wang, Elias Mrowca, Damian Binder, Felix Tung, Hsiao-Yu Fish Pramod, R.T. Holdaway, Cameron Tao, Sirui Smith, Kevin Sun, Fan-Yun Fei-Fei, Li Kanwisher, Nancy Tenenbaum, Joshua B. Yamins, Daniel L.K. Fan, Judith Department of Psychology StanfordCA94305 United States Department of Electrical Engineering StanfordCA94305 United States Department of Computer Science StanfordCA94305 United States Wu Tsai Neurosciences Institute StanfordCA94305 United States Department of Cognitive Science UC San Diego CA92093 United States Department of Psychology UC San Diego CA92093 United States Department of Brain and Cognitive Sciences and CBMM MIT CambridgeMA02139 United States

While current vision algorithms excel at many challenging tasks, it is unclear how well they understand the physical dynamics of real-world environments. Here we introduce Physion, a dataset and benchmark for rigorously evaluating the ability to predict how physical scenarios will evolve over time. Our dataset features realistic simulations of a wide range of physical phenomena, including rigid and soft-body collisions, stable multi-object configurations, rolling, sliding, and projectile motion, thus providing a more comprehensive challenge than previous benchmarks. We used Physion to benchmark a suite of models varying in their architecture, learning objective, input-output structure, and training data. In parallel, we obtained precise measurements of human prediction behavior on the same set of scenarios, allowing us to directly evaluate how well any model could approximate human behavior. We found that vision algorithms that learn object-centric representations generally outperform those that do not, yet still fall far short of human performance. On the other hand, graph neural networks with direct access to physical state information both perform substantially better and make predictions that are more similar to those made by humans. These results suggest that extracting physical representations of scenes is the main bottleneck to achieving human-level and human-like physical understanding in vision algorithms. We have publicly released all data and code to facilitate the use of Physion to benchmark additional models in a fully reproducible manner, enabling systematic evaluation of progress towards vision algorithms that understand physical environments as robustly as people do. Copyright © 2021, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Measuring the complexity of packet traces

arXiv

引用

arXiv 2019年

作者： Avin, Chen Ghobadi, Manya Griner, Chen Schmid, Stefan School of Electrical and Computer Engineering Ben Gurion University of the Negev Israel Computer Science and Artificial Intelligence Laboratory MIT United States Faculty of Computer Science University of Vienna Austria

This paper studies the structure of several real-world traces (including Facebook, High Performance Computing, Machine Learning, and simulation generated traces) and presents a systematic approach to quantify and compare the structure of packet traces based on the entropy contained in the trace file. Insights into the structure of packet traces can lead to improved network algorithms that are optimized toward specific traffic patterns. We then present a methodology to quantify the temporal and non-temporal components of entropy contained in a packet trace, called the trace complexity, using randomization and compression. We show that trace complexity provides unique insights into the characteristics of various applications and argue that there is a need for traffic generation models that preserve the intrinsic structure of empirically measured application traces. We then propose a traffic generator model that is able to produce a synthetic trace that matches the complexity level of its corresponding real-world trace. Copyright © 2019, The Authors. All rights reserved.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

Topology attack and defense for graph neural networks: An optimization perspective

arXiv

引用

arXiv 2019年

作者： Xu, Kaidi Chen, Hongge Liu, Sijia Chen, Pin-Yu Weng, Tsui-Wei Hong, Mingyi Lin, Xue Electrical & Computer Engineering Northeastern University Boston United States Electrical Engineering & Computer Science Massachusetts Institute of Technology Cambridge United States MIT-IBM Watson AI Lab IBM Research Electrical & Computer Engineering University of Minnesota Minneapolis United States

Graph neural networks (GNNs) which apply the deep neural networks to graph data have achieved significant performance for the task of semi-supervised node classification. However, only few work has addressed the adversarial robustness of GNNs. In this paper, we first present a novel gradient-based attack method that facilitates the difficulty of tackling discrete graph data. When comparing to current adversarial attacks on GNNs, the results show that by only perturbing a small number of edge perturbations, including addition and deletion, our optimization-based attack can lead to a noticeable decrease in classification performance. Moreover, leveraging our gradient-based attack, we propose the first optimization-based adversarial training for GNNs. Our method yields higher robustness against both different gradient based and greedy attack methods without sacrificing classification accuracy on original graph. Code is available at https://***/KaidiXu/GCN_ADV_Train. Copyright © 2019, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Probabilistic Machine Learning for Healthcare

引用

Biomedical Data science 2021年第1期4卷 393-415页

作者： Irene Y. Chen Shalmali Joshi Marzyeh Ghassemi Rajesh Ranganath 1Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge Massachusetts 02139 USA email: iychen@mit.edu 2Vector Institute Toronto Ontario M5G 1M1 Canada email: shalmali@vectorinstitute.ai 3Institute for Medical and Evaluative Sciences Massachusetts Institute of Technology Cambridge Massachusetts 02139 USA 6Department of Population Health New York University Grossman School of Medicine New York NY 10016 USA 5Center for Data Science New York University New York NY 10012 USA 4Department of Computer Science Courant Institute New York University New York NY 10012 USA

Machine learning can be used to make sense of healthcare data. Probabilistic machine learning models help provide a complete picture of observed data in healthcare. In this review, we examine how probabilistic machine learning can advance healthcare. We consider challenges in the predictive model building pipeline where probabilistic models can be beneficial, including calibration and missing data. Beyond predictive models, we also investigate the utility of probabilistic machine learning models in phenotyping, in generative models for clinical use cases, and in reinforcement learning.

关键词： probabilistic modeling health electronic health records machine learning artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

From Solar Cells to Ocean Buoys: Wide-Bandwidth Limits to Absorption by Metaparticle Arrays

引用

Physical Review Applied 2019年第3期11卷 034033-034033页

作者： Mohammed Benzaouia Grgur Tokić Owen D. Miller Dick K.P. Yue Steven G. Johnson Department of Electrical Engineering and Computer Science MIT Cambridge Massachusetts 02139 USA Department of Mechanical Engineering MIT Cambridge Massachusetts 02139 USA Department of Applied Physics and Energy Sciences Institute Yale University New Haven Connecticut 06511 USA Department of Mathematics MIT Cambridge Massachusetts 02139 USA

In this paper, we develop an approximate wide-bandwidth upper bound to the absorption enhancement in arrays of metaparticles, applicable to general wave-scattering problems and motivated here by ocean-buoy energy extraction. We show that general limits, including the well-known Yablonovitch result in solar cells, arise from reciprocity conditions. The use of reciprocity in the stochastic regime leads us to a corrected diffusion model from which we derive our main result: an analytical prediction of optimal array absorption that closely matches exact simulations for both random and optimized arrays under angle and frequency averaging. This result also enables us to propose and quantify approaches to increase performance through careful particle design and/or using external reflectors. We show, in particular, that the use of membranes on the water’s surface allows substantial enhancement.

关键词： Elasticity Electromagnetism Ocean energy Scattering theory Metamaterials Solar cells

来源：评论

学校读者我要写书评

暂无评论

mitigation of Doxorubicin Cardiotoxicity With Synergistic miRNA Combinations Identified Using Combinatorial Genetics en masse (CombiGEM)

引用

JACC: CardioOncology 2025年第4期7卷 396-410页

作者： Higashikuni, Yasutomi Platt, Colin Hastings, Margaret H. Chen, William C.W. Guerra, Justin R.B. Tokuyama, Takeshi Torizal, Fuad Gandhi Liu, Wenhao Obana, Takumi Bayer, Abraham L. Whipple, Hannah Kuznetsov, Alexandra Yeri, Ashish Turissini, Cole Kitchen, Robert R. Shibayama, Kota Matsumura, Takayoshi Takeda, Norihiko Uosaki, Hideki Asnani, Aarti H. Lu, Timothy K. Rosenzweig, Anthony Division of Cardiovascular and Genetic Research Center for Molecular Medicine Jichi Medical University Shimotsuke Japan Department of Cardiovascular Medicine The University of Tokyo Tokyo Japan Synthetic Biology Group MIT Synthetic Biology Center Massachusetts Institute of Technology Cambridge MA United States Research Laboratory of Electronics Massachusetts Institute of Technology Cambridge MA United States Department of Biological Engineering Massachusetts Institute of Technology Cambridge MA United States Cardiovascular Research Center Division of Cardiology Corrigan Minehan Heart Center Department of Medicine Massachusetts General Hospital Harvard Medical School Boston MA United States Stanley and Judith Frankel Institute for Heart and Brain Health University of Michigan Medical Center Ann Arbor MI United States Division of Basic Biomedical Sciences Sanford School of Medicine University of South Dakota Vermillion SD United States Division of Regenerative Medicine Center for Molecular Medicine Jichi Medical University Shimotsuke Japan Division of Cardiovascular Medicine Department of Medicine Beth Israel Deaconess Medical Center and Harvard Medical School Boston MA United States Department of Immunology Tufts University Boston MA United States Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge MA United States

Background: Cardiomyocyte loss occurs in acute and chronic cardiac injury, including cardiotoxicity due to chemotherapeutics like doxorubicin, and contributes to heart failure development. There is a pressing need for cardiac-specific therapeutics that target cardiomyocyte loss, preventing chemotherapy complications without compromising chemotherapeutic efficacy. Objectives: The authors employed massively parallel combinatorial genetic screening to find microRNA (miRNA) combinations that promote cardiomyocyte survival. Methods: CombiGEM (combinatorial genetics en masse) screening in a cardiomyocyte cell line was followed by validation in the original cell type and screening in primary cardiomyocytes. The top combination was tested in mouse and developing zebrafish models of doxorubicin cardiotoxicity. RNA sequencing provided insight into possible mechanisms. Results: Multiple miRNA combinations protected cardiomyocytes from doxorubicin in vitro. The most effective (miR-222+miR-455) appeared to act synergistically, and mitigated doxorubicin cardiotoxicity phenotypes in murine and zebrafish in vivo models. RNA sequencing revealed overlapping and synergistic regulation of relevant genes and biological processes in cardiomyocytes, including mitochondrial homeostasis, oxidative stress, muscle contraction, and others. Conclusions: We identified miR-222 and miR-455 as a combination with potential therapeutic applications for cardioprotection. This study furthers our knowledge of the cardiac effects of miRNAs and their combinations and demonstrates the potential of CombiGEM for cardioprotective combinatorial therapeutic discovery. © 2025 The Authors

关键词： cardiac myocytes cardiomyopathy chemotherapy toxicity cytoprotection drug therapy heart failure innovation preclinical study systems biology

来源：评论

学校读者我要写书评

暂无评论

Mediated interactions beyond the nearest neighbor in an array of superconducting qubits

arXiv

引用

arXiv 2021年

作者： Yanay, Yariv Braumüller, Jochen Orlando, Terry P. Gustavsson, Simon Tahan, Charles Oliver, William D. Laboratory for Physical Sciences 8050 Greenmead Dr. College ParkMD20740 United States Research Laboratory of Electronics Massachusetts Institute of Technology CambridgeMA02139 United States Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology CambridgeMA02139 United States Department of Physics Massachusetts Institute of Technology CambridgeMA02139 United States MIT Lincoln Laboratory LexingtonMA02421 United States

We consider mediated interactions in an array of floating transmons, where each qubit capacitor consists of two superconducting pads galvanically isolated from ground. Each such pair contributes two quantum degrees of freedom, one of which is used as a qubit, while the other remains fixed. However, these extraneous modes can generate coupling between the qubit modes that extends beyond the nearest neighbor. We present a general formalism describing the formation of this coupling and calculate it for a one-dimensional chain of transmons. We show that the strength of coupling and its range (that is, the exponential falloff) can be tuned independently via circuit design to realize a continuum from nearest-neighbor-only interactions to interactions that extend across the length of the chain. We present designs with capacitance and microwave simulations showing that various interaction configurations can be achieved in realistic circuits. Such coupling could be used in analog simulation of different quantum regimes or to increase connectivity in digital quantum systems. Thus mechanism must also be taken into account in other types of qubits with extraneous modes. Copyright © 2021, The Authors. All rights reserved.

关键词： Quantum optics

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：