重大更新！公众号每日速递覆盖arXiv所有方向,涵盖CS|物理|数学|经济|统计|金融|生物|电气等领域。点击查看历史文章列表，可在公众号内订阅#arXiv每日学术速递话题，接收每日推送。点击访问arxivdAIly.com每日更新更及时。 人工智能cs.AI 方向，今日共计42篇
【1】 Maximum Entropy Baseline for Integrated Gradients
标题：积分梯度的最大熵基线
作者：Hanxiao Tan
机构*：AI Group, TU Dortmund, Germany
链接：点击下载PDF文件
【2】 Uncertainty-Aware Search Framework for Multi-Objective Bayesian Optimization
标题：多目标贝叶斯优化的不确定性感知搜索框架
作者：Syrine Belakaria,Aryan Deshwal,Nitthilan Kannappan Jayakodi,Janardhan Rao Doppa
机构*：School of EECS, Washington State University
Journal-ref：Proceedings of the AAAI Conference on Artificial Intelligence. 2020
链接：点击下载PDF文件
【3】 Mining Logical Event Schemas From Pre-Trained Language Models
标题：从预先训练的语言模型中挖掘逻辑事件模式
作者：Lane Lawley,Lenhart Schubert
机构*：University of Rochester, Department of Computer Science
备注：To appear at ACL SRW 2022
链接：点击下载PDF文件
【4】 Internet of Things Device Capabilities, Architectures, Protocols, and Smart Applications in Healthcare Domain: A Review
标题：医疗保健领域的物联网设备功能、架构、协议和智能应用：综述
作者：Md. Milon Islam,Sheikh Nooruddin,Fakhri Karray,Ghulam Muhammad
机构*：Pattern Analysis and Machine Intelligence, Department of Electrical, and Computer Engineering, University of Waterloo, ON, N,L ,G, (e-mail:, Intelligence, Department of Electrical and Computer Engineering
备注：27 pages, 7 figures, 4 tables
链接：点击下载PDF文件
【5】 Offline Distillation for Robot Lifelong Learning with Imbalanced Experience
标题：非均衡体验下机器人终身学习的线下蒸馏
作者：Wenxuan Zhou,Steven Bohez,Jan Humplik,Abbas Abdolmaleki,Dushyant Rao,Markus Wulfmeier,Tuomas Haarnoja,Nicolas Heess
机构*：Robotics Institute, Carnegie Mellon University, DeepMind
链接：点击下载PDF文件
【6】 Adaptive Cross-Attention-Driven Spatial-Spectral Graph Convolutional Network for Hyperspectral Image Classification
标题：自适应交叉注意驱动的空间-谱图卷积网络用于高光谱图像分类
作者：Jin-Yu Yang,Heng-Chao Li,Wen-Shuai Hu,Lei Pan,Qian Du
链接：点击下载PDF文件
【7】 Towards Few-shot Entity Recognition in Document Images: A Label-aware Sequence-to-Sequence Framework
标题：面向文档图像的Few-Shot实体识别：一种标签感知的序列到序列框架
作者：Zilong Wang,Jingbo Shang
机构*：University of California, San Diego
备注：ACL 2022 Findings
链接：点击下载PDF文件
【8】 MuCoT: Multilingual Contrastive Training for Question-Answering in Low-resource Languages
标题：MuCoT：低资源语言问答的多语言对比训练
作者：Gokul Karthik Kumar,Abhishek Singh Gehlot,Sahal Shaji Mullappilly,Karthik Nandakumar
机构*：Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI), Abu Dhabi, UAE
备注：Accepted for oral presentation at ACL 2022 Workshop on Speech and Language Technologies for Dravidian Languages
链接：点击下载PDF文件
【9】 Multi-View Breast Cancer Classification via Hypercomplex Neural Networks
标题：基于超复杂神经网络的乳腺癌多视角分类
作者：Eleonora Lopez,Eleonora Grassucci,Martina Valleriani,Danilo Comminiello
机构*： when readingAuthors are with the Department of Information Engineering, Sapienza University of Rome
备注：This paper has been submitted to IEEE Transactions on Pattern Analysis and Machine Intelligence
链接：点击下载PDF文件
【10】 Membership-Mappings for Practical Secure Distributed Deep Learning
标题：实用安全分布式深度学习的成员映射
作者：Mohit Kumar,Weiping Zhang,Lukas Fischer,Bernhard Freudenthaler
机构*： Universityof Rostock, Zhang is with the Northwestern Polytechnical University
链接：点击下载PDF文件
【11】 Hierarchical Quality-Diversity for Online Damage Recovery
标题：分级质量--在线损害恢复的多样性
作者：Maxime Allard,Simón C. Smith,Konstantinos Chatzilygeroudis,Antoine Cully
机构*：Adaptive and Intelligent Robotics Lab, Imperial College London, United Kingdom, Computer Engineering and Informatics Department, University of Patras, Greece
备注：Accepted at GECCO 2022
链接：点击下载PDF文件
【12】 Back to the Roots: Reconstructing Large and Complex Cranial Defects using an Image-based Statistical Shape Model
标题：寻根：使用基于图像的统计形状模型重建大型复杂颅骨缺损
作者：Jianning Li,David G. Ellis,Antonio Pepe,Christina Gsaxner,Michele R. Aizenberg,Jens Kleesiek,Jan Egger
备注：9 pages
链接：点击下载PDF文件
【13】 NumGLUE: A Suite of Fundamental yet Challenging Mathematical Reasoning Tasks
标题：NumGLUE：一套基本但具有挑战性的数学推理任务
作者：Swaroop Mishra,Arindam Mitra,Neeraj Varshney,Bhavdeep Sachdeva,Peter Clark,Chitta Baral,Ashwin Kalyan
机构*：Arizona State University, Microsoft Research, Allen Institute for AI
备注：ACL 2022
链接：点击下载PDF文件
【14】 Proximal Policy Optimization Learning based Control of Congested Freeway Traffic
标题：基于近邻策略优化学习的高速公路拥堵交通控制
作者：Shurong Mo,Jie Qi,Anqi Pan
机构*： Donghua University
链接：点击下载PDF文件
【15】 ASR in German: A Detailed Error Analysis
标题：德语ASR：详细的错误分析
作者：Johannes Wirth,Rene Peinl
机构*：Research Group System Integration, Hof University of Applied Sciences, Hof, Germany, René Peinl
链接：点击下载PDF文件
【16】 Stylized Knowledge-Grounded Dialogue Generation via Disentangled Template Rewriting
标题：基于解缠模板重写的程式化基于知识的对话生成
作者：Qingfeng Sun,Can Xu,Huang Hu,Yujing Wang,Jian Miao,Xiubo Geng,Yining Chen,Fei Xu,Daxin Jiang
机构*：Microsoft, Beijing, China
备注：Accepted to NAACL 2022 Main Conference
链接：点击下载PDF文件
【17】 Automatic detection of glaucoma via fundus imaging and artificial intelligence: A review
标题：眼底成像和人工智能技术在青光眼自动检测中的应用
作者：Lauren Coan,Bryan Williams,Krishna Adithya Venkatesh,Swati Upadhyaya,Silvester Czanner,Rengaraj Venkatesh,Colin E. Willoughby,Srinivasan Kavitha,Gabriela Czanner
机构*：Communications, Lancaster University, UK), Science and Mathematics, Liverpool John Moores University, Informatics and Information Technologies, Slovak University of Technology, Slovakia), Officer, Aravind Eye Hospital, Pondicherry, India), Ulster University, UK)
链接：点击下载PDF文件
【18】 Enriching Artificial Intelligence Explanations with Knowledge Fragments
标题：用知识片段丰富人工智能解释
作者：Jože M. Rožanec,Elena Trajkova,Inna Novalija,Patrik Zajec,Klemen Kenda,Blaž Fortuna,Dunja Mladenić
机构*： Blaž, Fortuna , and Dunja Mladeni´c , Jožef Stefan International Postgraduate School, Jamova , Ljubljana, Slovenia, Jožef Stefan Institute, Jamova , Ljubljana, Slovenia, Qlector d.o.o., Rovšnikova , Ljubljana, Slovenia
链接：点击下载PDF文件
【19】 Multi-agent Actor-Critic with Time Dynamical Opponent Model
标题：具有时间动态对手模型的多智能体参与者-批评者
作者：Yuan Tian,Klaus-Rudolf Kladny,Qin Wang,Zhiwu Huang,Olga Fink
机构*：ETH Z¨urich, Switzerland, EPFL, Switzerland, Singapore Management University, Singapore
链接：点击下载PDF文件
【20】 DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object Detection
标题：DAIR-V2X：面向车基协同三维目标检测的大规模数据集
作者：Haibao Yu,Yizhen Luo,Mao Shu,Yiyi Huo,Zebang Yang,Yifeng Shi,Zhenglong Guo,Hanyu Li,Xing Hu,Jirui Yuan,Zaiqing Nie
机构*：Institute for AI Industry Research(AIR), Tsinghua University, Baidu Inc. , Department of Computer Science and Technology, Tsinghua University, University of Chinese Academy of Science
备注：CVPR2022
链接：点击下载PDF文件
【21】 Solving Price Per Unit Problem Around the World: Formulating Fact Extraction as Question Answering
标题：解决世界范围内的单价问题：将事实提取视为问题回答
作者：Tarik Arici,Kushal Kumar,Hayreddin Çeker,Anoop S V K K Saladi,Ismail Tutar
机构*：New York, NY, USA, Bengaluru, KA, India, Seattle, WA, USA
备注：8 pages, 2 figures, 8 tables. This work was accepted in TrueFact KDD '21 workshop
链接：点击下载PDF文件
【22】 A Reinforcement Learning Approach for Electric Vehicle Routing Problem with Vehicle-to-Grid Supply
标题：考虑车网供电的电动汽车路径问题的强化学习方法
作者：Ajay Narayanan,Prasant Misra,Ankush Ojha,Vivek Bandhu,Supratim Ghosh,Arunchandar Vasan
机构*：Tata Consultancy Services - Research | #Tata Consultancy Services
备注：6 pages; 1 figure; Proc. of the Adaptive and Learning Agents Workshop (ALA 2022), Cruz, Hayes, da Silva, Santos (eds.), May 9-10, 2022, Online, https: ala2022.github.io.2022
链接：点击下载PDF文件
【23】 Forecasting SQL Query Cost at Twitter
标题：预测Twitter的SQL查询成本
作者：Chunxu Tang,Beinan Wang,Zhenxiao Luo,Huijun Wu,Shajan Dasan,Maosong Fu,Yao Li,Mainak Ghosh,Ruchin Kabra,Nikhil Kantibhai Navadiya,Da Cheng,Fred Dai,Vrushali Channapattan,Prachi Mishra
机构*：Twitter, Inc., San Francisco, USA
备注：2021 IEEE International Conference on Cloud Engineering (IC2E). IEEE, 2021
链接：点击下载PDF文件
【24】 Trigger-GNN: A Trigger-Based Graph Neural Network for Nested Named Entity Recognition
标题：Trigger-GNN：一种基于触发器的嵌套命名实体识别图神经网络
作者：Yuan Sui,Fanyang Bu,Yingting Hu,Wei Yan,Liang Zhang
机构*：a School of Information Science and Engineering, Shandong Normal University, Jinan, China, b Science and Key Laboratory of Particle Physics and Particle Irradiation, Shandong University, Qingdao, China
备注：Submitted to IJCNN-2022. arXiv admin note: text overlap with arXiv:2004.07493 by other authors
链接：点击下载PDF文件
【25】 Fully End-to-end Autonomous Driving with Semantic Depth Cloud Mapping and Multi-Agent
标题：基于语义深度云映射和多智能体的全端到端自主驾驶
作者：Oskar Natan,Jun Miura
机构*： andalso with the Department of Computer Science and Electronics, GadjahMada University
备注：This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible
链接：点击下载PDF文件
【26】 Make The Most of Prior Data: A Solution for Interactive Text Summarization with Preference Feedback
标题：充分利用先验数据：一种带偏好反馈的交互式文本摘要解决方案
作者：Duy-Hung Nguyen,Nguyen Viet Dung Nghiem,Bao-Sinh Nguyen,Dung Tien Le,Shahab Sabahi,Minh-Tien Nguyen,Hung Le
机构*：Cinnamon AI ,th floor, Geleximco building, Hoang Cau, Dong Da, Hanoi, Vietnam.
链接：点击下载PDF文件
【27】 Learning Design and Construction with Varying-Sized Materials via Prioritized Memory Resets
标题：基于优先记忆重置的不同尺寸材料的学习设计与施工
作者：Yunfei Li,Tao Kong,Lei Li,Yi Wu
机构*：designer, env, Replay buffer, Update, Query, , , ID, pose, Reset, Teleporter, Motion generator, Train RL with PMR, low-level, controller, !, Simulated trajectory, Arm robot, cliff, blocks with various size, Real robot deployment
备注：To be published in ICRA 2022
链接：点击下载PDF文件
【28】 Scalable privacy-preserving cancer type prediction with homomorphic encryption
标题：基于同态加密的可扩展隐私保护癌症类型预测
作者：Esha Sarkar,Eduardo Chielle,Gamze Gursoy,Leo Chen,Mark Gerstein,Michail Maniatakos
机构*：Tandon School of Engineering, Brooklyn, USA, Department of Electrical and, Computer Engineering, New York University Abu Dhabi, Abu Dhabi, UAE, Program in Computational Biology, and Bioinformatics, Yale University, New Haven, USA, Department of Computer Science
链接：点击下载PDF文件
【29】 Deep Normed Embeddings for Patient Representation
标题：用于患者表示的深度范数嵌入
作者：Thesath Nanayakkara,Gilles Clermont,Christopher James Langmead,David Swigon
机构*：Department of Mathematics, Pittsburgh, PA, Department of Critical Care Medicine, The Clinical Research, Investigation, and Systems Modeling of Acute Illness (CRISMA) Center, University of Pittsburgh School of Medicine, Computational Biology Department
备注：A minimal implementation of this work can be found at this https URL
链接：点击下载PDF文件
【30】 Neural Processes with Stochastic Attention: Paying more attention to the context dataset
标题：随机注意的神经过程：对上下文数据集的更多关注
作者：Mingyu Kim,Kyeongryeol Go,Se-Young Yun
机构*：KAIST AI
备注：Published at ICLR2022; Presented at 5th workshop on Meta-Learning at NeurIPS2021
链接：点击下载PDF文件
【31】 Heterogeneous Acceleration Pipeline for Recommendation System Training
标题：用于推荐系统训练的异质加速管道
作者：Muhammad Adnan,Yassaman Ebrahimzadeh Maboud,Divya Mahajan,Prashant J. Nair
机构*：The University of British Columbia∗, Microsoft+
链接：点击下载PDF文件
【32】 Deep Reinforcement Learning Based Semi-Autonomous Control for Robotic Surgery
标题：基于深度强化学习的机器人手术半自主控制
作者：Ruiqi Zhu,Dandan Zhang,Benny Lo
机构*：The Hamlyn Centre, Imperial College London, Department of Engineering Mathematics, University of Bristol
链接：点击下载PDF文件
【33】 A Simple Approach to Adversarial Robustness in Few-shot Image Classification
标题：一种在Few-Shot图像分类中提高对手稳健性的简单方法
作者：Akshayvarun Subramanya,Hamed Pirsiavash
机构*： University of Maryland, Baltimore County, University of California, Davis
链接：点击下载PDF文件
【34】 A Multilingual Perspective Towards the Evaluation of Attribution Methods in Natural Language Inference
标题：自然语言推理归因方法评价的多语种视角
作者：Kerem Zaman,Yonatan Belinkov
机构*：Bo˘gaziçi University, Istanbul, Turkey, Technion – Israel Institute of Technology, Haifa, Israel
备注：15 pages, 5 figures. Code and data at this https URL
链接：点击下载PDF文件
【35】 ProtoTEx: Explaining Model Decisions with Prototype Tensors
标题：ProtoTEx：用原型张量解释模型决策
作者：Anubrata Das,Chitrank Gupta,Venelin Kovatchev,Matthew Lease,Junyi Jessy Li
机构*：School of Information and ,Dept. of Linguistics, The University of Texas at Austin, Dept. of Computer Science, Indian Institute of Technology Bombay
备注：Accepted in ACL Main 2022
链接：点击下载PDF文件
【36】 Accelerated Design and Deployment of Low-Carbon Concrete for Data Centers
标题：数据中心低碳混凝土的加速设计与部署
作者：Xiou Ge,Richard T. Goodwin,Haizi Yu,Pablo Romero,Omar Abdelrahman,Amruta Sudhalkar,Julius Kusuma,Ryan Cialdella,Nishant Garg,Lav R. Varshney
机构*：Champaign, USA
备注：18 pages. arXiv admin note: text overlap with arXiv:1905.08222
链接：点击下载PDF文件
【37】 Learning Implicit Priors for Motion Optimization
标题：运动优化中的隐式先验学习
作者：Alexander Lambert,An T. Le,Julen Urain,Georgia Chalvatzaki,Byron Boots,Jan Peters
机构*： Allen School of Computer Science and Engineering (CSE), University of Washington (USA) 2 Intelligent Autonomous Systems Lab, Technische Universit¨at Darmstadt(Germany)(a) EBM for trajectories(b) Pouring TaskFig
备注：15 pages, paper website: this https URL
链接：点击下载PDF文件
【38】 Position-wise optimizer: A nature-inspired optimization algorithm
标题：位置优化器：一种受自然启发的优化算法
作者：Amir Valizadeh
机构*：Keshavarz Blvd., Tehran, Iran
备注：12 pages, 4 figures
链接：点击下载PDF文件
【39】 Spatiotemporal Estimation of TROPOMI NO2 Column with Depthwise Partial Convolutional Neural Network
标题：用深度部分卷积神经网络估计Tropomi NO2柱的时空分布
作者：Yannic Lops,Masoud Ghahremanloo,Arman Pouyaei,Yunsoo Choi,Jia Jung,Seyedali Mousavinezhad,Ahmed Khan Salman,Davyda Hammond
机构*：Department of Earth and Atmospheric Sciences, University of Houston, TX , Oak Ridge Associated Universities, Oak Ridge, TN
备注：Keywords: Partial Convolution, Depthwise, TROPOMI, Kriging, Spatiotemporal Imputation, CMAQ. 12 pages & 6 figures
链接：点击下载PDF文件
【40】 Variational Heteroscedastic Volatility Model
标题：变分异方差波动率模型
作者：Zexuan Yin,Paolo Barucca
机构*：†Department of Computer Science, University College London, WC,E ,JE, United Kingdom, ‡International Research Training Group, Humboldt Universit¨at zu Berlin, Group , Spandauer Str., Berlin, Germany
链接：点击下载PDF文件
【41】 A deep learning method for solving stochastic optimal control problems driven by fully-coupled FBSDEs
标题：求解全耦合FBSDE驱动的随机最优控制问题的深度学习方法
作者：Shaolin Ji,Shige Peng,Ying Peng,Xichuan Zhang
机构*：Zhongtai Securities Institute for Financial Studies, Shandong University, China, School of Mathematics, Shandong University, China
链接：点击下载PDF文件
【42】 Enhancement of Pitch Controllability using Timbre-Preserving Pitch Augmentation in FastPitch
标题：在快速音调中使用保音性音调增强来增强音调的可控性
作者：Hanbin Bae,Young-Sun Joo
机构*：Speech AI Lab, NCSOFT Corp., Republic of Korea
备注：Submitted to INTERSPEECH 2022
链接：点击下载PDF文件
机器翻译，仅供参考
重大更新！公众号每日速递覆盖arXiv所有方向,涵盖CS|物理|数学|经济|统计|金融|生物|电气等领域。点击查看历史文章列表，可在公众号内订阅#arXiv每日学术速递话题，接收每日推送。点击访问arxivdaily.com每日更新更及时。 |
用Deepseek满血版问问看
