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41篇

【1】 Ensemble Spectral Prediction (ESP) Model for Metabolite Annotation
标题：代谢物注释的集成谱预测(ESP)模型
作者：Xinmeng Li,Hao Zhu,Li-ping Liu,Soha Hassoun
机构*：Department of Computer Science, Tufts University, Medford , USA; bDepartment of Chemical and Biological Engineering, Tufts University, Medford , USA
链接：点击下载PDF文件

【2】 An Audit of Misinformation Filter Bubbles on YouTube: Bubble Bursting and Recent Behavior Changes
标题：对过滤虚假信息的审计Youtube上的泡沫：泡沫爆炸和最近的行为变化
作者：Matus Tomlein,Branislav Pecher,Jakub Simko,Ivan Srba,Robert Moro,Elena Stefancova,Michal Kompan,Andrea Hrckova,Juraj Podrouzek,Maria Bielikova
机构*： Kempelen Institute of Intelligent Technologies
Journal-ref：RecSys '21: Fifteenth ACM Conference on Recommender Systems, 2021
链接：点击下载PDF文件

【3】 A World-Self Model Towards Understanding Intelligence
标题：理解智能的世界-自我模型
作者：Yutao Yue
机构*：Institute of Deep Perception Technology, JITRI, Wuxi, China
备注：19 pages, 5 figures
链接：点击下载PDF文件

【4】 Code Smells for Machine Learning Applications
标题：机器学习应用中的代码嗅觉
作者：Haiyin Zhang,Luís Cruz,Arie van Deursen
机构*：AI for Fintech Research, ING, Amsterdam, Netherlands, Delft University of Technology, Delft, Netherlands
备注：Accepted at CAIN
链接：点击下载PDF文件

【5】 LAMBDA: Covering the Solution Set of Black-Box Inequality by Search Space Quantization
标题：Lambda：搜索空间量化覆盖黑盒不等式解集
作者：Lihao Liu,Tianyue Feng,Xingyu Xing,Junyi Chen
机构*：School of Automotive Studies, Tongji University
链接：点击下载PDF文件

【6】 Speech-enhanced and Noise-aware Networks for Robust Speech Recognition
标题：用于鲁棒语音识别的语音增强和噪声感知网络
作者：Hung-Shin Lee,Pin-Yuan Chen,Yu Tsao,Hsin-Min Wang
机构*：Institute of Information Science, Academia Sinica, Research Center for Information Technology Innovation, Academia Sinica
备注：submitted to Interspeech 2022
链接：点击下载PDF文件

【7】 The TerraByte Client: providing access to terabytes of plant data
标题：千兆字节客户端：提供对千兆字节工厂数据的访问
作者：Michael A. Beck,Christopher P. Bidinosti,Christopher J. Henry,Manisha Ajmani
机构*：University of Winnipeg, Winnipeg, MB Canada
链接：点击下载PDF文件

【8】 Chain-based Discriminative Autoencoders for Speech Recognition
标题：用于语音识别的基于链的区分式自动编码器
作者：Hung-Shin Lee,Pin-Tuan Huang,Yao-Fei Cheng,Hsin-Min Wang
机构*：Institute of Information Science, Academia Sinica, Taiwan
备注：submitted to Interspeech 2022
链接：点击下载PDF文件

【9】 Learning to Mediate Disparities Towards Pragmatic Communication
标题：学会调和差异走向语用交际
作者：Yuwei Bao,Sayan Ghosh,Joyce Chai
机构*：Computer Science and Engineering, University of Michigan, §ASAPP
备注：9 pages. Accepted to ACL 2022
链接：点击下载PDF文件

【10】 LQoCo: Learning to Optimize Cache Capacity Overloading in Storage Systems
标题：LQOCO：学习优化存储系统中的缓存容量过载
作者：Ji Zhang,Xijun Li,Xiyao Zhou,Mingxuan Yuan,Zhuo Cheng,Keji HuangYifan Li
机构*：Huawei Data Storage and Machine Vision Product Line,Huawei Noah’s Ark Lab,MIRA Lab, USTC
备注：This paper has been accepted by DAC 2022. Xijun is the correspoonding author
链接：点击下载PDF文件

【11】 Repairing Group-Level Errors for DNNs Using Weighted Regularization
标题：用加权正则化方法修复DNN的组级错误
作者：Ziyuan Zhong,Yuchi Tian,Conor J. Sweeney,Vicente Ordonez-Roman,Baishakhi Ray
机构*：CONOR J.SWEENEY, Columbia University, USA
链接：点击下载PDF文件

【12】 Formal Semantics and Formally Verified Validation for Temporal Planning
标题：时间规划的形式化语义和形式化验证
作者：Mohammad Abdulaziz,Lukas Koller
机构*：Techniche Universitt München, Germany, King’s College London, United Kingdom
链接：点击下载PDF文件

【13】 Learning Relational Rules from Rewards
标题：从奖励中学习关系规则
作者：Guillermo Puebla,Leonidas A. A. Doumas
机构*：School of Philosophy, Psychology, and Language Sciences, The University of Edinburgh, School of Psychological Science, University of Bristol
链接：点击下载PDF文件

【14】 Fast Hybrid Image Retargeting
标题：快速混合图像重定向
作者：Daniel Valdez-Balderas,Oleg Muraveynyk,Timothy Smith
机构*：Samsung R&D Institute, Staines-upon-Thames, TW,QE, U. K.
Journal-ref：2021 IEEE International Conference on Image Processing (ICIP), 2021, pp. 1849-1853
链接：点击下载PDF文件

【15】 Unsupervised Learning of Temporal Abstractions with Slot-based Transformers
标题：基于槽变换的时间抽象的无监督学习
作者：Anand Gopalakrishnan,Kazuki Irie,Jürgen Schmidhuber,Sjoerd van Steenkiste
机构*：The Swiss AI Lab, IDSIA, University of Lugano (USI) & SUPSI, Lugano, Switzerland, King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia, Google Research
备注：26 pages, 8 figures
链接：点击下载PDF文件

【16】 Personalize Web Searching Strategies Classification and Comparison
标题：个性化网络搜索策略分类与比较
作者：Mariya Evtimova-Gardair,Ivan Momtchev
机构*：Technical University of Sofia
Journal-ref：Journal of Communication and Computer, David Publishing, ISSN: 1548-7709 (Print), 1930-1553 (Online), 2016, p.19-23
链接：点击下载PDF文件

【17】 EnHDC: Ensemble Learning for Brain-Inspired Hyperdimensional Computing
标题：EnHDC：用于脑启发超维计算的集成学习
作者：Ruixuan Wang,Dongning Ma,Xun Jiao
机构*：Villanova University, Villanova, PA
链接：点击下载PDF文件

【18】 Facial Expression Recognition with Swin Transformer
标题：基于Swin Transform的人脸表情识别
作者：Jun-Hwa Kim,Namho Kim,Chee Sun Won
机构*：Department of Electronics and Electrical Engineering, Dongguk University, seoul, Korea
链接：点击下载PDF文件

【19】 From MIM-Based GAN to Anomaly Detection:Event Probability Influence on Generative Adversarial Networks
标题：从基于MIM的GAN到异常检测：事件概率对产生式对抗网络的影响
作者：Rui She,Pingyi Fan
机构*： Tsinghua University
链接：点击下载PDF文件

【20】 Semi-supervised and Deep learning Frameworks for Video Classification and Key-frame Identification
标题：用于视频分类和关键帧识别的半监督深度学习框架
作者：Sohini Roychowdhury
机构*：Adjunct Faculty, Computer Engineering
备注：9 pages, 7 images, 3 tables
链接：点击下载PDF文件

【21】 A Comparative Evaluation of Machine Learning Algorithms for the Prediction of RC Buildings' Seismic Damage
标题：钢筋混凝土建筑物震害预测的机器学习算法比较评价
作者：Konstantinos Demertzis,Konstantinos Kostinakis,Konstantinos Morfidis,Lazaros Iliadis
机构*：School of Science & Technology, Informatics Studies, Hellenic Open University, Greece, School of Engineering, Department of Civil Engineering, and General Courses, Democritus University of Thrace, Kimmeria, Xanthi, Greece
链接：点击下载PDF文件

【22】 Component-wise Analysis of Automatically Designed Multiobjective Algorithms on Constrained Problems
标题：约束问题自动设计多目标算法的构件化分析
作者：Yuri Lavinas,Gabriela Ochoa,Claus Aranha
机构*：University of Tsukuba, Japan, University of Stirling, UK
链接：点击下载PDF文件

【23】 Risk-Aware Off-Road Navigation via a Learned Speed Distribution Map
标题：通过学习的速度分布图实现风险感知越野导航
作者：Xiaoyi Cai,Michael Everett,Jonathan Fink,Jonathan P. How
机构*： Massachusetts Institute of Tech-nology
备注：7 pages and 9 figures
链接：点击下载PDF文件

【24】 Dealing with Sparse Rewards Using Graph Neural Networks
标题：用图神经网络处理稀疏奖励问题
作者：Matvey Gerasyov,Ilya Makarov
机构*：National Research University Higher School of Economics, Moscow, Russia
链接：点击下载PDF文件

【25】 Automatic Song Translation for Tonal Languages
标题：声调语言歌曲的自动翻译
作者：Fenfei Guo,Chen Zhang,Zhirui Zhang,Qixin He,Kejun Zhang,Jun Xie,Jordan Boyd-Graber
机构*：University of Maryland, Zhejiang University, Tencent AI Lab, Purdue University, Alibaba DAMO Academy, CS, iSchool, UMIACS, LSC
备注：Accepted at Findings of ACL 2022, 15 pages, 4 Tables and 10 Figures
链接：点击下载PDF文件

【26】 Reshaping Robot Trajectories Using Natural Language Commands: A Study of Multi-Modal Data Alignment Using Transformers
标题：使用自然语言命令重塑机器人轨迹：使用Transformer的多模态数据对齐研究
作者：Arthur Bucker,Luis Figueredo,Sami Haddadin,Ashish Kapoor,Shuang Ma,Rogerio Bonatti
机构*：Technische Universit¨at M¨unchen,Microsoft
链接：点击下载PDF文件

【27】 Automated Algorithm Selection: from Feature-Based to Feature-Free Approaches
标题：自动算法选择：从基于特征的方法到无征方法
作者：Mohamad Alissa,Kevin Sim,Emma Hart
机构*：Hart, Received: date Accepted: date
备注：pre-print paper
链接：点击下载PDF文件

【28】 Probing Representation Forgetting in Supervised and Unsupervised Continual Learning
标题：有监督和无监督持续学习中的表征遗忘探究
作者：MohammadReza Davari,Nader Asadi,Sudhir Mudur,Rahaf Aljundi,Eugene Belilovsky
机构*： Concordia University , Mila – Quebec AI Institute, Toyota Research Insititute
备注：Accepted at CVPR 2022
链接：点击下载PDF文件

【29】 Gender and Racial Stereotype Detection in Legal Opinion Word Embeddings
标题：法律意见词嵌入中的性别和种族刻板印象检测
作者：Sean Matthews,John Hudzina,Dawn Sepehr
机构*： Thomson Reuters Labs, Eagan, Minnesota, USA, Thomson Reuters Labs, Toronto, Canada
备注：Accepted at AAAI-22, AI for Social Impact Track
链接：点击下载PDF文件

【30】 Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)
标题：推荐作为语言处理(RLP)：统一的预训练、个性化提示和预测范式(P5)
作者：Shijie Geng,Shuchang Liu,Zuohui Fu,Yingqiang Ge,Yongfeng Zhang
机构*：Department of Computer Science, Rutgers University, NJ , US
链接：点击下载PDF文件

【31】 Predicting Personas Using Mechanic Frequencies and Game State Traces
标题：使用机械频率和游戏状态轨迹预测人物角色
作者：Michael Cerny Green,Ahmed Khalifa,M Charity,Debosmita Bhaumik,Julian Togelius
机构*：Game Innovation Lab, New York University, Tandon, New York City, USA, Institute of Digital Games, University of Malta, Msida, Malta
备注：9 pages, 3 tables, 2 figures
链接：点击下载PDF文件

【32】 Occluded Human Mesh Recovery
标题：被遮挡的人体网格恢复
作者：Rawal Khirodkar,Shashank Tripathi,Kris Kitani
机构*：Carnegie Mellon University, Max Planck Institute for Intelligent Systems
链接：点击下载PDF文件

【33】 Linking Emergent and Natural Languages via Corpus Transfer
标题：通过语料库迁移将新兴语言与自然语言联系起来
作者：Shunyu Yao,Mo Yu,Yang Zhang,Karthik R Narasimhan,Joshua B. Tenenbaum,Chuang Gan
机构*：Princeton University, WeChat AI, MIT-IBM Watson AI Lab, Karthik Narasimhan
备注：ICLR 2022 Spotlight. Github repo: this https URL
链接：点击下载PDF文件

【34】 Addressing Client Drift in Federated Continual Learning with Adaptive Optimization
标题：用自适应优化解决联合持续学习中的客户漂移
作者：Yeshwanth Venkatesha,Youngeun Kim,Hyoungseob Park,Yuhang Li,Priyadarshini Panda
机构*：Yale University, New Haven CT , USA
链接：点击下载PDF文件

【35】 Remember and Forget Experience Replay for Multi-Agent Reinforcement Learning
标题：多智能体强化学习的记忆与遗忘经验回放
作者：Pascal Weber,Daniel Wlchli,Mustafa Zeqiri,Petros Koumoutsakos
机构*：Paulson School of Engineering and Applied Sciences, HarvardUniversity
链接：点击下载PDF文件

【36】 MonoDETR: Depth-aware Transformer for Monocular 3D Object Detection
标题：MonoDETR：用于单目三维目标检测的深度感知转换器
作者：Renrui Zhang,Han Qiu,Tai Wang,Xuanzhuo Xu,Ziyu Guo,Yu Qiao,Peng Gao,Hongsheng Li
机构*：Shanghai AI Laboratory, Peking University, The Chinese University of Hong Kong
备注：10 pages, 5 figures, submitted to CVPR 2022
链接：点击下载PDF文件

【37】 Tackling Online One-Class Incremental Learning by Removing Negative Contrasts
标题：通过消除负面对比来应对在线一节课增量学习
作者：Nader Asadi,Sudhir Mudur,Eugene Belilovsky
机构*：Concordia University and Mila
备注：Accepted at NeurIPS 2021 Workshop on Distribution Shifts
链接：点击下载PDF文件

【38】 Precipitaion Nowcasting using Deep Neural Network
标题：基于深度神经网络的降水短时预报
作者：Mohamed Chafik Bakkay,Mathieu Serrurier,Valentin Kivachuk Burda,Florian Dupuy,Naty Citlali Cabrera-Gutierrez,Michael Zamo,Maud-Alix Mader,Olivier Mestre,Guillaume Oller,Jean-Christophe Jouhaud,Laurent Terray
链接：点击下载PDF文件

【39】 Interpretability of Neural Network With Physiological Mechanisms
标题：神经网络的生理机制可解释性
作者：Anna Zou,Zhiyuan Li
机构*：Department of Psychology, University of Florida, Department of Electrical Engineering and Computer Science, University of Cincinnati, Imaging Research Center, Cincinnati Children’s Hospital Medical Center
链接：点击下载PDF文件

【40】 BDDM: Bilateral Denoising Diffusion Models for Fast and High-Quality Speech Synthesis
标题：BDDM：快速高质量语音合成的双边去噪扩散模型
作者：Max W. Y. Lam,Jun Wang,Dan Su,Dong Yu
机构*：Tencent AI Lab, Shenzhen, China, Bellevue WA, USA
Journal-ref：International Conference on Learning Representations 2022
链接：点击下载PDF文件

【41】 Computing Optimal Location of Microphone for Improved Speech Recognition
标题：用于改进语音识别的麦克风最佳位置计算
作者：Karan Nathwani,Bhavya Dixit,Sunil Kumar Kopparapu
机构*：Department of Electrical Engg, IIT Jammu, India, TCS Research, Tata Consultancy Services Limited, India
备注：5 pages
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。