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45篇

【1】 Fixing Malfunctional Objects With Learned Physical Simulation and Functional Prediction
标题：使用学习的物理模拟和功能预测修复故障对象
作者：Yining Hong,Kaichun Mo,Li Yi,Leonidas J. Guibas,Antonio Torralba,Joshua B. Tenenbaum,Chuang Gan
机构*：UCLA, Stanford University, Tsinghua University, MIT BCS, CBMM, CSAIL, MIT-IBM Watson AI Lab, Malfunctional, Shape, Video, Possible Fix, Physical, Simulation
备注：CVPR 2022. Project page: this http URL
链接：点击下载PDF文件

【2】 Cross-view Transformers for real-time Map-view Semantic Segmentation
标题：用于实时地图-视图语义分割的交叉视图转换器
作者：Brady Zhou,Philipp Krhenbühl
机构*：UT Austin, Philipp Kr¨ahenb¨uhl
备注：CVPR 2022 Oral. Code at this https URL
链接：点击下载PDF文件

【3】 Rapid Locomotion via Reinforcement Learning
标题：基于强化学习的快速移动
作者：Gabriel B Margolis,Ge Yang,Kartik Paigwar,Tao Chen,Pulkit Agrawal
机构*：MIT Improbable AI Lab, NSF AI Institute for Artificial Intelligence and Fundamental Interactions, Massachusetts Institute of Technology, Cambridge, MA
备注：Accepted for publication at Robotics: Science and Systems (RSS) 2022
链接：点击下载PDF文件

【4】 Development of Interpretable Machine Learning Models to Detect Arrhythmia based on ECG Data
标题：基于心电数据检测心律失常的可解释机器学习模型的开发
作者：Shourya Verma
机构*：Master in Scientific Computing, Interdisciplinary Center for Scientific Computing (IWR), Universitt Heidelberg, Heidelberg, Germany
链接：点击下载PDF文件

【5】 Diversifying Neural Dialogue Generation via Negative Distillation
标题：通过负蒸馏使神经对话产生多样化
作者：Yiwei Li,Shaoxiong Feng,Bin Sun,Kan Li
机构*：School of Computer Science, Beijing Institute of Technology
备注：Accepted by NAACL 2022 main conference
链接：点击下载PDF文件

【6】 Spiking Graph Convolutional Networks
标题：尖峰图卷积网络
作者：Zulun Zhu,Jiaying Peng,Jintang Li,Liang Chen,Qi Yu,Siqiang Luo
机构*：Sun Yat-Sen University,Rochester Institute of Technology,Nanyang Technological University
备注：Accepted by IJCAI 2022; Code available at this https URL
链接：点击下载PDF文件

【7】 Edge-enabled Metaverse: The Convergence of Metaverse and Mobile Edge Computing
标题：边缘启用的Metverse：Metverse和移动边缘计算的融合
作者：Sahraoui Dhelim,Tahar Kechadi,Liming Chen,Nyothiri Aung,Huansheng Ning,Luigi Atzori
机构*：Liming Chen is with the School of Computing, Ulster University, Luigi Atzori is with the Department of Electrical and Electronic Engineer-ing, University of Cagliari, ItalyHuansheng Ning is with the School of Computer and CommunicationEngineering
备注：Submitted to IEEE IoTJ
链接：点击下载PDF文件

【8】 Automating Reasoning with Standpoint Logic via Nested Sequents
标题：基于嵌套序列的立场逻辑自动推理
作者：Tim S. Lyon,Lucía Gómez lvarez
机构*：Computational Logic Group, TU Dresden
备注：Accepted to KR 2022: this https URL
链接：点击下载PDF文件

【9】 Rethinking Classifier And Adversarial Attack
标题：对量词与对抗性攻击的再思考
作者：Youhuan Yang,Lei Sun,Leyu Dai,Song Guo,Xiuqing Mao,Xiaoqin Wang,Bayi Xu
机构*： School of Cyber Science and Engineering, Zhengzhou University, Zhengzhou , China, Information Engineering University, Zhengzhou , China
链接：点击下载PDF文件

【10】 Based-CE white-box adversarial attack will not work using super-fitting
标题：基于CE的白盒对抗性攻击将不会使用超级拟合
作者：Youhuan Yang,Lei Sun,Leyu Dai,Song Guo,Xiuqing Mao,Xiaoqin Wang,Bayi Xu
机构*： School of Cyber Science and Engineering, Zhengzhou University, Zhengzhou , China, Information Engineering University, Zhengzhou , China
链接：点击下载PDF文件

【11】 Communication-Efficient Adaptive Federated Learning
标题：通信高效的自适应联邦学习
作者：Yujia Wang,Lu Lin,Jinghui Chen
机构*： Pennsylvania State University; E-mail, Department of Computer Science, University of Virginia; E-mail
备注：49 pages, 7 figures
链接：点击下载PDF文件

【12】 Hybrid CNN Based Attention with Category Prior for User Image Behavior Modeling
标题：基于注意力和类别先验的混合CNN用户形象行为建模
作者：Xin Chen,Qingtao Tang,Ke Hu,Yue Xu,Shihang Qiu,Jia Cheng,Jun Lei
机构*：Meituan, China
备注：Accepted by SIGIR 2022
链接：点击下载PDF文件

【13】 Do Different Deep Metric Learning Losses Lead to Similar Learned Features?
标题：不同的深度度量学习损失是否会导致相似的学习特征？
作者：Konstantin Kobs,Michael Steininger,Andrzej Dulny,Andreas Hotho
机构*：University of W¨urzburg, Germany
备注：Published at ICCV 2021
链接：点击下载PDF文件

【14】 On Disentangled and Locally Fair Representations
标题：关于解缠与局部公平表示
作者：Yaron Gurovich,Sagie Benaim,Lior Wolf
机构*：School of Computer Science, Tel Aviv University
链接：点击下载PDF文件

【15】 What is Right for Me is Not Yet Right for You: A Dataset for Grounding Relative Directions via Multi-Task Learning
标题：适合我的还不适合你：通过多任务学习确定相对方向的数据集
作者：Jae Hee Lee,Matthias Kerzel,Kyra Ahrens,Cornelius Weber,Stefan Wermter
机构*：University of Hamburg
备注：Accepted to IJCAI 2022
链接：点击下载PDF文件

【16】 Region-Based Merging of Open-Domain Terminological Knowledge
标题：基于区域的开放领域术语知识融合
作者：Zied Bouraoui,Sebastien Konieczny,Thanh Ma,Nicolas Schwind,Ivan Varzinczak
机构*：CRIL, Univ. Artois & CNRS, France, National Institute of Advanced Industrial Science and Technology, Tokyo, Japan
备注：10 pages, 19th International Conference on Principles of Knowledge Representation and Reasoning, KR'22
链接：点击下载PDF文件

【17】 Polynomial-Time Algorithms for Counting and Sampling Markov Equivalent DAGs with Applications
标题：计算和采样马尔可夫等价DAG的多项式时间算法及其应用
作者：Marcel Wienbst,Max Bannach,Maciej Likiewicz
机构*：Institute for Theoretical Computer Science, University of L¨ubeck, L¨ubeck, Germany, Maciej Liskiewicz
备注：Preliminary results of this work have been presented at the AAAI Conference on Artificial Intelligence (AAAI 2021), see arXiv:2012.09679
链接：点击下载PDF文件

【18】 GANimator: Neural Motion Synthesis from a Single Sequence
标题：GANIMATOR：从单一序列合成神经运动
作者：Peizhuo Li,Kfir Aberman,Zihan Zhang,Rana Hanocka,Olga Sorkine-Hornung
机构*： The University of Chicago, The University ofChicago
备注：SIGGRAPH 2022. Project page: this https URL , Video: this https URL
链接：点击下载PDF文件

【19】 Contrastive Multi-view Hyperbolic Hierarchical Clustering
标题：对比多视点双曲线层次聚类
作者：Fangfei Lin,Bing Bai,Kun Bai,Yazhou Ren,Peng Zhao,Zenglin Xu
机构*：University of Electronic Science and Technology of China, Chengdu, China, Tencent Security Big Data Lab, Tencent Inc., China, Harbin Institute of Technology, Shenzhen, China, Department of Network Intelligence, Peng Cheng National Lab, Shenzhen, China
备注：This work was accepted by IJCAI2022
链接：点击下载PDF文件

【20】 Natural Language Inference with Self-Attention for Veracity Assessment of Pandemic Claims
标题：带有自我注意的自然语言推理用于评估大流行宣传的真实性
作者：M. Arana-Catania,Elena Kochkina,Arkaitz Zubiaga,Maria Liakata,Rob Procter,Yulan He
机构*：Department of Computer Science, University of Warwick, UK, The Alan Turing Institute, UK, Queen-Mary University of London, UK
备注：16 pages, 1 figure, 8 tables, presented in NAACL 2022
链接：点击下载PDF文件

【21】 A Temporal-Pattern Backdoor Attack to Deep Reinforcement Learning
标题：一种针对深度强化学习的时间模式后门攻击
作者：Yinbo Yu,Jiajia Liu,Shouqing Li,Kepu Huang,Xudong Feng
机构*：School of Cybersecurity, Northwestern Polytechnical University, Xi’an , China, Research & Development Institute of Northwestern Polytechnical University in Shenzhen, Shenzhen , China
链接：点击下载PDF文件

【22】 One Size Does Not Fit All: The Case for Personalised Word Complexity Models
标题：一刀切并不适合所有人：个性化单词复杂性模型的情况
作者：Sian Gooding,Manuel Tragut
机构*：University of Cambridge, Google
链接：点击下载PDF文件

【23】 Monitoring AI systems: A Problem Analysis, Framework and Outlook
标题：人工智能监控系统：问题分析、框架与展望
作者：Annet Onnes
机构*：Information and Computing Sciences, Utrecht University, The Netherlands
链接：点击下载PDF文件

【24】 M2R2: Missing-Modality Robust emotion Recognition framework with iterative data augmentation
标题：M2R2：基于迭代数据增强的缺失型情感识别框架
作者：Ning Wang
机构*： Missing-Modality Robust emotion Recognition framework with iterativedata augmentationWang NingXi’an Jiaotong University
链接：点击下载PDF文件

【25】 FastRE: Towards Fast Relation Extraction with Convolutional Encoder and Improve Cascade Binary Tagging Framework
标题：FASTER：采用卷积编码和改进的级联二进制标记框架实现快速关系提取
作者：Guozheng Li,Xu Chen,Peng Wang,Jiafeng Xie,Qiqing Luo
机构*：School of Computer Science and Engineering, Southeast University, School of Cyber Science and Engineering, Southeast University, School of Artificial Intelligence, Southeast University, Tencent Inc.
备注：Accepted to IJCAI-ECAI 2022
链接：点击下载PDF文件

【26】 Alignahead: Online Cross-Layer Knowledge Extraction on Graph Neural Networks
标题：Alignhead：基于图神经网络的在线跨层知识抽取
作者：Jiongyu Guo,Defang Chen,Can Wang
机构*：Zhejiang University, ZJU-Bangsun Joint Research Center, Shanghai Institute for Advanced Study of Zhejiang University
备注：Accepted to IJCNN-2022
链接：点击下载PDF文件

【27】 Declaration-based Prompt Tuning for Visual Question Answering
标题：基于声明的视觉问答提示调优
作者：Yuhang Liu,Wei Wei,Daowan Peng,Feida Zhu
机构*：Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, School of Computer, Science and Technology, Huazhong University of Science and Technology, China, Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL), China
备注：Accepted to IJCAI2022, data and codes are available at this https URL
链接：点击下载PDF文件

【28】 COGMEN: COntextualized GNN based Multimodal Emotion recognitioN
标题：COGMEN：基于上下文GNN的多通道情感识别
作者：Abhinav Joshi,Ashwani Bhat,Ayush Jain,Atin Vikram Singh,Ashutosh Modi
机构*：Indian Institute of Technology Kanpur (IIT-K)
备注：17 pages (9 main + 8 appendix). Accepted at NAACL 2022
链接：点击下载PDF文件

【29】 Multi-Graph based Multi-Scenario Recommendation in Large-scale Online Video Services
标题：大规模在线视频服务中基于多图的多场景推荐
作者：Fan Zhang,Qiuying Peng,Yulin Wu,Zheng Pan,Rong Zeng,Da Lin,Yue Qi
机构*：OPPO Research Institute, Shenzhen, China, OPPO AI&Data Engineering System, Beijing, China, Bytedance Ltd.
备注：Accepted to WWW 2022 Graph Learning workshop
链接：点击下载PDF文件

【30】 Text to artistic image generation
标题：从文本到艺术图像的生成
作者：Qinghe Tian,Jean-Claude Franchitti
机构*：University of Waterloo, New York University Courant Institute
备注：7 pages, 8 figures
链接：点击下载PDF文件

【31】 FAITH: Few-Shot Graph Classification with Hierarchical Task Graphs
标题：信念：基于层次任务图的Few-Shot图分类
作者：Song Wang,Yushun Dong,Xiao Huang,Chen Chen,Jundong Li
机构*：University of Virginia, Hong Kong Polytechnic University
备注：IJCAI-ECAI 2022
链接：点击下载PDF文件

【32】 Dangling-Aware Entity Alignment with Mixed High-Order Proximities
标题：基于混合高阶近似值的悬挂式实体对齐
作者：Juncheng Liu,Zequn Sun,Bryan Hooi,Yiwei Wang,Dayiheng Liu,Baosong Yang,Xiaokui Xiao,Muhao Chen
机构*：National University of Singapore, Nanjing University, Alibaba Group, University of Southern California
备注：NAACL 2022 (Findings)
链接：点击下载PDF文件

【33】 Spot-adaptive Knowledge Distillation
标题：现场自适应知识蒸馏
作者：Jie Song,Ying Chen,Jingwen Ye,Mingli Song
Journal-ref：IEEE Transactions on Image Processing, 2022
链接：点击下载PDF文件

【34】 Robust Conversational Agents against Imperceptible Toxicity Triggers
标题：强大的对话代理，可抵御潜伏的毒性触发
作者：Ninareh Mehrabi,Ahmad Beirami,Fred Morstatter,Aram Galstyan
机构*：University of Southern California - Information Sciences Institute, Meta AI
链接：点击下载PDF文件

【35】 Interactive Grounded Language Understanding in a Collaborative Environment: IGLU 2021
标题：协作环境下的交互式扎根语言理解：IGLU 2021
作者：Julia Kiseleva,Ziming Li,Mohammad Aliannejadi,Shrestha Mohanty,Maartje ter Hoeve,Mikhail Burtsev,Alexey Skrynnik,Artem Zholus,Aleksandr Panov,Kavya Srinet,Arthur Szlam,Yuxuan Sun,Marc-Alexandre Cté Katja Hofmann,Ahmed Awadallah,Linar Abdrazakov,Igor Churin,Putra Manggala,Kata Naszadi,Michiel van der Meer,Taewoon Kim
机构*：Kim, Microsoft Research, University of Amsterdam, Alexa AI, MIPT, AIRI, Facebook AI, Moscow Institute of Physics and Technology, Kalashnikov Izhevsk State Technical University, Universiteit Leiden, Vrije Universiteit Amsterdam
Journal-ref：Proceedings of Machine Learning Research NeurIPS 2021 Competition and Demonstration Track
链接：点击下载PDF文件

【36】 Response Component Analysis for Sea State Estimation Using Artificial Neural Networks and Vessel Response Spectral Data
标题：利用人工神经网络和舰船反应谱数据进行海况估计的响应分量分析
作者：Nathan K. Long,Daniel Sgarioto,Matthew Garratt,Karl Sammut
机构*：University of New South Wales, Campbell ACT, Australia, Defence Science and Technology Group, Fishermans Bend VIC, Australia, Defence Science and Technology Group, Edinburgh SA, Australia, Flinders University, Tonsley SA, Australia
备注：Preprint under review
链接：点击下载PDF文件

【37】 PREME: Preference-based Meeting Exploration through an Interactive Questionnaire
标题：Preme：通过互动问卷进行基于偏好的会议探索
作者：Negar Arabzadeh,Ali Ahmadvand,Julia Kiseleva,Yang Liu,Ahmed Hassan Awadallah,Ming Zhong,Milad Shokouhi
机构*： University of Waterloo, Emory University, Microsoft Research, University of Illinois
链接：点击下载PDF文件

【38】 Time-multiplexed Neural Holography: A flexible framework for holographic near-eye displays with fast heavily-quantized spatial light modulators
标题：时分复用神经全息术：一种采用快速重量化空间光调制器的全息近眼显示的灵活框架
作者：Suyeon Choi,Manu Gopakumar,Yifan,Peng,Jonghyun Kim,Matthew O'Toole,Gordon Wetzstein
机构*：MATTHEW O’TOOLE, Carnegie Mellon University, USA, RGBD Supervision, Choi et al., frame, Ours, frames, Focal Stack Supervision, Light Field Supervision, OLAS, Padmanaban et al .
备注：Project page with more details: this http URL
链接：点击下载PDF文件

【39】 GitRank: A Framework to Rank GitHub Repositories
标题：GitRank：一个对GitHub知识库进行排名的框架
作者：Nianjan Hasabnis
机构*：Intel Labs, Santa Clara, California, USA
备注：3 pages, 1 figure; to be published in Mining Software Repositories 2022 conference (hackathon)
链接：点击下载PDF文件

【40】 Convolutional and Residual Networks Provably Contain Lottery Tickets
标题：卷积网络和剩余网络可证明包含彩票
作者：Rebekka Burkholz
链接：点击下载PDF文件

【41】 Exploring the Benefits of Teams in Multiagent Learning
标题：探索团队在多智能体学习中的优势
作者：David Radke,Kate Larson,Tim Brecht
机构*：David R. Cheriton School of Computer Science, University of Waterloo
备注：7 pages, 5 figures, Published at IJCAI 2022. arXiv admin note: text overlap with arXiv:2204.07471
链接：点击下载PDF文件

【42】 Most Activation Functions Can Win the Lottery Without Excessive Depth
标题：大多数激活功能可以在没有过多深度的情况下赢得彩票
作者：Rebekka Burkholz
链接：点击下载PDF文件

【43】 Zero Day Threat Detection Using Graph and Flow Based Security Telemetry
标题：基于图和流的安全遥测零日威胁检测
作者：Christopher Redino,Dhruv Nandakumar,Robert Schiller,Kevin Choi,Abdul Rahman,Edward Bowen,Matthew Weeks,Aaron Shaha,Joe Nehila
备注：11 pages, 6 figures, submitting to NeurIPS 2022
链接：点击下载PDF文件

【44】 Original or Translated? A Causal Analysis of the Impact of Translationese on Machine Translation Performance
标题：原创的还是翻译的？翻译用法对机器翻译性能影响的因果分析
作者：Jingwei Ni,Zhijing Jin,Markus Freitag,Mrinmaya Sachan,Bernhard Schlkopf
机构*：University College London, MPI & ETH Zürich, Google Research
备注：NAACL 2022
链接：点击下载PDF文件

【45】 Minimum Cost Intervention Design for Causal Effect Identification
标题：因果关系识别的最小成本干预设计
作者：Sina Akbari,Jalal Etesami,Negar Kiyavash
备注：31 pages, 10 figures, ICML2022
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。