历史文章列表 网站https://www.arxivdaily.com/
注：含中英文摘要速递见公众号【arXiv每日学术速递】,涵盖CS|物理|数学|经济|统计|金融|生物|电气等领域。

cs.AI人工智能，共计86篇

【1】 Predictive Querying for Autoregressive Neural Sequence Models
标题：自回归神经序列模型的预测查询
链接：https://arxiv.org/abs/2210.06464
作者：Alex Boyd,Sam Showalter,Stephan Mandt,Padhraic Smyth
机构：Department of Statistics, Department of Computer Science, University of California, Irvine
备注：Presented at the Conference on Neural Information Processing Systems (NeurIPs 2022)

【2】 Holo-Dex: Teaching Dexterity with Immersive Mixed Reality
标题：Holo-Dex：用身临其境的混合现实教授灵巧
链接：https://arxiv.org/abs/2210.06463
作者：Sridhar Pandian Arunachalam,Irmak Güzey,Soumith Chintala,Lerrel Pinto
机构：New York University, Irmak G¨uzey, Meta AI
备注：Data, code and videos are available at this https URL

【3】 Self-Guided Diffusion Models
标题：自导扩散模型
链接：https://arxiv.org/abs/2210.06462
作者：Vincent Tao Hu,David W Zhang,Yuki M. Asano,Gertjan J. Burghouts,Cees G. M. Snoek
机构：David W. Zhang, University of Amsterdam, TNO

【4】 Better Smatch = Better Parser? AMR evaluation is not so simple anymore
标题：更好的匹配=更好的解析器？AMR评估不再那么简单了
链接：https://arxiv.org/abs/2210.06461
作者：Juri Opitz,Anette Frank
机构：Dept. of Computational Linguistics, Heidelberg University, Heidelberg
备注：accepted at "Evaluation and Comparison of NLP Systems" Workshop (Eval4NLP 2022)

【5】 Efficient Knowledge Distillation from Model Checkpoints
标题：从模型检查点进行高效的知识提取
链接：https://arxiv.org/abs/2210.06458
作者：Chaofei Wang,Qisen Yang,Rui Huang,Shiji Song,Gao Huang
机构：Department of Automation, Tsinghua University, China
备注：Accepted by NeurIPS2022

【6】 Token-Label Alignment for Vision Transformers
标题：视觉变形器的令牌标签对准
链接：https://arxiv.org/abs/2210.06455
作者：Han Xiao,Wenzhao Zheng,Zheng Zhu,Jie Zhou,Jiwen Lu
机构：Beijing National Research Center for Information Science and Technology, China, Department of Automation, Tsinghua University, China, PhiGent Robotics
备注：Source code available at this https URL

【7】 On the Effectiveness of Lipschitz-Driven Rehearsal in Continual Learning
标题：利普希茨驱动排练在继续学习中的有效性研究
链接：https://arxiv.org/abs/2210.06443
作者：Lorenzo Bonicelli,Matteo Boschini,Angelo Porrello,Concetto Spampinato,Simone Calderara
机构：Concetto Smampinato, AImageLab - University of Modena and Reggio Emilia, PeRCeiVe Lab - University of Catania
备注：22 pages, 8 figures. Accepted at the thirty-sixth Conference on Neural Information Processing Systems (NeurIPS 2022), New Orleans, US

【8】 Self-supervised video pretraining yields strong image representations
标题：自监督视频预训练产生强大的图像表示
链接：https://arxiv.org/abs/2210.06433
作者：Nikhil Parthasarathy,S. M. Ali Eslami,Joo Carreira,Olivier J. Hénaff
机构：DeepMind, NYU Center for Neural Science, London, UK, New York, NY
备注：Technical report

【9】 Relational Graph Convolutional Neural Networks for Multihop Reasoning: A Comparative Study
标题：用于多跳推理的关系图卷积神经网络的比较研究
链接：https://arxiv.org/abs/2210.06418
作者：Ieva Staliūnait,Philip John Gorinski,Ignacio Iacobacci
机构： Department of Computer Science and Technology, University of Cambridge, Huawei Noah’s Ark Lab, London
备注：8 pages + 2 pages references, 3 figures, 3 tables

【10】 A Unified Framework with Meta-dropout for Few-shot Learning
标题：一种支持元丢弃的少发式学习统一框架
链接：https://arxiv.org/abs/2210.06409
作者：Shaobo Lin,Xingyu Zeng,Rui Zhao
机构：Sensetime Research

【11】 PriMeSRL-Eval: A Practical Quality Metric for Semantic Role Labeling Systems Evaluation
标题：PriMeSRL-EVAL：一种用于语义角色标注系统评估的实用质量度量
链接：https://arxiv.org/abs/2210.06408
作者：Ishan Jindal,Alexandre Rademaker,Khoi-Nguyen Tran,Huaiyu Zhu,Hiroshi Kanayama,Marina Danilevsky,Yunyao Li
机构：IBM Research, bApple

【12】 Interactive Language: Talking to Robots in Real Time
标题：交互式语言：与机器人实时对话
链接：https://arxiv.org/abs/2210.06407
作者：Corey Lynch,Ayzaan Wahid,Jonathan Tompson,Tianli Ding,James Betker,Robert Baruch,Travis Armstrong,Pete Florence
机构：Robotics at Google

【13】 What Makes Graph Neural Networks Miscalibrated?
标题：是什么导致了图形神经网络的错误校准？
链接：https://arxiv.org/abs/2210.06391
作者：Hans Hao-Hsun Hsu,Yuesong Shen,Christian Tomani,Daniel Cremers
机构： Technical University of Munich, Germany, Munich Center for Machine Learning, Germany
备注：Accepted to NeurIPS 2022

【14】 Multi-Level Firing with Spiking DS-ResNet: Enabling Better and Deeper Directly-Trained Spiking Neural Networks
标题：使用尖峰DS-ResNet的多级触发：实现更好和更深入的直接训练的尖峰神经网络
链接：https://arxiv.org/abs/2210.06386
作者：Lang Feng,Qianhui Liu,Huajin Tang,De Ma,Gang Pan
机构：College of Computer Science and Technology, Zhejiang University, Hangzhou, China, Zhejiang Lab, Hangzhou, China

【15】 Near-Optimal Multi-Agent Learning for Safe Coverage Control
标题：用于安全覆盖控制的近优多智能体学习
链接：https://arxiv.org/abs/2210.06380
作者：Manish Prajapat,Matteo Turchetta,Melanie N. Zeilinger,Andreas Krause
机构：ETH Zurich
备注：Accepted at NeurIPS 2022

【16】 Probing Commonsense Knowledge in Pre-trained Language Models with Sense-level Precision and Expanded Vocabulary
标题：利用语义级精确度和扩展词汇量在预训练语言模型中探索常识知识
链接：https://arxiv.org/abs/2210.06376
作者：Daniel Loureiro,Alípio Mário Jorge
机构： Cardiff NLP, School of Computer Science and Informatics, Cardiff University, UK, LIAAD - INESC TEC, University of Porto, Portugal

【17】 Individualized Conditioning and Negative Distances for Speaker Separation
标题：说话人分离的个别化条件作用和负距离
链接：https://arxiv.org/abs/2210.06368
作者：Tao Sun,Nidal Abuhajar,Shuyu Gong,Zhewei Wang,Charles D. Smith,Xianhui Wang,Li Xu,Jundong Liu
机构：School of Electrical Engineering and Computer Science, Ohio University, Athens, OH , Department of Neurology, University of Kentucky, Lexington, KY , Division of Communication Sciences, Ohio University, Athens, OH
备注：Accepted to ICMLA 2022

【18】 A Generlist Framework for Panoptic Segmentation of Images and Videos
标题：一种通用的图像和视频全景分割框架
链接：https://arxiv.org/abs/2210.06366
作者：Ting Chen,Lala Li,Saurabh Saxena,Geoffrey Hinton,David J. Fleet
机构：Google Research, Brain Team

【19】 Text-to-Audio Grounding Based Novel Metric for Evaluating Audio Caption Similarity
标题：基于文本-音频基础的音频字幕相似度评价新指标
链接：https://arxiv.org/abs/2210.06354
作者：Swapnil Bhosale,Rupayan Chakraborty,Sunil Kumar Kopparapu
机构：TCS Research, Tata Consultancy Services Limited, India.
备注：9 pages, 8 figures,

【20】 CTL++: Evaluating Generalization on Never-Seen Compositional Patterns of Known Functions, and Compatibility of Neural Representations
标题：CTL++：评估未知函数组合模式的泛化和神经表示的兼容性
链接：https://arxiv.org/abs/2210.06350
作者：Róbert Csordás,Kazuki Irie,Jürgen Schmidhuber
机构：The Swiss AI Lab IDSIA, USI & SUPSI, Lugano, Switzerland, AI Initiative, KAUST, Thuwal, Saudi Arabia
备注：Accepted to EMNLP 2022

【21】 Context Generation Improves Open Domain Question Answering
标题：语境生成改进了开放领域问答
链接：https://arxiv.org/abs/2210.06349
作者：Dan Su,Mostofa Patwary,Shrimai Prabhumoye,Peng Xu,Ryan Prenger,Mohammad Shoeybi,Pascale Fung,Anima Anandkumar,Bryan Catanzaro
机构：The Hong Kong University of Science and Technology, §NVIDIA
备注：8 pages

【22】 TaskMix: Data Augmentation for Meta-Learning of Spoken Intent Understanding
标题：TaskMix：口语意图理解元学习的数据增强
链接：https://arxiv.org/abs/2210.06341
作者：Surya Kant Sahu
机构：Skit.ai, The Learning Machines
备注：Accepted at Findings of AACL-IJCNLP 2022

【23】 Improving Radiology Report Generation Systems by Removing Hallucinated References to Non-existent Priors
标题：通过消除对不存在的前科的幻觉引用来改进放射学报告生成系统
链接：https://arxiv.org/abs/2210.06340
作者：Vignav Ramesh,Nathan Andrew Chi,Pranav Rajpurkar
机构：Harvard University, Nathan A. Chi, Stanford University, Harvard Medical School
备注：13 pages, 1 figure, 11 tables; Under review at ML4H 2022 Symposium (Collocated with NeurIPS 2022)

【24】 Non-Axiomatic Term Logic: A Computational Theory of Cognitive Symbolic Reasoning
标题：非公理术语逻辑：认知符号推理的计算理论
链接：https://arxiv.org/abs/2210.06316
作者：Kotaro Funakoshi
机构：FUNAKOSHI(AT)LR.PI.TITECH.AC.JP, Tokyo Institute of Technology

【25】 Changing the Representation: Examining Language Representation for Neural Sign Language Production
标题：改变表征：考察神经手语产生的语言表征
链接：https://arxiv.org/abs/2210.06312
作者：Harry Walsh,Ben Saunders,Richard Bowden
机构：University of Surrey
备注：8 pages, 4 figures, 5 tables, SLTAT 2022

【26】 TwiRGCN: Temporally Weighted Graph Convolution for Question Answering over Temporal Knowledge Graphs
标题：TwiRGCN：时态知识图上问答的时态加权图卷积
链接：https://arxiv.org/abs/2210.06281
作者：Aditya Sharma,Apoorv Saxena,Chitrank Gupta,Seyed Mehran Kazemi,Partha Talukdar,Soumen Chakrabarti
机构：IISc, Bangalore, IIT Bombay, Google Research, Montreal, Google Research, India
备注：9 pages + references + appendix

【27】 Task Compass: Scaling Multi-task Pre-training with Task Prefix
标题：任务指南针：使用任务前缀扩展多任务预训练
链接：https://arxiv.org/abs/2210.06277
作者：Zhuosheng Zhang,Shuohang Wang,Yichong Xu,Yuwei Fang,Wenhao Yu,Yang Liu,Hai Zhao,Chenguang Zhu,Michael Zeng
机构：Shanghai Jiao Tong University, Shanghai, China, Microsoft Cognitive Services Research, Redmond, WA, USA, University of Notre Dame, Notre Dame, IN, USA
备注：Findings of EMNLP 2022

【28】 Entity Aware Negative Sampling with Auxiliary Loss of False Negative Prediction for Knowledge Graph Embedding
标题：知识图嵌入中具有辅助漏判损失的实体感知负抽样
链接：https://arxiv.org/abs/2210.06242
作者：Sang-Hyun Je
机构：Kakao Enterprise Corp.

【29】 Quasi-symbolic explanatory NLI via disentanglement: A geometrical examination
标题：解纠缠的准符号解释NLI：几何检验
链接：https://arxiv.org/abs/2210.06230
作者：Yingji Zhang,Danilo S. Carvalho,Ian Pratt-Hartmann,André Freitas
机构：Department of Computer Science, University of Manchester, United Kingdom, Idiap Research Institute, Switzerland
备注：16 pages. arXiv admin note: text overlap with arXiv:2210.02898

【30】 On the Generalizability of ECG-based Stress Detection Models
：基于心电的应力检测模型的泛化研究
链接：https://arxiv.org/abs/2210.06225
作者：Pooja Prajod,Elisabeth André
机构：Human-Centered Artificial Intelligence, University of Augsburg, Augsburg, Germany, Elisabeth Andre, , IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including
备注：Accepted to IEEE ICMLA 2022

【31】 Diffusion Models for Causal Discovery via Topological Ordering
标题：基于拓扑序的因果发现扩散模型
链接：https://arxiv.org/abs/2210.06201
作者：Pedro Sanchez,Xiao Liu,Alison Q O'Neil,Sotirios A. Tsaftaris
机构：The University of Edinburgh, Canon Medical Research Europe, The Alan Turing Institute
备注：Implementation is available at this https URL

【32】 Gotcha: A Challenge-Response System for Real-Time Deepfake Detection
标题：GETCHA：一种用于实时深伪检测的挑战-响应系统
链接：https://arxiv.org/abs/2210.06186
作者：Govind Mittal,Jiraphon Yenphraphai,Chinmay Hegde,Nasir Memon
机构：New York University

【33】 The Role of Exploration for Task Transfer in Reinforcement Learning
标题：探索性任务迁移在强化学习中的作用
链接：https://arxiv.org/abs/2210.06168
作者：Jonathan C Balloch,Julia Kim,and Jessica L Inman,Mark O Riedl
机构：College of Computing, Georgia Institute of Technology, Jessica L. Inman, Georgia Tech Research Institute
备注：4 pages

【34】 ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding
标题：Ernie-Layout：布局知识增强的视觉丰富文档理解的预训练
链接：https://arxiv.org/abs/2210.06155
作者：Qiming Peng,Yinxu Pan,Wenjin Wang,Bin Luo,Zhenyu Zhang,Zhengjie Huang,Teng Hu,Weichong Yin,Yongfeng Chen,Yin Zhang,Shikun Feng,Yu Sun,Hao Tian,Hua Wu,Haifeng Wang
机构：Baidu Inc., Beijing, China, Zhejiang University, Hangzhou, China
备注：Accepted to EMNLP 2022 (Findings)

【35】 Can Artificial Intelligence Reconstruct Ancient Mosaics?
标题：人工智能能重建古代马赛克吗？
链接：https://arxiv.org/abs/2210.06145
作者：Fernando Moral-Andrés,Elena Merino-Gómez,Pedro Reviriego,Fabrizio Lombardi
机构：Universidad Antonio de Nebrija, Madrid, Spain, Universidad de Valladolid, Valladolid, Spain, Universidad Politécnica de Madrid, Northeastern University, Boston, US

【36】 THUEE system description for NIST 2020 SRE CTS challenge
标题：NIST 2020 SRE CTS挑战赛THUEE系统描述
链接：https://arxiv.org/abs/2210.06111
作者：Yu Zheng,Jinghan Peng,Miao Zhao,Yufeng Ma,Min Liu,Xinyue Ma,Tianyu Liang,Tianlong Kong,Liang He,Minqiang Xu
机构：SpeakIn Technologies Co. Ltd., ShangHai, China, Department of Electronic Engineering Tsinghua University, Beijing, China
备注：3 pages, 1 table; System desciption of NIST 2020 SRE CTS challenge

【37】 Federated Continual Learning for Text Classification via Selective Inter-client Transfer
标题：基于选择性客户端传输的联合持续学习文本分类算法
链接：https://arxiv.org/abs/2210.06101
作者：Yatin Chaudhary,Pranav Rai,Matthias Schubert,Hinrich Schütze,Pankaj Gupta
机构：DRIMCo GmbH, Munich, Germany | ,University of Munich (LMU), Munich, Germany
备注：EMNLP2022 (Findings): 11 pages, 5 figures, 4 tables

【38】 Using Massive Multilingual Pre-Trained Language Models Towards Real Zero-Shot Neural Machine Translation in Clinical Domain
标题：使用海量多语种预训练语言模型实现临床领域的真正零激发神经机器翻译
链接：https://arxiv.org/abs/2210.06068
作者：Lifeng Han,Gleb Erofeev,Irina Sorokina,Serge Gladkoff,Goran Nenadic
机构： The University of Manchester, UK, Logrus Global, Translation & Localization
备注：8 pages, 2 figures

【39】 Multi-Granularity Cross-modal Alignment for Generalized Medical Visual Representation Learning
标题：用于广义医学视觉表征学习的多粒度跨模式对齐
链接：https://arxiv.org/abs/2210.06044
作者：Fuying Wang,Yuyin Zhou,Shujun Wang,Varut Vardhanabhuti,Lequan Yu
机构：The University of Hong Kong, University of California, Santa Cruz, University of Cambridge
备注：NeurIPS 2022

【40】 Question Answering Over Biological Knowledge Graph via Amazon Alexa
标题：通过Amazon Alexa在生物知识图上进行问答
链接：https://arxiv.org/abs/2210.06040
作者：Md. Rezaul Karim,Hussain Ali,Prinon Das,Mohamed Abdelwaheb,Stefan Decker
机构： Computer Science , - Information Systems and Databases, RWTH Aachen University, Germany, Fraunhofer Institute for Applied Information Technology FIT, Germany
备注：This paper is based on the Knowledge Graph Lab course (this https URL) offered at Computer Science 5 - Information Systems and Databases, RWTH Aachen University, Germany, and a joint collaboration with Osthus GmbH (this https URL), Aachen, Germany

【41】 Lbl2Vec: An Embeddig-Based Approach for Unsupervised Document Retrieval on Predefined Topics
标题：Lbl2Vec：一种基于嵌入的预定义主题无监督文档检索方法
链接：https://arxiv.org/abs/2210.06023
作者：Tim Schopf,Daniel Braun,Florian Matthes
机构：Department of Informatics, Technical University of Munich, Boltzmannstrasse , Garching, Germany
备注：None

【42】 Phantom -- An RL-driven framework for agent-based modeling of complex economic systems and markets
标题：Phantom--RL驱动的基于智能体的复杂经济系统和市场建模框架
链接：https://arxiv.org/abs/2210.06012
作者：Leo Ardon,Jared Vann,Deepeka Garg,Tom Spooner,Sumitra Ganesh
机构：J.P. Morgan AI Research, Sutter Hill Ventures
备注：2022 ACM International Conference on Artificial Intelligence in Finance - Benchmarks for AI in Finance Workshop

【43】 JukeDrummer: Conditional Beat-aware Audio-domain Drum Accompaniment Generation via Transformer VQ-VA
标题：JukeDrummer：通过TransformerVQ-VA生成条件节拍感知音域鼓伴奏
链接：https://arxiv.org/abs/2210.06007
作者：Yueh-Kao Wu,Ching-Yu Chiu,Yi-Hsuan Yang
机构：Academia Sinica, National Cheng Kung University, Taiwan AI Labs
备注：Accepted at ISMIR 2022

【44】 Probabilities Are Not Enough: Formal Controller Synthesis for Stochastic Dynamical Models with Epistemic Uncertainty
标题：概率是不够的：具有认知不确定性的随机动态模型的形式控制器综合
链接：https://arxiv.org/abs/2210.05989
作者：Thom Badings,Licio Romao,Alessandro Abate,Nils Jansen
机构： Radboud University, Nijmegen, the Netherlands, University of Oxford, Oxford, United Kingdom

【45】 BORA: Bayesian Optimization for Resource Allocation
标题：Bora：资源分配的贝叶斯优化
链接：https://arxiv.org/abs/2210.05977
作者：Antonio Candelieri,Andrea Ponti,Francesco Archetti
机构： Using Bayesian Optimization as a more effective and efficient approach, than semi-bandit feedback to solve the optimal resource allocation, Extending the original formulation of the optimal resource allocation
备注：31 pages, 12 figures

【46】 JuryGCN: Quantifying Jackknife Uncertainty on Graph Convolutional Networks
标题：JuryGCN：量化图卷积网络上的刀切不确定性
链接：https://arxiv.org/abs/2210.05959
作者：Jian Kang,Qinghai Zhou,Hanghang Tong
机构： and Hanghang TongUniversity of Illinois at Urbana-Champaign
备注：Accepted to KDD'22

【47】 Projective Transformation Rectification for Camera-captured Chest X-ray Photograph Interpretation with Synthetic Data
标题：利用合成数据进行胸部摄影解译的投影变换校正
链接：https://arxiv.org/abs/2210.05954
作者：Chak Fong Chong,Yapeng Wang,Benjamin Ng,Xu Yang
机构：Macao Polytechnic University, Macao SAR, China, Corresponding author

【48】 Explaining Online Reinforcement Learning Decisions of Self-Adaptive Systems
标题：解释自适应系统的在线强化学习决策
链接：https://arxiv.org/abs/2210.05931
作者：Felix Feit,Andreas Metzger,Klaus Pohl
机构：paluno (The Ruhr Institute for Software Technology), University of Duisburg-Essen; Essen, Germany
备注：Published at 3rd Intl Conference on Autonomic Computing and Self-Organizing Systems (ACSOS 2022)

【49】 Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learning
标题：无攻击的高效对抗性训练：最坏情况感知的稳健强化学习
链接：https://arxiv.org/abs/2210.05927
作者：Yongyuan Liang,Yanchao Sun,Ruijie Zheng,Furong Huang
机构： Shanghai AI Lab, University of Maryland, College Park
备注：36th Conference on Neural Information Processing Systems (NeurIPS 2022)

【50】 A Unified Framework for Alternating Offline Model Training and Policy Learning
标题：一种交替进行离线模型训练和政策学习的统一框架
链接：https://arxiv.org/abs/2210.05922
作者：Shentao Yang,Shujian Zhang,Yihao Feng,Mingyuan Zhou
机构：The University of Texas at Austin, Salesforce Research
备注：36th Conference on Neural Information Processing Systems (NeurIPS 2022)

【51】 Finite time analysis of temporal difference learning with linear function approximation: Tail averaging and regularisation
标题：基于线性函数逼近的时态差分学习有限时间分析：尾部平均化和正则化
链接：https://arxiv.org/abs/2210.05918
作者：Gandharv Patil,Prashanth L. A.,Dheeraj Nagaraj,Doina Precup
机构：: McGill University & Mila,: Indian Institute of Technology Madras,: Google Research

【52】 Enemy Spotted: in-game gun sound dataset for gunshot classification and localization
标题：发现敌人：用于枪击分类和定位的游戏中枪声数据集
链接：https://arxiv.org/abs/2210.05917
作者：Junwoo Park,Youngwoo Cho,Gyuhyeon Sim,Hojoon Lee,Jaegul Choo
机构：Kim Jaechul Graduate School of AI, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea
备注：Accepted at IEEE Conference on Games (GoG) 2022

【53】 Travel the Same Path: A Novel TSP Solving Strategy
标题：走同一条路：一种新的TSP求解策略
链接：https://arxiv.org/abs/2210.05906
作者：Pingbang Hu
机构：Department of Computer Science, University of Michigan

【54】 Perplexity from PLM Is Unreliable for Evaluating Text Quality
标题：PLM的困惑程度不能作为评估文本质量的可靠指标
链接：https://arxiv.org/abs/2210.05892
作者：Yequan Wang,Jiawen Deng,Aixin Sun,Xuying Meng
机构：Beijing Academy of Artificial Intelligence, Beijing, China, CoAI Group, DCST, IAI, BNRIST, Tsinghua University, Beijing, China, School of Computer Science and Engineering, Nanyang Technological University, Singapore

【55】 Deep Learning for Iris Recognition: A Survey
标题：深度学习在虹膜识别中的研究进展
链接：https://arxiv.org/abs/2210.05866
作者：Kien Nguyen,Hugo Proena,Fernando Alonso-Fernandez
机构： Queensland University of Technology, University of Beira Interior, Halmstad University

【56】 SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models
标题：SlotFormer：以对象为中心模型的无监督视觉动力学仿真
链接：https://arxiv.org/abs/2210.05861
作者：Ziyi Wu,Nikita Dvornik,Klaus Greff,Thomas Kipf,Animesh Garg
机构： University of Toronto, Vector Institute, Samsung AI Centre Toronto, Google Research
备注：Project page: this https URL

【57】 Contrastive introspection (ConSpec) to rapidly identify invariant steps for success
标题：对比自省(ConSpec)，快速确定成功的不变步骤
链接：https://arxiv.org/abs/2210.05845
作者：Chen Sun,Wannan Yang,Benjamin Alsbury-Nealy,Yoshua Bengio,Blake Richards
机构：Mila, Université de Montréal, New York University, University of Toronto, Baycrest Health Sciences, SilicoLabs Incorporated, Mila, Montréal Neurological Institute, McGill University, Learning in Machines and Brains Program, CIFAR

【58】 Synthetic Power Analyses: Empirical Evaluation and Application to Cognitive Neuroimaging
标题：综合能力分析：认知神经成像的经验评价及应用
链接：https://arxiv.org/abs/2210.05835
作者：Peiye Zhuang,Bliss Chapman,Ran Li,Oluwasanmi Koyejo
机构：Dept. of Comupter Science, University of Illinois, at Urbana-Champaign, Apple, Google, Sanmi Koyejo, & Beckman Institute
备注：Accepted to Asilomar 2019

【59】 Social-Group-Agnostic Word Embedding Debiasing via the Stereotype Content Model
标题：基于刻板印象内容模型的社会群体不可知词嵌入去偏倚
链接：https://arxiv.org/abs/2210.05831
作者：Ali Omrani,Brendan Kennedy,Mohammad Atari,Morteza Dehghani
机构：University of Southern California
备注：short paper

【60】 AMICO: Amodal Instance Composition
标题：Amico：非模态实例组成
链接：https://arxiv.org/abs/2210.05828
作者：Peiye Zhuang,Jia-bin Huang,Ayush Saraf,Xuejian Rong,Changil Kim,Denis Demandolx
机构：Illinois, Urbana-, Champaign, University of Maryland, College Park, Facebook
备注：Accepted to BMVC 2021, 20 oages, 12 figures

【61】 Controllable Radiance Fields for Dynamic Face Synthesis
标题：动态人脸合成中的可控辐射场
链接：https://arxiv.org/abs/2210.05825
作者：Peiye Zhuang,Liqian Ma,Oluwasanmi Koyejo,Alexander G. Schwing
机构：University of Illinois Urbana-Champaign,ZMO AI Inc.,Stanford University,Google Inc., Identity , sampling, Free-view dynamic head synthesis with motion control
备注：Accepted to 3DV 2022. 13 pages, 15 figures

【62】 Deep Counterfactual Estimation with Categorical Background Variables
标题：类别背景变量下的深度反事实估计
链接：https://arxiv.org/abs/2210.05811
作者：Edward De Brouwer
机构：ESAT-STADIUS, KU Leuven
备注：Proceedings of the NeurIPS 2022 Conference

【63】 Exploration via Elliptical Episodic Bonuses
标题：通过椭圆形插曲加成的探索
链接：https://arxiv.org/abs/2210.05805
作者：Mikael Henaff,Roberta Raileanu,Minqi Jiang,Tim Rocktschel
机构：Meta AI Research, University College London

【64】 Towards Discriminative and Transferable One-Stage Few-Shot Object Detectors
标题：朝向可辨别和可转移的单级小射击目标探测器
链接：https://arxiv.org/abs/2210.05783
作者：Karim Guirguis,Mohamed Abdelsamad,George Eskandar,Ahmed Hendawy,Matthias Kayser,Bin Yang,Juergen Beyerer
机构：Robert Bosch GmbH, Karlsruhe Institute of Technology, University of Stuttgart, Fraunhofer IOSB

【65】 Gradient-Guided Importance Sampling for Learning Binary Energy-Based Models
标题：基于梯度引导的重要抽样学习二元能量模型
链接：https://arxiv.org/abs/2210.05782
作者：Meng Liu,Haoran Liu,Shuiwang Ji
机构：Department of Computer Science & Engineering, Texas A&M University, College Station, TX , USA

【66】 Bil-DOS: A Bi-lingual Dialogue Ordering System (for Subway)
标题：BIL-DOS：一个面向地铁的双语对话订餐系统
链接：https://arxiv.org/abs/2210.05773
作者：Zirong Chen,Haotian Xue
机构：Georgetown University, Department of Computer Science

【67】 Applying FrameNet to Chinese(Poetry)
标题：将FrameNet应用于汉语(诗歌)
链接：https://arxiv.org/abs/2210.05772
作者：Zirong Chen
机构：Department of Computer Science, Georgetown University, Washington, DC, USA

【68】 Decoupled Context Processing for Context Augmented Language Modeling
标题：语境增强语言建模中的语境解耦处理
链接：https://arxiv.org/abs/2210.05758
作者：Zonglin Li,Ruiqi Guo,Sanjiv Kumar
机构：Google Research, New York

【69】 Stochastic Constrained DRO with a Complexity Independent of Sample Size
标题：复杂性与样本量无关的随机约束DRO
链接：https://arxiv.org/abs/2210.05740
作者：Qi Qi,Jiameng Lyu,Kung sik Chan,Er Wei Bai,Tianbao Yang
机构：Kung-sik Chan, Er-Wei Bai, Department of Computer Science, The University of Iowa, Iowa City, IA , USA, Yau Mathematical Sciences Center, Tsinghua University, Beijing, China
备注：37 pages, 16 figures

【70】 Embeddings as Epistemic States: Limitations on the Use of Pooling Operators for Accumulating Knowledge
标题：作为认知状态的嵌入：使用汇集运算符积累知识的限制
链接：https://arxiv.org/abs/2210.05723
作者：Steven Schockaert
机构：Cardiff University, School of Computer Science & Informatics, Abacws building, Senghennydd Road, CF,AG, Cardiff, UK

【71】 Relational Embeddings for Language Independent Stance Detection
标题：用于语言无关姿态检测的关系嵌入
链接：https://arxiv.org/abs/2210.05715
作者：Joseba Fernandez de Landa,Rodrigo Agerri
机构：HiTZ Center - Ixa, University of the Basque Country UPVEHU

【72】 Visual Language Maps for Robot Navigation
标题：用于机器人导航的可视化语言地图
链接：https://arxiv.org/abs/2210.05714
作者：Chenguang Huang,Oier Mees,Andy Zeng,Wolfram Burgard
机构： these systems 1University of Freiburg, 3University of Technology Nuremberg
备注：Project page: https:http://vlmaps.github.io

【73】 Towards Consistency and Complementarity: A Multiview Graph Information Bottleneck Approach
标题：走向一致性和互补性：一种多视点图信息瓶颈方法
链接：https://arxiv.org/abs/2210.05676
作者：Xiaolong Fan,Maoguo Gong,Yue Wu,Mingyang Zhang,Hao Li,Xiangming Jiang

【74】 Transformers generalize differently from information stored in context vs in weights
标题：与存储在上下文中的信息不同，转换器的泛化方式与权重不同
链接：https://arxiv.org/abs/2210.05675
作者：Stephanie C. Y. Chan,Ishita Dasgupta,Junkyung Kim,Dharshan Kumaran,Andrew K. Lampinen,Felix Hill
机构：DeepMind

【75】 Unsupervised detection of structural damage using Variational Autoencoder and a One-Class Support Vector Machine
标题：基于变分自动编码器和单类支持向量机的结构损伤非监督检测
链接：https://arxiv.org/abs/2210.05674
作者：Andrea Pollastro,Giusiana Testa,Antonio Bilotta,Roberto Prevete
机构： Department of Electrical Engineering and Information Technology, University of, Naples Federico II, Naples, Italy, Department of Structures for Engineering and Architecture, University of Naples

【76】 Quantifying Uncertainty with Probabilistic Machine Learning Modeling in Wireless Sensing
标题：无线传感中基于概率机器学习建模的不确定性量化
链接：https://arxiv.org/abs/2210.06416
作者：Amit Kachroo,Sai Prashanth Chinnapalli
机构：Amazon Lab, Sunnyvale, California, USA
备注：6 pages, 3 figures, Submitted to IEEE CCNC 2023

【77】 An Ensemble Teacher-Student Learning Approach with Poisson Sub-sampling to Differential Privacy Preserving Speech Recognition
标题：用于差分隐私保护语音识别的泊松次抽样集成师生学习方法
链接：https://arxiv.org/abs/2210.06382
作者：Chao-Han Huck Yang,Jun Qi,Sabato Marco Siniscalchi,Chin-Hui Lee
机构：Georgia Institute of Technology, USA and ,Kore University of Enna, Italy, Department of Electronic Systems, NTNU, Trondheim, Norway
备注：Accepted to ISCA, ISCSLP 2022, Singapore. 5 Pages

【78】 A Self-attention Guided Multi-scale Gradient GAN for Diversified X-ray Image Synthesis
标题：一种用于多种X射线图像合成的自关注多尺度梯度GaN
链接：https://arxiv.org/abs/2210.06334
作者：Muhammad Muneeb Saad,Mubashir Husain Rehmani,Ruairi O'Reilly
机构：Rehmani,[,,,,], and Ruairi O’Reilly,[,,,,], Munster Technological University Cork, Ireland
备注：Submitted to the AICS-2022 Conference

【79】 Generalised Mutual Information for Discriminative Clustering
标题：基于广义互信息的判别聚类
链接：https://arxiv.org/abs/2210.06300
作者：Ohl Louis,Mattei Pierre-Alexandre,Bouveyron Charles,Harchaoui Warith,Leclercq Mickal,Droit Arnaud,Precioso Frederic
机构：Generalised Mutual Informationfor Discriminative ClusteringLouis OhlUniversité Cte d’AzurInria, Maasai teamCHU de Québec Research CenterLaval Universitylouis, frPierre-Alexandre MatteiUniversité Cte d’AzurInria, frCharles BouveryonUniversité Cte d’AzurInria
备注：To be published in Neural Information Processing Systems 2022

【80】 Cross Task Neural Architecture Search for EEG Signal Classifications
标题：基于跨任务神经结构的脑电信号分类算法
链接：https://arxiv.org/abs/2210.06298
作者：Yiqun Duan,Zhen Wang,Yi Li,Jianhang Tang,Yu-Kai Wang,Chin-Teng Lin
机构： CIBCI lab, Australian Artificial Intelligence Institute, School of Computer Science, University of Technology Sydney, Ultimo, NSW , Australia, School of Computer Science, The University of Sydney, Darlington, NSW , Australia

【81】 Multimodality Multi-Lead ECG Arrhythmia Classification using Self-Supervised Learning
标题：基于自监督学习的多模多导联心电心律失常分类
链接：https://arxiv.org/abs/2210.06297
作者：Thinh Phan,Duc Le,Patel Brijesh,Donald Adjeroh,Jingxian Wu,Morten Olgaard Jensen,Ngan Le
机构：Department of AI Convergence, Chonnam National University, Gwangju, South Korea , Department of CSCE, University of Arkansas, Fayetteville, Arkansas , Department of Cardiology, West Virginia University, Morgantown, WV , Department of CSEE, Department of ELEG

【82】 Transfer learning on electromyography (EMG) tasks: approaches and beyond
标题：肌电(EMG)任务的迁移学习：方法和超越
链接：https://arxiv.org/abs/2210.06295
作者：Di Wu,Jie Yang,Mohamad Sawan
机构：Center of Excellence in Biomedical Research on Advanced Integrated-on-chips, Neurotechnologies, School of Engineering, Westlake University, Hangzhou, China, Institute of Advanced Technology, Westlake Institute for Advanced Study, Hangzhou

【83】 Two-stream Network for ECG Signal Classification
标题：用于心电信号分类的双流网络
链接：https://arxiv.org/abs/2210.06293
作者：Xinyao Hou,Shengmei Qin,Jianbo Su
机构：!

【84】 The evolution of AI approaches for motor imagery EEG-based BCIs
标题：基于脑电的运动想象脑机接口人工智能方法研究进展
链接：https://arxiv.org/abs/2210.06290
作者：Aurora Saibene,Silvia Corchs,Mirko Caglioni,Francesca Gasparini
机构： University of Milano-Bicocca, Viale Sarca , Milano, Italy, NeuroMI, Milan Center for Neuroscience, Piazza dell’Ateneo Nuovo , University of Insubria, Via J. H. Dunant , Varese, Italy
备注：Submitted to Italian Workshop on Artificial Intelligence for Human Machine Interaction (AIxHMI 2022), December 02, 2022, Udine, Italy

【85】 Finding and Listing Front-door Adjustment Sets
标题：查找并列出前门调整集
链接：https://arxiv.org/abs/2210.05816
作者：Hyunchai Jeong,Jin Tian,Elias Bareinboim
机构：Purdue University, Iowa State University, Columbia University
备注：Pages: 18 (main paper 10, references 2, appendix 6), Figures: 9 (main paper 7, appendix 2), to be published in Proceedings of the 36th Annual Conference on Neural Information Processing Systems

【86】 Predictive Event Segmentation and Representation with Neural Networks: A Self-Supervised Model Assessed by Psychological Experiments
标题：基于神经网络的预测事件分割与表示：一种心理学实验验证的自监督模型
链接：https://arxiv.org/abs/2210.05710
作者：Hamit Basgol,Inci Ayhan,Emre Ugur
机构：Department of Computer Science, at the University of Tübingen, Germany, Department of Psychology, Department of Computer Engineering, at Bogazii University, Turkey
备注：27 pages, 9 figures, supplementary document can be found in the latex file

机器翻译由腾讯交互翻译提供，仅供参考

历史文章列表 网站http://www.arxivdaily.com/
注：含中英文摘要速递见公众号【arXiv每日学术速递】,涵盖CS|物理|数学|经济|统计|金融|生物|电气等领域。