AI Agent - arXivDaily 专题

2402.05946 2024-03-20 cs.LG cs.AI 62%

Unveiling Latent Causal Rules: A Temporal Point Process Approach for Abnormal Event Explanation

Yiling Kuang, Chao Yang, Yang Yang, Shuang Li

专题命中工作流自动化：planning(abstract)；分类 cs.AI、cs.LG

Comments Accepted by AISTATS 2024

2210.10243 2024-03-18 cs.LG cs.AI 62%

CLUTR: Curriculum Learning via Unsupervised Task Representation Learning

Abdus Salam Azad, Izzeddin Gur, Jasper Emhoff, Nathaniel Alexis, Aleksandra Faust, Pieter Abbeel, Ion Stoica

专题命中工作流自动化：agent(abstract)；分类 cs.AI、cs.LG

Comments Preprint, Currently Under Review

2211.16648 2024-03-15 cs.DC cs.AI cs.LG 62%

COMET: A Comprehensive Cluster Design Methodology for Distributed Deep Learning Training

Divya Kiran Kadiyala, Saeed Rashidi, Taekyung Heo, Abhimanyu Rajeshkumar Bambhaniya, Tushar Krishna, Alexandros Daglis

专题命中工作流自动化：workflow(abstract)；分类 cs.AI、cs.LG

2403.06221 2024-03-12 cs.AI cs.CL cs.IR 62%

TRAD: Enhancing LLM Agents with Step-Wise Thought Retrieval and Aligned Decision

Ruiwen Zhou, Yingxuan Yang, Muning Wen, Ying Wen, Wenhao Wang, Chunling Xi, Guoqiang Xu, Yong Yu, Weinan Zhang

专题命中工作流自动化：agent(abstract)；分类 cs.AI、cs.CL

Comments Codes available at: https://github.com/skyriver-2000/TRAD-Official

2403.04790 2024-03-11 cs.CL cs.AI 62%

Online Training of Large Language Models: Learn while chatting

Juhao Liang, Ziwei Wang, Zhuoheng Ma, Jianquan Li, Zhiyi Zhang, Xiangbo Wu, Benyou Wang

专题命中工作流自动化：AI agent(abstract)；分类 cs.AI、cs.CL

2403.02370 2024-03-06 cs.CL cs.AI 62%

adaptMLLM: Fine-Tuning Multilingual Language Models on Low-Resource Languages with Integrated LLM Playgrounds

Séamus Lankford, Haithem Afli, Andy Way

专题命中工作流自动化：workflow(abstract)；分类 cs.AI、cs.CL

Journal ref Information 2023, 14(12), 638

2402.13304 2024-02-22 cs.LG cs.AI 62%

Harmful algal bloom forecasting. A comparison between stream and batch learning

Andres Molares-Ulloa, Elisabet Rocruz, Daniel Rivero, Xosé A. Padin, Rita Nolasco, Jesús Dubert, Enrique Fernandez-Blanco

专题命中工作流自动化：workflow(abstract)；分类 cs.AI、cs.LG

2402.08611 2024-02-14 cs.LG cs.AI 62%

A Cost-Sensitive Transformer Model for Prognostics Under Highly Imbalanced Industrial Data

Ali Beikmohammadi, Mohammad Hosein Hamian, Neda Khoeyniha, Tony Lindgren, Olof Steinert, Sindri Magnússon

专题命中工作流自动化：workflow(abstract)；分类 cs.AI、cs.LG

2401.01269 2024-02-14 cs.CR cs.AI cs.SE 62%

LLbezpeky: Leveraging Large Language Models for Vulnerability Detection

Noble Saji Mathews, Yelizaveta Brus, Yousra Aafer, Meiyappan Nagappan, Shane McIntosh

专题命中工作流自动化：workflow(abstract)；分类 cs.AI、cs.SE

Comments This project report was presented as a part of the course CS858 at the University of Waterloo under the supervision of Prof. Yousra Aafer

2402.05828 2024-02-09 cs.LG cs.AI 62%

Discovering Temporally-Aware Reinforcement Learning Algorithms

Matthew Thomas Jackson, Chris Lu, Louis Kirsch, Robert Tjarko Lange, Shimon Whiteson, Jakob Nicolaus Foerster

专题命中工作流自动化：agent(abstract)；分类 cs.AI、cs.LG

Comments Published at ICLR 2024

2304.07896 2024-02-09 cs.LG cs.AI stat.ML 62%

Out-of-Variable Generalization for Discriminative Models

Siyuan Guo, Jonas Wildberger, Bernhard Schölkopf

专题命中工作流自动化：agent(abstract)；分类 cs.AI、cs.LG

Comments Accepted at ICLR 2024

2212.09437 2024-01-26 cs.SE cs.LG 62%

Machine Learning Systems are Bloated and Vulnerable

Huaifeng Zhang, Fahmi Abdulqadir Ahmed, Dyako Fatih, Akayou Kitessa, Mohannad Alhanahnah, Philipp Leitner, Ahmed Ali-Eldin

专题命中工作流自动化：workflow(abstract)；分类 cs.LG、cs.SE

2312.09442 2024-01-25 eess.SP cs.AI cs.LG 62%

A Compact LSTM-SVM Fusion Model for Long-Duration Cardiovascular Diseases Detection

Siyang Wu

专题命中工作流自动化：workflow(abstract)；分类 cs.AI、cs.LG

2312.07899 2024-01-17 q-bio.QM cs.AI cs.CV cs.LG 62%

Morphological Profiling for Drug Discovery in the Era of Deep Learning

Qiaosi Tang, Ranjala Ratnayake, Gustavo Seabra, Zhe Jiang, Ruogu Fang, Lina Cui, Yousong Ding, Tamer Kahveci, Jiang Bian, Chenglong Li, Hendrik Luesch, Yanjun Li

专题命中工作流自动化：workflow(abstract)；分类 cs.AI、cs.LG

Comments 44 pages, 5 figure, 5 tables

2401.06538 2024-01-15 cs.NI cs.AI cs.LG 62%

Intelligent Data-Driven Architectural Features Orchestration for Network Slicing

Rodrigo Moreira, Flavio de Oliveira Silva, Tereza Cristina Melo de Brito Carvalho, Joberto S. B. Martins

专题命中工作流自动化：planning(abstract)；分类 cs.AI、cs.LG

Comments 12 pages, 6 figures, Conference ADVANCE 24 - International Workshop on ADVANCEs in ICT Infrastructures and Services - February 26--29, 2024 - Hanoi, Vietnam

2401.05251 2024-01-11 cs.LG cs.AI cs.SY eess.SY 62%

ReACT: Reinforcement Learning for Controller Parametrization using B-Spline Geometries

Thomas Rudolf, Daniel Flögel, Tobias Schürmann, Simon Süß, Stefan Schwab, Sören Hohmann

专题命中工作流自动化：agent(abstract)；分类 cs.AI、cs.LG

Comments 7 pages, 7 figures, accepted at the 2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Honolulu, HI, USA

2401.05033 2024-01-11 cs.CL cs.AI 62%

Bootstrapping LLM-based Task-Oriented Dialogue Agents via Self-Talk

Dennis Ulmer, Elman Mansimov, Kaixiang Lin, Justin Sun, Xibin Gao, Yi Zhang

专题命中工作流自动化：workflow(abstract)；分类 cs.AI、cs.CL

2401.02986 2024-01-09 cs.CL cs.AI 62%

Identification of Regulatory Requirements Relevant to Business Processes: A Comparative Study on Generative AI, Embedding-based Ranking, Crowd and Expert-driven Methods

Catherine Sai, Shazia Sadiq, Lei Han, Gianluca Demartini, Stefanie Rinderle-Ma

专题命中工作流自动化：workflow(abstract)；分类 cs.AI、cs.CL

2312.16378 2023-12-29 cs.CL cs.AI 62%

Automating Knowledge Acquisition for Content-Centric Cognitive Agents Using LLMs

Sanjay Oruganti, Sergei Nirenburg, Jesse English, Marjorie McShane

专题命中工作流自动化：agent(abstract)；分类 cs.AI、cs.CL

Comments 7 pages, 7 figures, AAAI Fall Symposium Series 2023 on Integrating Cognitive Architecture and Generative Models

2010.03744 2023-12-20 cs.LG cs.AI stat.ML 62%

Maximum Reward Formulation In Reinforcement Learning

Sai Krishna Gottipati, Yashaswi Pathak, Rohan Nuttall, Sahir, Raviteja Chunduru, Ahmed Touati, Sriram Ganapathi Subramanian, Matthew E. Taylor, Sarath Chandar

专题命中工作流自动化：agent(abstract)；分类 cs.AI、cs.LG

Comments 14 pages, 5 figures Update based on reviewer feedback

2307.01504 2023-12-19 cs.SI cs.AI cs.LG 62%

All in One: Multi-task Prompting for Graph Neural Networks

Xiangguo Sun, Hong Cheng, Jia Li, Bo Liu, Jihong Guan

专题命中工作流自动化：workflow(abstract)；分类 cs.AI、cs.LG

Comments KDD 23 Best Research Paper Award, which is the first for Hong Kong and Mainland China. A Python Library is released as ProG: https://github.com/sheldonresearch/ProG Submitted to SIGKDD'23 in 03 Feb 2023; Receive Acceptance in 17 May 2023 (Rating 3 4 4 4); Submit to arXiv 1st time in 4 Jul 2023

2312.04965 2023-12-11 cs.CV cs.AI cs.CL 62%

Inversion-Free Image Editing with Natural Language

Sihan Xu, Yidong Huang, Jiayi Pan, Ziqiao Ma, Joyce Chai

专题命中工作流自动化：workflow(abstract)；分类 cs.AI、cs.CL

Comments Project Page: https://sled-group.github.io/InfEdit/

2312.04594 2023-12-11 cs.CR cs.AI cs.LG 62%

FedGeo: Privacy-Preserving User Next Location Prediction with Federated Learning

Chung Park, Taekyoon Choi, Taesan Kim, Mincheol Cho, Junui Hong, Minsung Choi, Jaegul Choo

专题命中工作流自动化：agent(abstract)；分类 cs.AI、cs.LG

Comments Accepted at 31st ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (ACM SIGSPATIAL 2023)

2312.03881 2023-12-08 cs.LG cs.AI 62%

FoMo Rewards: Can we cast foundation models as reward functions?

Ekdeep Singh Lubana, Johann Brehmer, Pim de Haan, Taco Cohen

专题命中工作流自动化：agent(abstract)；分类 cs.AI、cs.LG

Comments Accepted to NeurIPS FMDM workshop

2312.03764 2023-12-08 cs.LG cs.AI 62%

Similarity-based Knowledge Transfer for Cross-Domain Reinforcement Learning

Sergio A. Serrano, Jose Martinez-Carranza, L. Enrique Sucar

专题命中工作流自动化：agent(abstract)；分类 cs.AI、cs.LG

Comments 30 pages, 7 figures

2304.14721 2023-12-08 cs.RO cs.CL cs.SE cs.SY eess.SY 62%

Towards autonomous system: flexible modular production system enhanced with large language model agents

Yuchen Xia, Manthan Shenoy, Nasser Jazdi, Michael Weyrich

专题命中工作流自动化：planning(abstract)；分类 cs.CL、cs.SE

Comments This is the pre-print draft manuscript. The peer-reviewed version will be published exclusively by IEEE after the conference, which is set to take place from September 12th to 15th, 2023. We've made several improvements to the final version of the paper based on valuable feedback and suggestions from other researchers

Journal ref 2023 IEEE 28th International Conference on Emerging Technologies and Factory Automation (ETFA)

2312.00808 2023-12-05 cs.AI cs.LG cs.RO 62%

Transforming organic chemistry research paradigms: moving from manual efforts to the intersection of automation and artificial intelligence

Chengchun Liu, Yuntian Chen, Fanyang Mo

专题命中工作流自动化：planning(abstract)；分类 cs.AI、cs.LG

2311.14708 2023-11-28 cs.CY cs.AI cs.CL cs.HC 62%

Large Language Model-Driven Classroom Flipping: Empowering Student-Centric Peer Questioning with Flipped Interaction

Chee Wei Tan

专题命中工作流自动化：workflow(abstract)；分类 cs.AI、cs.CL

Comments Submitted

2311.10471 2023-11-20 cs.LG cs.AI 62%

Regions are Who Walk Them: a Large Pre-trained Spatiotemporal Model Based on Human Mobility for Ubiquitous Urban Sensing

Ruixing Zhang, Liangzhe Han, Leilei Sun, Yunqi Liu, Jibin Wang, Weifeng Lv

专题命中工作流自动化：workflow(abstract)；分类 cs.AI、cs.LG

Comments 8 pages

2311.00334 2023-11-14 cs.LG cs.AI cs.DC 62%

MetisFL: An Embarrassingly Parallelized Controller for Scalable & Efficient Federated Learning Workflows

Dimitris Stripelis, Chrysovalantis Anastasiou, Patrick Toral, Armaghan Asghar, Jose Luis Ambite

专题命中工作流自动化：workflow(abstract)；分类 cs.AI、cs.LG

Comments 15 pages, 11 figures, Accepted at DistributedML '23

1. 工作流自动化 10492 篇

Unveiling Latent Causal Rules: A Temporal Point Process Approach for Abnormal Event Explanation

CLUTR: Curriculum Learning via Unsupervised Task Representation Learning

COMET: A Comprehensive Cluster Design Methodology for Distributed Deep Learning Training

TRAD: Enhancing LLM Agents with Step-Wise Thought Retrieval and Aligned Decision

Online Training of Large Language Models: Learn while chatting

adaptMLLM: Fine-Tuning Multilingual Language Models on Low-Resource Languages with Integrated LLM Playgrounds

Harmful algal bloom forecasting. A comparison between stream and batch learning

A Cost-Sensitive Transformer Model for Prognostics Under Highly Imbalanced Industrial Data

LLbezpeky: Leveraging Large Language Models for Vulnerability Detection

Discovering Temporally-Aware Reinforcement Learning Algorithms

Out-of-Variable Generalization for Discriminative Models

Machine Learning Systems are Bloated and Vulnerable

A Compact LSTM-SVM Fusion Model for Long-Duration Cardiovascular Diseases Detection

Morphological Profiling for Drug Discovery in the Era of Deep Learning

Intelligent Data-Driven Architectural Features Orchestration for Network Slicing

ReACT: Reinforcement Learning for Controller Parametrization using B-Spline Geometries

Bootstrapping LLM-based Task-Oriented Dialogue Agents via Self-Talk

Identification of Regulatory Requirements Relevant to Business Processes: A Comparative Study on Generative AI, Embedding-based Ranking, Crowd and Expert-driven Methods

Automating Knowledge Acquisition for Content-Centric Cognitive Agents Using LLMs

Maximum Reward Formulation In Reinforcement Learning

All in One: Multi-task Prompting for Graph Neural Networks

Inversion-Free Image Editing with Natural Language

FedGeo: Privacy-Preserving User Next Location Prediction with Federated Learning

FoMo Rewards: Can we cast foundation models as reward functions?

Similarity-based Knowledge Transfer for Cross-Domain Reinforcement Learning

Towards autonomous system: flexible modular production system enhanced with large language model agents

Transforming organic chemistry research paradigms: moving from manual efforts to the intersection of automation and artificial intelligence

Large Language Model-Driven Classroom Flipping: Empowering Student-Centric Peer Questioning with Flipped Interaction

Regions are Who Walk Them: a Large Pre-trained Spatiotemporal Model Based on Human Mobility for Ubiquitous Urban Sensing

MetisFL: An Embarrassingly Parallelized Controller for Scalable & Efficient Federated Learning Workflows