AI Agent

Assessing Hidden Risks of LLMs: An Empirical Study on Robustness, Consistency, and Credibility

Wentao Ye, Mingfeng Ou, Tianyi Li, Yipeng chen, Xuetao Ma, Yifan Yanggong, Sai Wu, Jie Fu, Gang Chen, Haobo Wang, Junbo Zhao

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

Challenges and Practices of Deep Learning Model Reengineering: A Case Study on Computer Vision

Wenxin Jiang, Vishnu Banna, Naveen Vivek, Abhinav Goel, Nicholas Synovic, George K. Thiruvathukal, James C. Davis

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

Comments Under submission to EMSE

InTune: Reinforcement Learning-based Data Pipeline Optimization for Deep Recommendation Models

Kabir Nagrecha, Lingyi Liu, Pablo Delgado, Prasanna Padmanabhan

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

Comments Accepted at RecSys 2023. 11 pages, 2 pages of references. 8 figures with 2 tables

Fountain -- an intelligent contextual assistant combining knowledge representation and language models for manufacturing risk identification

Saurabh Kumar, Daniel Fuchs, Klaus Spindler

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

MyCrunchGPT: A chatGPT assisted framework for scientific machine learning

Varun Kumar, Leonard Gleyzer, Adar Kahana, Khemraj Shukla, George Em Karniadakis

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

Comments Updated title, abstract and added references

How Can Large Language Models Help Humans in Design and Manufacturing?

Liane Makatura, Michael Foshey, Bohan Wang, Felix HähnLein, Pingchuan Ma, Bolei Deng, Megan Tjandrasuwita, Andrew Spielberg, Crystal Elaine Owens, Peter Yichen Chen, Allan Zhao, Amy Zhu, Wil J Norton, Edward Gu, Joshua Jacob, Yifei Li, Adriana Schulz, Wojciech Matusik

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

Project Florida: Federated Learning Made Easy

Daniel Madrigal Diaz, Andre Manoel, Jialei Chen, Nalin Singal, Robert Sim

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

Exploring Perspectives on the Impact of Artificial Intelligence on the Creativity of Knowledge Work: Beyond Mechanised Plagiarism and Stochastic Parrots

Advait Sarkar

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

Comments Advait Sarkar. 2023. Exploring Perspectives on the Impact of Artificial Intelligence on the Creativity of Knowledge Work Beyond Mechanised Plagiarism and Stochastic Parrots. In Annual Symposium on Human-Computer Interaction for Work 2023 (CHIWORK 2023), June 13-16, 2023, Oldenburg, Germany. ACM, New York, NY, USA, 17 pages

Hyperparameter Tuning Cookbook: A guide for scikit-learn, PyTorch, river, and spotPython

Thomas Bartz-Beielstein

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

IxDRL: A Novel Explainable Deep Reinforcement Learning Toolkit based on Analyses of Interestingness

Pedro Sequeira, Melinda Gervasio

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

Comments To be published in the Proceedings of the 1st World Conference on eXplainable Artificial Intelligence (xAI 2023). arXiv admin note: substantial text overlap with arXiv:2211.06376

MOPO-LSI: A User Guide

Yong Zheng, Kumar Neelotpal Shukla, Jasmine Xu, David, Wang, Michael O'Leary

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

Blockchain Framework for Artificial Intelligence Computation

Jie You

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

Comments 10 pages, 4 figures

Journal ref Software Impacts Volume 13, August 2022, 100314

SUPERNOVA: Automating Test Selection and Defect Prevention in AAA Video Games Using Risk Based Testing and Machine Learning

Alexander Senchenko, Naomi Patterson, Hamman Samuel, Dan Isper

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

Comments ICST 2022 Industry Track Proceedings, 10 pages, 8 figures, 2 tables

Journal ref Verification and Validation (ICST), 2022, pp. 345-354

Semi-Supervised Offline Reinforcement Learning with Action-Free Trajectories

Qinqing Zheng, Mikael Henaff, Brandon Amos, Aditya Grover

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

Comments ICML 2023. Code: https://github.com/facebookresearch/ssorl/

You Only Transfer What You Share: Intersection-Induced Graph Transfer Learning for Link Prediction

Wenqing Zheng, Edward W Huang, Nikhil Rao, Zhangyang Wang, Karthik Subbian

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

Comments Accepted in TMLR (https://openreview.net/forum?id=Nn71AdKyYH)

Deep Learning Models on CPUs: A Methodology for Efficient Training

Quchen Fu, Ramesh Chukka, Keith Achorn, Thomas Atta-fosu, Deepak R. Canchi, Zhongwei Teng, Jules White, Douglas C. Schmidt

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

Journal ref Journal of Machine Learning Theory, Applications and Practice (2023)

PyTorch Hyperparameter Tuning - A Tutorial for spotPython

Thomas Bartz-Beielstein

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

Comments Refers to spotPython version 0.2.15

Automated Annotation with Generative AI Requires Validation

Nicholas Pangakis, Samuel Wolken, Neil Fasching

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

Assessing the Generalizability of a Performance Predictive Model

Ana Nikolikj, Gjorgjina Cenikj, Gordana Ispirova, Diederick Vermetten, Ryan Dieter Lang, Andries Petrus Engelbrecht, Carola Doerr, Peter Korošec, Tome Eftimov

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

Comments To appear at GECCO 2023

PreQuant: A Task-agnostic Quantization Approach for Pre-trained Language Models

Zhuocheng Gong, Jiahao Liu, Qifan Wang, Yang Yang, Jingang Wang, Wei Wu, Yunsen Xian, Dongyan Zhao, Rui Yan

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

Comments Findings of ACL2023

Scalable Modular Synthetic Data Generation for Advancing Aerial Autonomy

Mehrnaz Sabet, Praveen Palanisamy, Sakshi Mishra

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

Comments 25 pages, 14 figures

A Methodology and Software Architecture to Support Explainability-by-Design

Trung Dong Huynh, Niko Tsakalakis, Ayah Helal, Sophie Stalla-Bourdillon, Luc Moreau

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

DialogVCS: Robust Natural Language Understanding in Dialogue System Upgrade

Zefan Cai, Xin Zheng, Tianyu Liu, Xu Wang, Haoran Meng, Jiaqi Han, Gang Yuan, Binghuai Lin, Baobao Chang, Yunbo Cao

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

Comments work in progress. The first three authors contribute equally

Bayesian Reinforcement Learning with Limited Cognitive Load

Dilip Arumugam, Mark K. Ho, Noah D. Goodman, Benjamin Van Roy

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

Pelphix: Surgical Phase Recognition from X-ray Images in Percutaneous Pelvic Fixation

Benjamin D. Killeen, Han Zhang, Jan Mangulabnan, Mehran Armand, Russel H. Taylor, Greg Osgood, Mathias Unberath

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

Constraining Representations Yields Models That Know What They Don't Know

Joao Monteiro, Pau Rodriguez, Pierre-Andre Noel, Issam Laradji, David Vazquez

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

Comments CR version published at ICLR 2023

Quantifying and Explaining Machine Learning Uncertainty in Predictive Process Monitoring: An Operations Research Perspective

Nijat Mehdiyev, Maxim Majlatow, Peter Fettke

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

From Natural Language to Simulations: Applying GPT-3 Codex to Automate Simulation Modeling of Logistics Systems

Ilya Jackson, Maria Jesus Saenz

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

Deep Generative Model and Its Applications in Efficient Wireless Network Management: A Tutorial and Case Study

Yinqiu Liu, Hongyang Du, Dusit Niyato, Jiawen Kang, Zehui Xiong, Dong In Kim, Abbas Jamalipour

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

Comments 8 pages, 5 figures

GPT4MIA: Utilizing Generative Pre-trained Transformer (GPT-3) as A Plug-and-Play Transductive Model for Medical Image Analysis

Yizhe Zhang, Danny Z. Chen

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

Comments Version 3: Added appendix with more results and visualizations. Questions and suggestions are welcome