Research library

Search papers on equipment connectivity, quality inspection, production analysis, and manufacturing work.

Search and filter

Paper list

T01. LLM agent orchestration and harness design

External research on how multiple language-model agents are planned, routed, and evaluated.

Show this topic only
  1. T01-14Candidate approachSince 2025

    Multi-Agent Collaboration via Evolving Orchestration

    Authors
    Yufan Dang, Chen Qian, Xueheng Luo, Jingru Fan, Zihao Xie, Ruijie Shi, Weize Chen, Cheng Yang, Xiaoyin Che, Ye Tian, Xuantang Xiong, Lei Han, Zhiyuan Liu, Maosong Sun
    Year
    2025
    Venue
    NeurIPS 2025

    Korean review of T01-14

  2. T01-4Candidate approach

    Generative Agents: Interactive Simulacra of Human Behavior

    Authors
    Joon Sung Park, Joseph C. O'Brien, Carrie J. Cai, Meredith Ringel Morris, Percy Liang, Michael S. Bernstein
    Year
    2023
    Venue
    UIST 2023

    Korean review of T01-4

  3. T01-5Candidate approach

    Reflexion: Language Agents with Verbal Reinforcement Learning

    Authors
    Noah Shinn, Federico Cassano, Edward Berman, Ashwin Gopinath, Karthik Narasimhan, Shunyu Yao
    Year
    2023
    Venue
    NeurIPS 2023

    Korean review of T01-5

  4. T01-6Candidate approach

    CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society

    Authors
    Guohao Li, Hasan Abed Al Kader Hammoud, Hani Itani, Dmitrii Khizbullin, Bernard Ghanem
    Year
    2023
    Venue
    NeurIPS 2023

    Korean review of T01-6

T02. Recursive language models and long-context handling

Research on reading documents that do not fit in one context window.

Show this topic only
  1. T02-4Candidate approach

    MemGPT: Towards LLMs as Operating Systems

    Authors
    Charles Packer, Sarah Wooders, Kevin Lin, Vivian Fang, Shishir G. Patil, Ion Stoica, Joseph E. Gonzalez
    Year
    2023
    Venue
    arXiv (UC Berkeley)

    Korean review of T02-4

  2. T02-8Candidate approach

    LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression

    Authors
    Huiqiang Jiang, Qianhui Wu, Xufang Luo, Dongsheng Li, Chin-Yew Lin, Yuqing Yang, Lili Qiu
    Year
    2024
    Venue
    ACL 2024

    Korean review of T02-8

  3. T02-10Candidate approach

    Efficient Streaming Language Models with Attention Sinks (StreamingLLM)

    Authors
    Guangxuan Xiao, Yuandong Tian, Beidi Chen, Song Han, Mike Lewis
    Year
    2024
    Venue
    ICLR 2024

    Korean review of T02-10

  4. T02-12Candidate approach

    Ring Attention with Blockwise Transformers for Near-Infinite Context

    Authors
    Hao Liu, Matei Zaharia, Pieter Abbeel
    Year
    2023
    Venue
    arXiv (UC Berkeley)

    Korean review of T02-12

  5. T02-13Candidate approach

    Extending Context Window of Large Language Models via Positional Interpolation

    Authors
    Shouyuan Chen, Sherman Wong, Liangjian Chen, Yuandong Tian
    Year
    2023
    Venue
    arXiv (Meta)

    Korean review of T02-13

  6. T02-14Candidate approach

    Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention

    Authors
    Tsendsuren Munkhdalai, Manaal Faruqui, Siddharth Gopal
    Year
    2024
    Venue
    arXiv (Google)

    Korean review of T02-14

  7. T02-15Candidate approach

    H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

    Authors
    Zhenyu Zhang, Ying Sheng, Tianyi Zhou, Tianlong Chen, Lianmin Zheng, Ruisi Cai, Zhao Song, Yuandong Tian, Christopher Re, Clark Barrett, Zhangyang Wang, Beidi Chen
    Year
    2023
    Venue
    NeurIPS 2023

    Korean review of T02-15

T03. Tool use, function calling, and the Model Context Protocol

External research and specifications for letting a model call outside tools.

Show this topic only
  1. T03-8Candidate approach

    ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs

    Authors
    Yujia Qin, Shihao Liang, Yining Ye, Kunlun Zhu, Lan Yan, Yaxi Lu, Yankai Lin, Xin Cong, Xiangru Tang, Bill Qian, Sihan Zhao, Lauren Hong, Runchu Tian, Ruobing Xie, Jie Zhou, Mark Gerstein, Dahai Li, Zhiyuan Liu, Maosong Sun
    Year
    2024
    Venue
    ICLR 2024

    Korean review of T03-8

T04. Planning, reflection, judging, and self-improving agents

Research on step-by-step reasoning, self-critique, and model-as-judge evaluation.

Show this topic only
  1. T04-8Candidate approach

    G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment

    Authors
    Yang Liu, Dan Iter, Yichong Xu, Shuohang Wang, Ruochen Xu, Chenguang Zhu
    Year
    2023
    Venue
    EMNLP 2023

    Korean review of T04-8

  2. T04-10Candidate approach

    Agent-as-a-Judge: Evaluate Agents with Agents

    Authors
    Mingchen Zhuge, Changsheng Zhao, Dylan Ashley, Wenyi Wang, Dmitrii Khizbullin, Yunyang Xiong, Zechun Liu, Ernie Chang, Raghuraman Krishnamoorthi, Yuandong Tian, Yangyang Shi, Vikas Chandra, Jürgen Schmidhuber
    Year
    2024
    Venue
    arXiv

    Korean review of T04-10

  3. T04-12Candidate approach

    Self-Rewarding Language Models

    Authors
    Weizhe Yuan, Richard Yuanzhe Pang, Kyunghyun Cho, Xian Li, Sainbayar Sukhbaatar, Jing Xu, Jason Weston
    Year
    2024
    Venue
    ICML 2024

    Korean review of T04-12

  4. T04-13Candidate approach

    Voyager: An Open-Ended Embodied Agent with Large Language Models

    Authors
    Guanzhi Wang, Yuqi Xie, Yunfan Jiang, Ajay Mandlekar, Chaowei Xiao, Yuke Zhu, Linxi Fan, Anima Anandkumar
    Year
    2024

    Korean review of T04-13

  5. T04-14Candidate approach

    STaR: Bootstrapping Reasoning With Reasoning

    Authors
    Eric Zelikman, Yuhuai Wu, Jesse Mu, Noah D. Goodman
    Year
    2022
    Venue
    NeurIPS 2022

    Korean review of T04-14

T05. Human review and approval workflows

Human-in-the-loop and approval research, including automation-induced complacency.

Show this topic only
  1. T05-22Candidate approachSince 2025

    What You Approve Is What Executes: Consent Integrity for Black-Box LLM Agents

    Authors
    Xiaoqi Weng
    Year
    2026
    Venue
    arXiv 2026-06 1

    Korean review of T05-22

  2. T05-23Candidate approachSince 2025

    Oversight Has a Capacity: Calibrating Agent Guards to a Subjective, Fatiguing Human

    Authors
    Emre Turan
    Year
    2026
    Venue
    arXiv 2026-06 8

    Korean review of T05-23

  3. T05-24Candidate approach

    Deep reinforcement learning from human preferences

    Authors
    Paul Christiano, Jan Leike, Tom B. Brown, Miljan Martic, Shane Legg, Dario Amodei
    Year
    2017
    Venue
    NIPS 2017 (Advances in Neural Information Processing Systems 30)

    Korean review of T05-24

  4. T05-25Candidate approach

    Human-in-the-loop machine learning: a state of the art

    Authors
    Eduardo Mosqueira-Rey, Elena Hernandez-Pereira, David Alonso-Rios, Jose Bobes-Bascaran, Angel Fernandez-Leal
    Year
    2023
    Venue
    Artificial Intelligence Review vol. 56 no. 4 3005-3054

    Korean review of T05-25

T06. RAG, knowledge graphs, ontologies, and provenance

Retrieval-augmented generation and structured knowledge with traceable sources.

Show this topic only
  1. T06-6Candidate approach

    HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models

    Authors
    Bernal Jimenez Gutierrez, Yiheng Shu, Yu Gu, Michihiro Yasunaga, Yu Su
    Year
    2024
    Venue
    NeurIPS 2024

    Korean review of T06-6

T07. Structured output, schema validation, and document understanding

Research on forcing machine-checkable output and reading business documents.

Show this topic only
  1. T07-4Candidate approach

    Nougat: Neural Optical Understanding for Academic Documents

    Authors
    Lukas Blecher, Guillem Cucurull, Thomas Scialom, Robert Stojnic
    Year
    2023
    Venue
    arXiv (Meta AI)

    Korean review of T07-4

T08. OCR, vision-language models, and industrial display reading

Research on reading meters, indicators, and shop-floor displays from images.

Show this topic only
  1. T08-14Candidate approachSince 2025

    Qwen2.5-VL Technical Report

    Authors
    Shuai Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Sibo Song, Kai Dang (27 authors in total)
    Year
    2025
    Venue
    arXiv (cs.CV, cs.CL)

    Korean review of T08-14

  2. T08-7Candidate approach

    TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models

    Authors
    Minghao Li, Tengchao Lv, Jingye Chen, Lei Cui, Yijuan Lu, Dinei Florencio, Cha Zhang, Zhoujun Li, Furu Wei
    Year
    2023
    Venue
    Proceedings of the AAAI Conference on Artificial Intelligence 37(11), 13094-13102 (2023)

    Korean review of T08-7

  3. T08-11Candidate approach

    OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models

    Authors
    Yuliang Liu, Zhang Li, Mingxin Huang, Biao Yang, Wenwen Yu, Chunyuan Li, Xucheng Yin, Cheng-lin Liu, Lianwen Jin, Xiang Bai
    Year
    2024
    Venue
    Science China Information Sciences (2024)

    Korean review of T08-11

  4. T08-13Candidate approach

    Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

    Authors
    Peng Wang, Shuai Bai, Sinan Tan, Shijie Wang, Zhihao Fan, Jinze Bai, Keqin Chen (19 authors in total)
    Year
    2024
    Venue
    arXiv (cs.CV)

    Korean review of T08-13

T09. Industrial time series, anomaly detection, and predictive maintenance

Sensor-driven fault detection, remaining useful life, and condition monitoring research.

Show this topic only
  1. T09-16Candidate approach

    Deep learning models for predictive maintenance: a survey, comparison, challenges and prospects

    Authors
    Oscar Serradilla, Ekhi Zugasti, Jon Rodriguez, Urko Zurutuza
    Year
    2022
    Venue
    Applied Intelligence vol. 52 no. 10 pp. 10934 pp. 10964

    Korean review of T09-16

T10. AutoML, model selection, evaluation design, and experiment tracking

Research on choosing and validating models instead of shipping a single fitted model.

Show this topic only
  1. T10-4Candidate approach

    Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization

    Authors
    Lisha Li, Kevin Jamieson, Giulia DeSalvo, Afshin Rostamizadeh, Ameet Talwalkar
    Year
    2018
    Venue
    Journal of Machine Learning Research 18 185, pp. 1-52

    Korean review of T10-4

  2. T10-5Candidate approach

    BOHB: Robust and Efficient Hyperparameter Optimization at Scale

    Authors
    Stefan Falkner, Aaron Klein, Frank Hutter
    Year
    2018
    Venue
    ICML 2018

    Korean review of T10-5

  3. T10-6Candidate approach

    Optuna: A Next-generation Hyperparameter Optimization Framework

    Authors
    Takuya Akiba, Shotaro Sano, Toshihiko Yanase, Takeru Ohta, Masanori Koyama
    Year
    2019
    Venue
    KDD 2019 Applied Data Science Track

    Korean review of T10-6

  4. T10-15Candidate approach

    Model Cards for Model Reporting

    Authors
    Margaret Mitchell, Simone Wu, Andrew Zaldivar, Parker Barnes, Lucy Vasserman, Ben Hutchinson, Elena Spitzer, Inioluwa Deborah Raji, Timnit Gebru
    Year
    2019
    Venue
    ACM FAT* 2019

    Korean review of T10-15

  5. T10-16Candidate approach

    Datasheets for Datasets

    Authors
    Timnit Gebru, Jamie Morgenstern, Briana Vecchione, Jennifer Wortman Vaughan, Hanna Wallach, Hal Daume III, Kate Crawford
    Year
    2021
    Venue
    Communications of the ACM vol. 64 no. 12 pp. 86-92

    Korean review of T10-16

T11. Object detection, multi-object tracking, and video understanding

Detection and tracking backbones behind camera-based safety and inspection work.

Show this topic only
  1. T11-6.3Candidate approachSince 2025

    SAM 2: Segment Anything in Images and Videos

    Authors
    Nikhila Ravi and 17 others (Meta FAIR)
    Year
    2025

    Korean review of T11-6.3

  2. T11-2.7Candidate approach

    DETRs Beat YOLOs on Real-time Object Detection (RT-DETR)

    Authors
    Yian Zhao, Wenyu Lv, Shangliang Xu, Jinman Wei, Guanzhong Wang, Qingqing Dang, Yi Liu, Jie Chen
    Year
    2024

    Korean review of T11-2.7

  3. T11-2.8Candidate approach

    Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection

    Authors
    Shilong Liu, Zhaoyang Zeng, Tianhe Ren, Feng Li, Hao Zhang, Jie Yang, Qing Jiang, Chunyuan Li, Jianwei Yang, Hang Su, Jun Zhu, Lei Zhang
    Year
    2024

    Korean review of T11-2.8

  4. T11-2.9Candidate approach

    YOLOv10: Real-Time End-to-End Object Detection

    Authors
    Ao Wang, Hui Chen, Lihao Liu, Kai Chen, Zijia Lin, Jungong Han, Guiguang Ding
    Year
    2024

    Korean review of T11-2.9

  5. T11-3.4Candidate approach

    Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking (OC-SORT)

    Authors
    Jinkun Cao, Jiangmiao Pang, Xinshuo Weng, Rawal Khirodkar, Kris Kitani
    Year
    2023

    Korean review of T11-3.4

  6. T11-5.3Candidate approach

    VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

    Authors
    Zhan Tong, Yibing Song, Jue Wang, Limin Wang
    Year
    2022

    Korean review of T11-5.3

T12. Video understanding and evidence selection with vision-language models

Research on explaining what a camera saw and pointing back to the evidence frame.

Show this topic only
  1. T12-5Candidate approach

    A Simple LLM Framework for Long-Range Video Question-Answering (LLoVi)

    Authors
    Ce Zhang, Taixi Lu, Md Mohaiminul Islam, Ziyang Wang, Shoubin Yu, Mohit Bansal, Gedas Bertasius
    Year
    2024
    Venue
    EMNLP 2024 main

    Korean review of T12-5

T13. Edge AI, streaming inference, and resource scheduling

Running models near the machine under limited compute and latency budgets.

Show this topic only
  1. T13-9Candidate approach

    INFaaS

    Authors
    Francisco Romero, Qian Li, Neeraja J. Yadwadkar, Christos Kozyrakis
    Year
    2021
    Venue
    USENIX ATC 2021, pp. 397-411

    Korean review of T13-9

  2. T13-10Candidate approach

    Orca: A Distributed Serving System for Transformer-Based Generative Models

    Authors
    Gyeong-In Yu, Joo Seong Jeong, Geon-Woo Kim, Soojeong Kim, Byung-Gon Chun
    Year
    2022
    Venue
    USENIX OSDI 2022, pp. 521-538

    Korean review of T13-10

  3. T13-11Candidate approach

    Efficient Memory Management for Large Language Model Serving with PagedAttention

    Authors
    Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph E. Gonzalez, Hao Zhang, Ion Stoica
    Year
    2023
    Venue
    ACM SOSP 2023, pp. 611-626

    Korean review of T13-11

  4. T13-12Candidate approach

    Gandiva: Introspective Cluster Scheduling for Deep Learning

    Authors
    Wencong Xiao, Romil Bhardwaj, Ramachandran Ramjee, Muthian Sivathanu, Nipun Kwatra, Zhenhua Han, Pratyush Patel, Xuan Peng, Hanyu Zhao, Quanlu Zhang, Fan Yang, Lidong Zhou
    Year
    2018
    Venue
    USENIX OSDI 2018, pp. 595-610

    Korean review of T13-12

  5. T13-13Candidate approach

    Tiresias: A GPU Cluster Manager for Distributed Deep Learning

    Authors
    Juncheng Gu, Mosharaf Chowdhury, Kang G. Shin, Yibo Zhu, Myeongjae Jeon, Junjie Qian, Hongqiang Liu, Chuanxiong Guo
    Year
    2019
    Venue
    USENIX NSDI 2019, pp. 485-500

    Korean review of T13-13

  6. T13-14Candidate approach

    AntMan: Dynamic Scaling on GPU Clusters for Deep Learning

    Authors
    Wencong Xiao, Shiru Ren, Yong Li, Yang Zhang, Pengyang Hou, Zhi Li, Yihui Feng, Wei Lin, Yangqing Jia
    Year
    2020
    Venue
    USENIX OSDI 2020, pp. 533-548

    Korean review of T13-14

  7. T13-15Candidate approach

    Heterogeneity-Aware Cluster Scheduling Policies for Deep Learning Workloads

    Authors
    Deepak Narayanan, Keshav Santhanam, Fiodar Kazhamiaka, Amar Phanishayee, Matei Zaharia
    Year
    2020
    Venue
    USENIX OSDI 2020, pp. 481-498

    Korean review of T13-15

  8. T13-16Candidate approach

    Pollux: Co-adaptive Cluster Scheduling for Goodput-Optimized Deep Learning

    Authors
    Aurick Qiao, Sang Keun Choe, Suhas Jayaram Subramanya, Willie Neiswanger, Qirong Ho, Hao Zhang, Gregory R. Ganger, Eric P. Xing
    Year
    2021
    Venue
    USENIX OSDI 2021, pp. 1-18

    Korean review of T13-16

T14. Industrial protocol translation, code generation, and program synthesis

Research on generating and checking the code that talks to plant equipment.

Show this topic only
  1. T14-4Candidate approach

    Agents4PLC: Automating Closed-loop PLC Code Generation and Verification in Industrial Control Systems using LLM-based Agents

    Authors
    Zihan Liu, Ruinan Zeng, Dongxia Wang, Gengyun Peng, Jingyi Wang, Qiang Liu, Peiyu Liu, Wenhai Wang
    Year
    2024
    Venue
    arXiv, pp. 12

    Korean review of T14-4

  2. T14-8Candidate approach

    Discoverer: Automatic Protocol Reverse Engineering from Network Traces

    Authors
    Weidong Cui (Microsoft Research), Jayanthkumar Kannan (UC Berkeley), Helen J. Wang (Microsoft Research)
    Year
    2007
    Venue
    16th USENIX Security Symposium, 2007

    Korean review of T14-8

  3. T14-9Candidate approach

    NetPlier: Probabilistic Network Protocol Reverse Engineering from Message Traces

    Authors
    Yapeng Ye, Zhuo Zhang, Fei Wang, Xiangyu Zhang, Dongyan Xu (Purdue University)
    Year
    2021
    Venue
    NDSS 2021

    Korean review of T14-9

  4. T14-14Candidate approach

    Polyglot: Automatic Extraction of Protocol Message Format using Dynamic Binary Analysis

    Authors
    Juan Caballero, Heng Yin, Zhenkai Liang, Dawn Song
    Year
    2007
    Venue
    ACM CCS 2007 (14th ACM Conference on Computer and Communications Security), pp. 317-329

    Korean review of T14-14

T15. OPC UA, Asset Administration Shell, MQTT, and manufacturing interoperability

Specifications and research for describing equipment and moving its data.

Show this topic only
  1. T15-2.6Candidate approach

    Open-Source Implementations of the Reactive Asset Administration Shell: A Survey

    Authors
    Michael Jacoby, Michael Baumann, Tino Bischoff, Hans Mees, Jens Müller, Ljiljana Stojanovic, Friedrich Volz
    Year
    2023
    Venue
    Sensors 23(11), 5229, 2023

    Korean review of T15-2.6

  2. T15-2.7Candidate approach

    Generation of Asset Administration Shell With Large Language Model Agents: Toward Semantic Interoperability in Digital Twins in the Context of Industry 4.0

    Authors
    Yuchen Xia, Zhewen Xiao, Nasser Jazdi, Michael Weyrich
    Year
    2024
    Venue
    IEEE Access, vol.12, pp.84863-84877, 2024. DOI 10.1109/ACCESS.2024.3415470

    Korean review of T15-2.7

T16. Manufacturing knowledge graphs and semantic layers

Research on giving plant data a shared meaning across systems.

Show this topic only
  1. T16-8Candidate approachSince 2025

    Intent-Driven Smart Manufacturing Integrating Knowledge Graphs and Large Language Models

    Authors
    Takoua Jradi, John Violos, Dimitrios Spatharakis, Lydia Mavraidi, Ioannis Dimolitsas, Aris Leivadeas, Symeon Papavassiliou
    Year
    2026
    Venue
    arXiv (cs.AI)

    Korean review of T16-8

  2. T16-4Candidate approach

    Literal-Aware Knowledge Graph Embedding for Welding Quality Monitoring: A Bosch Case

    Authors
    Zhipeng Tan, Baifan Zhou, Zhuoxun Zheng, Ognjen Savkovic, Ziqi Huang, Irlan Grangel Gonzalez, Ahmet Soylu, Evgeny Kharlamov
    Year
    2023
    Venue
    ISWC 2023 In-Use Track

    Korean review of T16-4

T17. Natural language to SQL and grounded report generation

Research on turning a question into a checked query and a sourced report.

Show this topic only
  1. T17-19Candidate approach

    InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks

    Authors
    Xueyu Hu, Ziyu Zhao, Shuang Wei
    Year
    2024
    Venue
    ICML 2024, PMLR vol. 235 pp. 19544-19572

    Korean review of T17-19

T18. AI quality management, model monitoring, and audit trails

Research and standards for keeping a deployed model accountable over time.

Show this topic only
  1. T18-11Candidate approachSince 2025

    Time to Retrain? Detecting Concept Drifts in Machine Learning Systems

    Authors
    Tri Minh Triet Pham, Karthikeyan Premkumar, Mohamed Naili, Jinqiu Yang
    Year
    2025
    Venue
    ICSE 2025

    Korean review of T18-11

From research to product use

Operating capabilities, pilots, and technologies in development are identified separately.

View technology