연구자료실
설비 연결, 품질 검사, 생산 분석과 제조 업무에 관련된 외부 논문입니다.
연구자료 검색
논문 목록
T01. LLM 에이전트 오케스트레이션과 하네스
이 주제만 보기- T01-13유사문제2025년 이후
Why Do Multi-Agent LLM Systems Fail?
- T01-14후보2025년 이후
Multi-Agent Collaboration via Evolving Orchestration
- T01-19유사문제2025년 이후
tau^2-Bench: Evaluating Conversational Agents in a Dual-Control Environment
- T01-12유사문제2025년 이후
tau-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
- T01-1구조대응
ReAct: Synergizing Reasoning and Acting in Language Models
- T01-2구조대응
Toolformer: Language Models Can Teach Themselves to Use Tools
- T01-3구조대응
HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face
- T01-4후보
Generative Agents: Interactive Simulacra of Human Behavior
- T01-5후보
Reflexion: Language Agents with Verbal Reinforcement Learning
- T01-6후보
CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society
- T01-7유사문제
WebArena: A Realistic Web Environment for Building Autonomous Agents
- T01-8유사문제
SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
- T01-9구조대응
AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversations
- T01-10구조대응
MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
- T01-11구조대응
SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering
- T01-15구조대응
Tree of Thoughts: Deliberate Problem Solving with Large Language Models
- T01-16유사문제
AgentBench: Evaluating LLMs as Agents
- T01-17유사문제
GAIA: a benchmark for General AI Assistants
- T01-18유사문제
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
T02. Recursive Language Model과 긴 문맥 처리
이 주제만 보기- T02-1구조대응2025년 이후
Recursive Language Models
- T02-2구조대응
RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
- T02-3유사문제
Walking Down the Memory Maze: Beyond Context Limit through Interactive Reading (MemWalker)
- T02-4후보
MemGPT: Towards LLMs as Operating Systems
- T02-5구조대응
Chain of Agents: Large Language Models Collaborating on Long-Context Tasks
- T02-6유사문제
Lost in the Middle: How Language Models Use Long Contexts
- T02-7유사문제
RULER: What's the Real Context Size of Your Long-Context Language Models?
- T02-8후보
LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression
- T02-9구조대응
Recursively Summarizing Books with Human Feedback
- T02-10후보
Efficient Streaming Language Models with Attention Sinks (StreamingLLM)
- T02-11유사문제
LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding
- T02-12후보
Ring Attention with Blockwise Transformers for Near-Infinite Context
- T02-13후보
Extending Context Window of Large Language Models via Positional Interpolation
- T02-14후보
Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention
- T02-15후보
H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models
T03. tool use, function calling과 MCP
이 주제만 보기- T03-13유사문제2025년 이후
Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions
- T03-12유사문제2025년 이후
The Berkeley Function Calling Leaderboard (BFCL): From Tool Use to Agentic Evaluation of Large Language Models
- T03-9유사문제2025년 이후
Tool Learning with Foundation Models
- T03-1구조대응
WebGPT: Browser-assisted question-answering with human feedback
- T03-2구조대응
MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning
- T03-6유사문제
API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs
- T03-7구조대응
Gorilla: Large Language Model Connected with Massive APIs
- T03-8후보
ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs
T04. 계획 수립, 반성, 평가자, 자기개선 에이전트
이 주제만 보기- T04-1구조대응
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- T04-4구조대응
Self-Refine: Iterative Refinement with Self-Feedback
- T04-7구조대응
Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
- T04-8후보
G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment
- T04-9유사문제
Let's Verify Step by Step
- T04-10후보
Agent-as-a-Judge: Evaluate Agents with Agents
- T04-11유사문제
Large Language Models Cannot Self-Correct Reasoning Yet
- T04-12후보
Self-Rewarding Language Models
- T04-13후보
Voyager: An Open-Ended Embodied Agent with Large Language Models
- T04-14후보
STaR: Bootstrapping Reasoning With Reasoning
- T04-15구조대응
Constitutional AI: Harmlessness from AI Feedback
- T04-16유사문제
CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing
T05. 사람 검토와 승인 절차 (human in the loop, approval workflow)
이 주제만 보기- T05-22후보2025년 이후
What You Approve Is What Executes: Consent Integrity for Black-Box LLM Agents
- T05-23후보2025년 이후
Oversight Has a Capacity: Calibrating Agent Guards to a Subjective, Fatiguing Human
- T05-21유사문제2025년 이후
Human-In-the-Loop Software Development Agents (HULA)
- T05-1유사문제
Ironies of Automation
- T05-2유사문제
The Out-of-the-Loop Performance Problem and Level of Control in Automation
- T05-3유사문제
Humans and Automation: Use, Misuse, Disuse, Abuse
- T05-4구조대응
A Model for Types and Levels of Human Interaction with Automation
- T05-5유사문제
Complacency and Bias in Human Use of Automation: An Attentional Integration
- T05-6구조대응
On Optimum Recognition Error and Reject Tradeoff
- T05-7구조대응
Learning with Rejection
- T05-8구조대응
Predict Responsibly: Improving Fairness and Accuracy by Learning to Defer
- T05-9구조대응
SelectiveNet: A Deep Neural Network with an Integrated Reject Option
- T05-10구조대응
Consistent Estimators for Learning to Defer to an Expert
- T05-11구조대응
Learning to Complement Humans
- T05-12구조대응
Machine Learning with a Reject Option: A survey
- T05-13유사문제
Trust in Automation: Designing for Appropriate Reliance
- T05-14유사문제
Guidelines for Human-AI Interaction
- T05-15유사문제
Effect of Confidence and Explanation on Accuracy and Trust Calibration in AI-Assisted Decision Making
- T05-16유사문제
Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance
- T05-17유사문제
To Trust or to Think: Cognitive Forcing Functions Can Reduce Overreliance on AI in AI-assisted Decision-making
- T05-18유사문제
The flaws of policies requiring human oversight of government algorithms
- T05-19구조대응
Identifying the Risks of LM Agents with an LM-Emulated Sandbox (ToolEmu)
- T05-20구조대응
AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
- T05-24후보
Deep reinforcement learning from human preferences
- T05-25후보
Human-in-the-loop machine learning: a state of the art
T06. RAG, 지식그래프, 온톨로지, 출처 추적
이 주제만 보기- T06-14유사문제2025년 이후
Enhancing retrieval-augmented generation for interoperable industrial knowledge representation and inference toward cognitive digital twins
- T06-1구조대응
Dense Passage Retrieval for Open-Domain Question Answering
- T06-2유사문제
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
- T06-3구조대응
Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering
- T06-4유사문제
Retrieval-Augmented Generation for Large Language Models: A Survey
- T06-5구조대응
From Local to Global: A Graph RAG Approach to Query-Focused Summarization
- T06-6후보
HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models
- T06-7구조대응
Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
- T06-8구조대응
Enabling Large Language Models to Generate Text with Citations
- T06-9유사문제
Measuring Attribution in Natural Language Generation Models
- T06-10구조대응
Provenance Semirings
- T06-11구조대응
Provenance in Databases: Why, How, and Where
- T06-12유사문제
Knowledge Graphs
- T06-13유사문제
A benchmark dataset with Knowledge Graph generation for Industry 4.0 production lines
T07. 구조화 출력, 스키마 검증, 문서 이해
이 주제만 보기- T07-10구조대응2025년 이후
XGrammar: Flexible and Efficient Structured Generation Engine for Large Language Models
XGrammar
- T07-11유사문제2025년 이후
JSONSchemaBench: A Rigorous Benchmark of Structured Outputs for Language Models
JSONSchemaBench
- T07-1구조대응
LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking
LayoutLMv3
- T07-2구조대응
OCR-free Document Understanding Transformer
Donut
- T07-3유사문제
TableFormer: Table Structure Understanding with Transformers
TableFormer
- T07-4후보
Nougat: Neural Optical Understanding for Academic Documents
Nougat
- T07-5유사문제
FUNSD: A Dataset for Form Understanding in Noisy Scanned Documents
FUNSD
- T07-6유사문제
DocVQA: A Dataset for VQA on Document Images
DocVQA
- T07-7구조대응
PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models
PICARD
- T07-8구조대응
Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning
Grammar-Constrained Decoding (GCD)
- T07-9구조대응
Efficient Guided Generation for Large Language Models
Outlines (Efficient Guided Generation)
- T07-12유사문제
Let Me Speak Freely? A Study On The Impact Of Format Restrictions On Large Language Model Performance
Let Me Speak Freely?
- T07-13유사문제
Grammar-Aligned Decoding
Grammar-Aligned Decoding (GAD)
T08. OCR, VLM과 산업 현장 표시장치 판독
이 주제만 보기- T08-1유사문제2025년 이후
Do Vision-Language Models Measure Up? Benchmarking Visual Measurement Reading with MeasureBench
MeasureBench (계측기 판독 평가 묶음)
- T08-2구조대응2025년 이후
DialBench: Towards Accurate Reading Recognition of Pointer Meter using Large Foundation Models
DialBench와 MRLM (바늘형 계기 판독)
- T08-14후보2025년 이후
Qwen2.5-VL Technical Report
Qwen2.5-VL (문서 판독과 위치 지정을 강화한 후속 세대)
- T08-3유사문제
Convolutional Neural Networks for Automatic Meter Reading
계량기 자동 판독을 위한 합성곱 신경망
- T08-4유사문제
Utilizing Smartphone-Based Machine Learning in Medical Monitor Data Collection: Seven Segment Digit Recognition
7세그먼트 표시창 숫자 인식
- T08-5구조대응
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
CRNN (글자 줄을 통째로 읽는 기본 구조)
- T08-6구조대응
Real-time Scene Text Detection with Differentiable Binarization
DBNet (글자 위치를 실시간으로 찾기)
- T08-7후보
TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models
TrOCR (트랜스포머만으로 만든 문자인식)
- T08-9구조대응
General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model
GOT-OCR2.0 (통합 단대단 문자인식)
- T08-11후보
OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models
OCRBench (다중모달 모델의 문자인식 평가)
- T08-12구조대응
ScreenAI: A Vision-Language Model for UI and Infographics Understanding
ScreenAI (화면과 인포그래픽 이해)
- T08-13후보
Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
Qwen2-VL
T09. 산업 시계열, 이상탐지, 예지보전
이 주제만 보기- T09-1유사문제
Current Time Series Anomaly Detection Benchmarks are Flawed and are Creating the Illusion of Progress
조기공개(early access)는 2021년에 등록되었다. 그래서 Crossref에는 연도 2021, 쪽수 1-1로 남아 있다. 확정 게재본은 DBLP와 IEEE 권호 정보 기준으로 35권 3호 2023년이다. 이 문서는 확정 게재본 기준으로 (Wu, Keogh, TKDE, 2023)으로 인용한다. 사전공개본은 arXiv:2009.13807이고 초판 투고일은 2020년 9월 29일이다. 요약본이 IEEE ICDE 2022에 1479쪽부터 1480쪽으로 실렸다(DOI 10.1109/ICDE53745.2022.00116).
- T09-2유사문제
Towards a Rigorous Evaluation of Time-series Anomaly Detection
사전공개본은 arXiv:2109.05257이고 초판은 2021년이다. 이 문서는 학회 게재본 기준으로 2022년으로 인용한다.
- T09-3유사문제
The Elephant in the Room: Towards A Reliable Time-Series Anomaly Detection Benchmark
- T09-4유사문제
Volume Under the Surface: A New Accuracy Evaluation Measure for Time-Series Anomaly Detection
- T09-5유사문제
A Review on Outlier/Anomaly Detection in Time Series Data
ACM 디지털 라이브러리 게재일은 2021년 4월 17일이다. 54권 3호의 지면 발행일은 2022년 4월이라 DBLP는 이 논문을 2022년으로 적는다. 이 문서는 게재일 기준으로 2021년으로 인용하고, 2022년 표기를 만나면 같은 논문으로 본다. 사전공개본은 arXiv:2002.04236이다.
- T09-6구조대응
Anomaly Detection in Time Series: A Comprehensive Evaluation
- T09-7유사문제
Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding
- T09-8구조대응
Robust Anomaly Detection for Multivariate Time Series through Stochastic Recurrent Neural Network (OmniAnomaly)
- T09-9유사문제
A Dataset to Support Research in the Design of Secure Water Treatment Systems (SWaT)
학회는 2016년에 열렸고 논문집은 2017년에 나왔다. 이 문서는 논문집 발행 기준으로 2017년으로 인용하고, 학회 표기는 CRITIS 2016으로 함께 적는다.
- T09-10구조대응
Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy
arXiv 초판은 2021년이다. 이 문서는 학회 발표 기준으로 2022년으로 인용한다.
- T09-11구조대응
TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data
- T09-12구조대응
Time-Series Anomaly Detection Service at Microsoft
- T09-13유사문제
Damage Propagation Modeling for Aircraft Engine Run-to-Failure Simulation
- T09-14유사문제
A review on machinery diagnostics and prognostics implementing condition-based maintenance
- T09-15유사문제
Machinery health prognostics: A systematic review from data acquisition to RUL prediction
- T09-16후보
Deep learning models for predictive maintenance: a survey, comparison, challenges and prospects
사전공개본은 arXiv:2010.03207이다. 사전공개본은 2020년 10월 7일 투고이고 저자가 3명(Serradilla, Zugasti, Zurutuza), 제목 끝이 prospect로 단수다. 학술지판은 저자가 4명(Jon Rodriguez 추가)이고 제목 끝이 prospects로 복수다. 이 문서는 학술지판 기준으로 인용한다.
T10. AutoML, 모델 선택, 평가 설계, 실험 추적
이 주제만 보기- T10-1유사문제
Random Search for Hyper-Parameter Optimization
- T10-2구조대응
Auto-WEKA: Combined Selection and Hyperparameter Optimization of Classification Algorithms
- T10-3구조대응
Efficient and Robust Automated Machine Learning (auto-sklearn)
- T10-4후보
Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization
- T10-5후보
BOHB: Robust and Efficient Hyperparameter Optimization at Scale
- T10-6후보
Optuna: A Next-generation Hyperparameter Optimization Framework
- T10-7구조대응
AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data
- T10-8구조대응
Auto-Sklearn 2.0: Hands-free AutoML via Meta-Learning
- T10-9유사문제
AMLB: an AutoML Benchmark
- T10-10유사문제
Statistical Comparisons of Classifiers over Multiple Data Sets
- T10-11유사문제
On Over-fitting in Model Selection and Subsequent Selection Bias in Performance Evaluation
- T10-12유사문제
Evaluating time series forecasting models: An empirical study on performance estimation methods
- T10-13구조대응
OpenML: Networked Science in Machine Learning
- T10-14구조대응
Developments in MLflow: A System to Accelerate the Machine Learning Lifecycle
- T10-15후보
Model Cards for Model Reporting
- T10-16후보
Datasheets for Datasets
T11. 객체 검출, 다중 객체 추적, 영상 이해
이 주제만 보기- T11-6.3후보2025년 이후
SAM 2: Segment Anything in Images and Videos
위험 구역 경계와 사람 영역을 픽셀 단위로 나눠 침입 여부를 판정하는 데 적용 후보다.
- T11-1.1구조대응
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale (ViT)
아래 DETR 계열 검출기, VideoMAE, SAM이 모두 이 백본 계보 위에 서 있다. 우리가 트랜스포머 기반 인식기를 쓸 때 계보의 출발점으로 맞대볼 수 있다.
- T11-2.1구조대응
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
2단계 검출기 기준선이다. 뒤에 나오는 DETR 계열이 무엇을 대체했는지 재는 기준으로 맞대볼 수 있다.
- T11-2.2구조대응
You Only Look Once: Unified, Real-Time Object Detection (YOLO)
실시간 1단계 검출의 출발점이다. RT-DETR이 비교 대상으로 삼는 계열의 원논문이다.
- T11-2.3구조대응
Focal Loss for Dense Object Detection (RetinaNet)
YOLO에서 DETR로 넘어가는 사이의 1단계 검출기 표준 기준선이다. 초점 손실 자체는 불균형이 심한 우리 위험 이벤트 학습에도 맞대볼 수 있다.
- T11-2.4구조대응
End-to-End Object Detection with Transformers (DETR)
영상 안전 판단의 검출 단계에서 후처리 규칙을 줄이는 구조로 맞대볼 수 있다.
- T11-2.5구조대응
Deformable DETR: Deformable Transformers for End-to-End Object Detection
DETR에서 RT-DETR로 넘어가는 중간 단계다. 실시간 트랜스포머 검출기의 근거를 잇는 고리다.
- T11-2.6구조대응
DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection
RT-DETR이 비교 기준으로 삼는 DINO-R50이 이 논문이고, Grounding DINO의 이름과 뼈대도 여기서 온다. 두 논문을 읽으려면 이 문헌이 먼저다.
- T11-2.7후보
DETRs Beat YOLOs on Real-time Object Detection (RT-DETR)
현장 카메라 실시간 검출 엔진 교체 후보다.
- T11-2.8후보
Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection
안전모 미착용, 지게차 접근처럼 학습 데이터가 적은 새 위험 항목을 말로 정의해 잡는 데 후보다.
- T11-2.9후보
YOLOv10: Real-Time End-to-End Object Detection
2.7절 RT-DETR의 "NMS 때문에 YOLO가 느리다"는 주장에 대한 반대편 최신 근거다. 저사양 엣지 장비용 실시간 검출기 후보로 RT-DETR과 나란히 놓고 봐야 한다.
- T11-3.1구조대응
Simple Online and Realtime Tracking (SORT)
추적 계보의 첫 논문이다. 뒤 논문들이 무엇을 보완했는지 재는 기준선으로 맞대볼 수 있다.
- T11-3.2유사문제
Simple Online and Realtime Tracking with a Deep Association Metric (DeepSORT)
작업자와 지게차를 끊김 없이 따라가야 하는 우리 영상 안전 판단과 같은 문제를 다룬다.
- T11-3.3구조대응
ByteTrack: Multi-Object Tracking by Associating Every Detection Box
설비 사이에 사람이 가려지는 공장 화면에서 궤적 유지 로직으로 맞대볼 수 있다.
- T11-3.4후보
Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking (OC-SORT)
ByteTrack 다음 세대 추적기다. 사람이 방향을 급하게 바꾸는 작업 현장에 적용 후보다.
- T11-4.1구조대응
Evaluating Multiple Object Tracking Performance: The CLEAR MOT Metrics (MOTA, MOTP)
3.3절 ByteTrack의 MOTA 80.3 같은 수치가 바로 이 문헌이 정의한 지표다. MOTA 수치를 쓸 때 붙일 정의 문헌이다.
- T11-4.2구조대응
Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking (IDF1)
3장 여러 논문이 쓰는 IDF1 수치의 정의 문헌이다. 우리 추적 성능을 IDF1로 보고하려면 이 문헌을 붙여야 한다.
- T11-4.3구조대응
HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking
우리 추적 성능을 수치로 보고할 때 쓰는 현행 표준 지표다. 성능 주장에는 이 지표를 붙여야 한다.
- T11-4.4구조대응
MOT16: A Benchmark for Multi-Object Tracking
3장 추적 성능 수치가 대부분 MOT17 기준인데, MOT17을 따로 다룬 별도 논문은 확인하지 못했다. MOT17 기준 수치를 쓸 때는 이 MOT16 문헌과 6절 MOT20 문헌을 함께 근거로 붙인다.
- T11-5.1구조대응
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset (I3D)
영상 행동인식의 기준선이자 Kinetics의 출처다. 뒤 논문들의 성능 수치가 모두 이 데이터셋 기준이다.
- T11-5.2유사문제
SlowFast Networks for Video Recognition
작업자 행동을 실시간으로 판정하는 문제와 같은 문제를 다룬다.
- T11-5.3후보
VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training
라벨이 거의 없는 공장 CCTV를 자기지도로 미리 학습시키는 방식의 후보다.
- T11-6.1구조대응
Learning Transferable Visual Models From Natural Language Supervision (CLIP)
말로 물체를 정의해 찾는 개방어휘 검출의 토대다. Grounding DINO 같은 방식이 여기서 출발한다.
- T11-6.2구조대응
Segment Anything (SAM)
SAM 2의 원본이다. 픽셀 단위 영역 판정을 쓰려면 이 원논문의 한계부터 봐야 한다.
T12. 영상 이해와 근거 선택 (Vision-Language Model)
이 주제만 보기- T12-2구조대응2025년 이후
Adaptive Keyframe Sampling for Long Video Understanding
- T12-1구조대응2025년 이후
Frame-Voyager: Learning to Query Frames for Video Large Language Models
- T12-13유사문제2025년 이후
Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis
- T12-3구조대응
Self-Chained Image-Language Model for Video Localization and Question Answering (SeViLA)
- T12-4구조대응
VideoAgent: Long-form Video Understanding with Large Language Model as Agent
- T12-5후보
A Simple LLM Framework for Long-Range Video Question-Answering (LLoVi)
- T12-6유사문제
Can I Trust Your Answer? Visually Grounded Video Question Answering (NExT-GQA)
- T12-7구조대응
TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding
- T12-8구조대응
VTimeLLM: Empower LLM to Grasp Video Moments
- T12-9유사문제
QVHighlights: Detecting Moments and Highlights in Videos via Natural Language Queries (Moment-DETR)
- T12-11구조대응
BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
- T12-12유사문제
EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding
- T12-14유사문제
Evaluating Object Hallucination in Large Vision-Language Models (POPE)
- T12-15유사문제
VideoHallucer: Evaluating Intrinsic and Extrinsic Hallucinations in Large Video-Language Models
T13. 엣지 AI, 스트리밍 추론, 자원 스케줄링
이 주제만 보기- T13-1구조대응
Neurosurgeon: Collaborative Intelligence Between the Cloud and Mobile Edge
Neurosurgeon
- T13-2유사문제
Live Video Analytics at Scale with Approximation and Delay-Tolerance
VideoStorm
- T13-3유사문제
AWStream: Adaptive Wide-Area Streaming Analytics
AWStream
- T13-4유사문제
Chameleon: Scalable Adaptation of Video Analytics
Chameleon
- T13-5유사문제
Reducto: On-Camera Filtering for Resource-Efficient Real-Time Video Analytics
Reducto
- T13-6구조대응
Ekya: Continuous Learning of Video Analytics Models on Edge Compute Servers
Ekya
- T13-7구조대응
Clipper: A Low-Latency Online Prediction Serving System
Clipper
- T13-8구조대응
Serving DNNs like Clockwork: Performance Predictability from the Bottom Up
Clockwork
- T13-9후보
INFaaS
- T13-10후보
Orca: A Distributed Serving System for Transformer-Based Generative Models
Orca
- T13-11후보
Efficient Memory Management for Large Language Model Serving with PagedAttention
vLLM
- T13-12후보
Gandiva: Introspective Cluster Scheduling for Deep Learning
Gandiva
- T13-13후보
Tiresias: A GPU Cluster Manager for Distributed Deep Learning
Tiresias
- T13-14후보
AntMan: Dynamic Scaling on GPU Clusters for Deep Learning
AntMan
- T13-15후보
Heterogeneity-Aware Cluster Scheduling Policies for Deep Learning Workloads
Gavel
- T13-16후보
Pollux: Co-adaptive Cluster Scheduling for Goodput-Optimized Deep Learning
Pollux
- T13-17구조대응
MLPerf Inference Benchmark
- T13-18유사문제
MillWheel: Fault-Tolerant Stream Processing at Internet Scale
MillWheel
- T13-19유사문제
The Dataflow Model: A Practical Approach to Balancing Correctness, Latency, and Cost in Massive-Scale, Unbounded, Out-of-Order Data Processing
Dataflow Model
T14. 산업용 프로토콜 번역, 코드 생성, 프로그램 합성
이 주제만 보기- T14-5구조대응2025년 이후
Training LLMs for Generating IEC 61131-3 Structured Text with Online Feedback
- T14-1유사문제
Evaluating Large Language Models Trained on Code
- T14-2유사문제
ChatGPT for PLC/DCS Control Logic Generation
- T14-3구조대응
LLM4PLC: Harnessing Large Language Models for Verifiable Programming of PLCs in Industrial Control Systems
- T14-4후보
Agents4PLC: Automating Closed-loop PLC Code Generation and Verification in Industrial Control Systems using LLM-based Agents
- T14-6유사문제
Automated Control Logic Test Case Generation using Large Language Models
- T14-7유사문제
Automated generation of OPC UA information models - A review and outlook
- T14-8후보
Discoverer: Automatic Protocol Reverse Engineering from Network Traces
- T14-9후보
NetPlier: Probabilistic Network Protocol Reverse Engineering from Message Traces
- T14-10구조대응
Automated Attack Synthesis by Extracting Finite State Machines from Protocol Specification Documents
- T14-11구조대응
Syntax-Guided Synthesis
- T14-12구조대응
Automating string processing in spreadsheets using input-output examples
- T14-13구조대응
Combinatorial Sketching for Finite Programs
- T14-14후보
Polyglot: Automatic Extraction of Protocol Message Format using Dynamic Binary Analysis
- T14-15유사문제
Program Synthesis with Large Language Models
T15. OPC UA, Asset Administration Shell, MQTT과 제조 상호운용성
이 주제만 보기- T15-2.10구조대응2025년 이후
ESP32-Based Sparkplug B Gateway Framework for Brownfield PLC Integration into an IIoT Unified Namespace: A Data Foundation for Intelligent Industrial Systems
Šenk 외 (2026) 구형 PLC를 Sparkplug B 통합 이름공간에 붙이는 게이트웨이
- T15-2.1유사문제
The Future of Industrial Communication: Automation Networks in the Era of the Internet of Things and Industry 4.0
Wollschlaeger 외 (2017) 산업통신의 미래, 프로토콜 지형 개괄
- T15-2.2유사문제
Insights into Mapping Solutions Based on OPC UA Information Model Applied to the Industry 4.0 Asset Administration Shell
Cavalieri & Salafia (2020) OPC UA 정보모델로 AAS를 표현하는 방법
- T15-2.3구조대응
Reusing OPC UA information models in the Asset Administration Shell
Weiss & Reichelt (2023) OPC UA 노드셋을 AAS 서브모델로 재사용
- T15-2.4유사문제
OPC UA versus ROS, DDS, and MQTT: Performance Evaluation of Industry 4.0 Protocols
Profanter 외 (2019) OPC UA, ROS, DDS, MQTT 성능 비교
- T15-2.5구조대응
Evaluation and Extension of OPC UA Publish/Subscribe MQTT Binding
Raddatz 외 (2020) OPC UA PubSub의 MQTT 바인딩 구현과 지연 측정
- T15-2.6후보
Open-Source Implementations of the Reactive Asset Administration Shell: A Survey
Jacoby 외 (2023) 오픈소스 AAS 구현체 비교 조사
- T15-2.7후보
Generation of Asset Administration Shell With Large Language Model Agents: Toward Semantic Interoperability in Digital Twins in the Context of Industry 4.0
Xia 외 (2024) 대형 언어모델 에이전트로 AAS 자동 생성
- T15-2.8구조대응
File- and API-based interoperability of digital twins by model transformation: An IIoT case study using asset administration shell
Platenius-Mohr 외 (2020) 모델 변환으로 디지털 트윈 상호운용성 확보
- T15-2.9유사문제
Streaming Machine Generated Data via the MQTT Sparkplug B Protocol for Smart Factory Operations
Koprov 외 (2022) MQTT Sparkplug B로 공작기계 데이터 스트리밍
- T15-2.11구조대응
A Cyber-Physical Machine Tools Platform using OPC UA and MTConnect
Liu 외 (2019) OPC UA와 MTConnect를 잇는 공작기계 플랫폼
T16. 제조 지식그래프와 시맨틱 레이어
이 주제만 보기- T16-8후보2025년 이후
Intent-Driven Smart Manufacturing Integrating Knowledge Graphs and Large Language Models
- T16-6구조대응2025년 이후
Knowledge Graphs as the Missing Data Layer for LLM-Based Industrial Asset Operations
- T16-7유사문제2025년 이후
Fault Cause Identification across Manufacturing Lines through Ontology-Guided and Process-Aware FMEA Graph Learning with LLMs
- T16-1구조대응
The Industrial Ontologies Foundry (IOF) Core Ontology
- T16-2구조대응
Semantic Integration of Bosch Manufacturing Data Using Virtual Knowledge Graphs
- T16-3유사문제
Knowledge Graphs in Manufacturing and Production: A Systematic Literature Review
- T16-4후보
Literal-Aware Knowledge Graph Embedding for Welding Quality Monitoring: A Bosch Case
- T16-5구조대응
Generation of Asset Administration Shell with Large Language Model Agents
- T16-9구조대응
Ontop: Answering SPARQL queries over relational databases
- T16-10구조대응
RML: A Generic Language for Integrated RDF Mappings of Heterogeneous Data
- T16-12유사문제
The Industry 4.0 Standards Landscape from a Semantic Integration Perspective
T17. 자연어를 SQL로 바꾸기와 근거 기반 보고서 생성
이 주제만 보기- T17-5유사문제2025년 이후
Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows
Spider 2.0
- T17-9구조대응2025년 이후
MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL
MAC-SQL
- T17-1유사문제
Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning
Seq2SQL와 WikiSQL
- T17-2유사문제
Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task
Spider
- T17-3구조대응
Semantic Evaluation for Text-to-SQL with Distilled Test Suites
실행 기반 채점법, Test Suite Accuracy
- T17-4유사문제
Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs
BIRD
- T17-6구조대응
RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers
RAT-SQL
- T17-7구조대응
DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction
DIN-SQL
- T17-8구조대응
Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation
DAIL-SQL
- T17-10구조대응
CHESS: Contextual Harnessing for Efficient SQL Synthesis
CHESS
- T17-13구조대응
Attributed Question Answering: Evaluation and Modeling for Attributed Large Language Models
Attributed QA, 귀속 자동 측정
- T17-14구조대응
RARR: Researching and Revising What Language Models Say, Using Language Models
RARR, 자동 귀속과 사후 수정
- T17-16구조대응
FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation
FActScore
- T17-17유사문제
ToTTo: A Controlled Table-To-Text Generation Dataset
ToTTo
- T17-18유사문제
QTSumm: Query-Focused Summarization over Tabular Data
QTSumm
- T17-19후보
InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks
InfiAgent-DABench
T18. AI 품질관리, 모델 모니터링, 감사기록
이 주제만 보기- T18-12구조대응2025년 이후
Provenance Tracking in Large-Scale Machine Learning Systems
- T18-11후보2025년 이후
Time to Retrain? Detecting Concept Drifts in Machine Learning Systems
- T18-1유사문제
Hidden Technical Debt in Machine Learning Systems
- T18-2구조대응
The ML Test Score: A Rubric for ML Production Readiness and Technical Debt Reduction
- T18-3구조대응
Data Validation for Machine Learning
- T18-6구조대응
Closing the AI Accountability Gap: Defining an End-to-End Framework for Internal Algorithmic Auditing
- T18-7유사문제
A Survey on Concept Drift Adaptation
- T18-8유사문제
Learning under Concept Drift: A Review
- T18-9구조대응
Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shift
- T18-10유사문제
Operationalizing Machine Learning: An Interview Study
연구에서 제품 적용까지
운영 중인 기능, 시범 적용과 개발 중인 기술을 구분해 정리했습니다.
보유기술 보기