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- T01-1Structural parallel
ReAct: Synergizing Reasoning and Acting in Language Models
- T01-2Structural parallel
Toolformer: Language Models Can Teach Themselves to Use Tools
- T01-3Structural parallel
HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face
- T01-9Structural parallel
AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversations
- T01-10Structural parallel
MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
- T01-11Structural parallel
SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering
- T01-15Structural parallel
Tree of Thoughts: Deliberate Problem Solving with Large Language Models
T02. Recursive language models and long-context handling
Research on reading documents that do not fit in one context window.
Show this topic only- T02-1Structural parallelSince 2025
Recursive Language Models
- T02-2Structural parallel
RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
- T02-5Structural parallel
Chain of Agents: Large Language Models Collaborating on Long-Context Tasks
- T02-9Structural parallel
Recursively Summarizing Books with Human Feedback
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- T03-1Structural parallel
WebGPT: Browser-assisted question-answering with human feedback
- T03-2Structural parallel
MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning
- T03-7Structural parallel
Gorilla: Large Language Model Connected with Massive APIs
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- T04-1Structural parallel
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- T04-4Structural parallel
Self-Refine: Iterative Refinement with Self-Feedback
- T04-7Structural parallel
Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
- T04-15Structural parallel
Constitutional AI: Harmlessness from AI Feedback
T05. Human review and approval workflows
Human-in-the-loop and approval research, including automation-induced complacency.
Show this topic only- T05-4Structural parallel
A Model for Types and Levels of Human Interaction with Automation
- T05-6Structural parallel
On Optimum Recognition Error and Reject Tradeoff
- T05-7Structural parallel
Learning with Rejection
- T05-8Structural parallel
Predict Responsibly: Improving Fairness and Accuracy by Learning to Defer
- T05-9Structural parallel
SelectiveNet: A Deep Neural Network with an Integrated Reject Option
- T05-10Structural parallel
Consistent Estimators for Learning to Defer to an Expert
- T05-11Structural parallel
Learning to Complement Humans
- T05-12Structural parallel
Machine Learning with a Reject Option: A survey
- T05-19Structural parallel
Identifying the Risks of LM Agents with an LM-Emulated Sandbox (ToolEmu)
- T05-20Structural parallel
AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
T06. RAG, knowledge graphs, ontologies, and provenance
Retrieval-augmented generation and structured knowledge with traceable sources.
Show this topic only- T06-1Structural parallel
Dense Passage Retrieval for Open-Domain Question Answering
- T06-3Structural parallel
Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering
- T06-5Structural parallel
From Local to Global: A Graph RAG Approach to Query-Focused Summarization
- T06-7Structural parallel
Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
- T06-8Structural parallel
Enabling Large Language Models to Generate Text with Citations
- T06-10Structural parallel
Provenance Semirings
- T06-11Structural parallel
Provenance in Databases: Why, How, and Where
T07. Structured output, schema validation, and document understanding
Research on forcing machine-checkable output and reading business documents.
Show this topic only- T07-10Structural parallelSince 2025
XGrammar: Flexible and Efficient Structured Generation Engine for Large Language Models
- T07-1Structural parallel
LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking
- T07-2Structural parallel
OCR-free Document Understanding Transformer
- T07-7Structural parallel
PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models
- T07-8Structural parallel
Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning
- T07-9Structural parallel
Efficient Guided Generation for Large Language Models
T08. OCR, vision-language models, and industrial display reading
Research on reading meters, indicators, and shop-floor displays from images.
Show this topic only- T08-2Structural parallelSince 2025
DialBench: Towards Accurate Reading Recognition of Pointer Meter using Large Foundation Models
- T08-5Structural parallel
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
- T08-6Structural parallel
Real-time Scene Text Detection with Differentiable Binarization
- T08-9Structural parallel
General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model
- T08-12Structural parallel
ScreenAI: A Vision-Language Model for UI and Infographics Understanding
T09. Industrial time series, anomaly detection, and predictive maintenance
Sensor-driven fault detection, remaining useful life, and condition monitoring research.
Show this topic only- T09-6Structural parallel
Anomaly Detection in Time Series: A Comprehensive Evaluation
- T09-8Structural parallel
Robust Anomaly Detection for Multivariate Time Series through Stochastic Recurrent Neural Network (OmniAnomaly)
- T09-10Structural parallel
Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy
- T09-11Structural parallel
TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data
- T09-12Structural parallel
Time-Series Anomaly Detection Service at Microsoft
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- T10-2Structural parallel
Auto-WEKA: Combined Selection and Hyperparameter Optimization of Classification Algorithms
- T10-3Structural parallel
Efficient and Robust Automated Machine Learning (auto-sklearn)
- T10-7Structural parallel
AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data
- T10-8Structural parallel
Auto-Sklearn 2.0: Hands-free AutoML via Meta-Learning
- T10-13Structural parallel
OpenML: Networked Science in Machine Learning
- T10-14Structural parallel
Developments in MLflow: A System to Accelerate the Machine Learning Lifecycle
T11. Object detection, multi-object tracking, and video understanding
Detection and tracking backbones behind camera-based safety and inspection work.
Show this topic only- T11-1.1Structural parallel
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale (ViT)
- T11-2.1Structural parallel
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- T11-2.2Structural parallel
You Only Look Once: Unified, Real-Time Object Detection (YOLO)
- T11-2.3Structural parallel
Focal Loss for Dense Object Detection (RetinaNet)
- T11-2.4Structural parallel
End-to-End Object Detection with Transformers (DETR)
- T11-2.5Structural parallel
Deformable DETR: Deformable Transformers for End-to-End Object Detection
- T11-2.6Structural parallel
DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection
- T11-3.1Structural parallel
Simple Online and Realtime Tracking (SORT)
- T11-3.3Structural parallel
ByteTrack: Multi-Object Tracking by Associating Every Detection Box
- T11-4.1Structural parallel
Evaluating Multiple Object Tracking Performance: The CLEAR MOT Metrics (MOTA, MOTP)
- T11-4.2Structural parallel
Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking (IDF1)
- T11-4.3Structural parallel
HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking
- T11-4.4Structural parallel
MOT16: A Benchmark for Multi-Object Tracking
- T11-5.1Structural parallel
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset (I3D)
- T11-6.1Structural parallel
Learning Transferable Visual Models From Natural Language Supervision (CLIP)
- T11-6.2Structural parallel
Segment Anything (SAM)
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- T12-2Structural parallelSince 2025
Adaptive Keyframe Sampling for Long Video Understanding
- T12-1Structural parallelSince 2025
Frame-Voyager: Learning to Query Frames for Video Large Language Models
- T12-3Structural parallel
Self-Chained Image-Language Model for Video Localization and Question Answering (SeViLA)
- T12-4Structural parallel
VideoAgent: Long-form Video Understanding with Large Language Model as Agent
- T12-7Structural parallel
TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding
- T12-8Structural parallel
VTimeLLM: Empower LLM to Grasp Video Moments
- T12-11Structural parallel
BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
T13. Edge AI, streaming inference, and resource scheduling
Running models near the machine under limited compute and latency budgets.
Show this topic only- T13-1Structural parallel
Neurosurgeon: Collaborative Intelligence Between the Cloud and Mobile Edge
- T13-6Structural parallel
Ekya: Continuous Learning of Video Analytics Models on Edge Compute Servers
- T13-7Structural parallel
Clipper: A Low-Latency Online Prediction Serving System
- T13-8Structural parallel
Serving DNNs like Clockwork: Performance Predictability from the Bottom Up
- T13-17Structural parallel
MLPerf Inference Benchmark
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- T14-5Structural parallelSince 2025
Training LLMs for Generating IEC 61131-3 Structured Text with Online Feedback
- T14-3Structural parallel
LLM4PLC: Harnessing Large Language Models for Verifiable Programming of PLCs in Industrial Control Systems
- T14-10Structural parallel
Automated Attack Synthesis by Extracting Finite State Machines from Protocol Specification Documents
- T14-11Structural parallel
Syntax-Guided Synthesis
- T14-12Structural parallel
Automating string processing in spreadsheets using input-output examples
- T14-13Structural parallel
Combinatorial Sketching for Finite Programs
T15. OPC UA, Asset Administration Shell, MQTT, and manufacturing interoperability
Specifications and research for describing equipment and moving its data.
Show this topic only- T15-2.10Structural parallelSince 2025
ESP32-Based Sparkplug B Gateway Framework for Brownfield PLC Integration into an IIoT Unified Namespace: A Data Foundation for Intelligent Industrial Systems
- T15-2.3Structural parallel
Reusing OPC UA information models in the Asset Administration Shell
- T15-2.5Structural parallel
Evaluation and Extension of OPC UA Publish/Subscribe MQTT Binding
- T15-2.8Structural parallel
File- and API-based interoperability of digital twins by model transformation: An IIoT case study using asset administration shell
- T15-2.11Structural parallel
A Cyber-Physical Machine Tools Platform using OPC UA and MTConnect
T16. Manufacturing knowledge graphs and semantic layers
Research on giving plant data a shared meaning across systems.
Show this topic only- T16-6Structural parallelSince 2025
Knowledge Graphs as the Missing Data Layer for LLM-Based Industrial Asset Operations
- T16-1Structural parallel
The Industrial Ontologies Foundry (IOF) Core Ontology
- T16-2Structural parallel
Semantic Integration of Bosch Manufacturing Data Using Virtual Knowledge Graphs
- T16-5Structural parallel
Generation of Asset Administration Shell with Large Language Model Agents
- T16-9Structural parallel
Ontop: Answering SPARQL queries over relational databases
- T16-10Structural parallel
RML: A Generic Language for Integrated RDF Mappings of Heterogeneous Data
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- T17-9Structural parallelSince 2025
MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL
- T17-3Structural parallel
Semantic Evaluation for Text-to-SQL with Distilled Test Suites
- T17-6Structural parallel
RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers
- T17-7Structural parallel
DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction
- T17-8Structural parallel
Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation
- T17-10Structural parallel
CHESS: Contextual Harnessing for Efficient SQL Synthesis
- T17-13Structural parallel
Attributed Question Answering: Evaluation and Modeling for Attributed Large Language Models
- T17-14Structural parallel
RARR: Researching and Revising What Language Models Say, Using Language Models
- T17-16Structural parallel
FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation
T18. AI quality management, model monitoring, and audit trails
Research and standards for keeping a deployed model accountable over time.
Show this topic only- T18-12Structural parallelSince 2025
Provenance Tracking in Large-Scale Machine Learning Systems
- T18-2Structural parallel
The ML Test Score: A Rubric for ML Production Readiness and Technical Debt Reduction
- T18-3Structural parallel
Data Validation for Machine Learning
- T18-6Structural parallel
Closing the AI Accountability Gap: Defining an End-to-End Framework for Internal Algorithmic Auditing
- T18-9Structural parallel
Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shift
From research to product use
Operating capabilities, pilots, and technologies in development are identified separately.
View technology