Tag
The paper presents Conservative Hybrid Graph Network (CHGN), a method for modeling dynamic process systems that allows extrapolation to unseen larger graphs without retraining and improves fault prediction in industrial applications.
FedCMAPSS introduces a benchmark for federated learning in remaining useful life estimation based on the NASA C-MAPSS dataset, with standardized tasks to evaluate federated optimization algorithms across neural architectures.
Perceptron, a startup founded by ex-Meta scientists, has launched Isaac 0.5, an open-weight visual AI model designed to help robots perceive, reason, and act in industrial environments like warehouses and factories.
The APAC-Egocentric-Stereo dataset provides first-person recordings of people working in industrial and other jobs, featuring stereo video, depth maps, tracking, and captions, now available in FiftyOne format on Hugging Face.
This paper proposes candidate-fate accounting, a framework for auditing automated machine learning pipeline searches in sensor diagnostics to enhance transparency by tracking all candidates and their outcomes.
This paper presents RecSys Factory, an LLM-agent platform deployed at Tencent that confines agent autonomy to decision points rather than full pipelines, balancing autonomy, determinism, and efficiency across three industrial recommender business lines.
This paper compares three methods for grounding a frozen LLM (Qwen2.5-32B-Instruct) in a wastewater treatment simulator for causal question answering, including live tool-use, structured parameter injection, and a small decoupled retrieval model, achieving high accuracy and cross-plant transfer.
The paper proposes an adversarial inverse reinforcement learning framework for machinery fault detection that learns a health reward from normal operational data without requiring fault labels, achieving consistent detection across multiple benchmarks.
RobustMAD introduces a benchmark to evaluate the real-world robustness of multimodal small language models for deployable industrial anomaly detection assistants. It reveals critical failure modes and provides guidance for next-generation systems.
Soofi introduces Soofi S, a 30B parameter Mixture-of-Experts open source foundation model trained on 27 trillion tokens, targeting industrial AI applications in German and English. The model is part of a European sovereign AI initiative.
Applied Computing, a London-based startup, has raised $20M for Orbital, a foundation AI model for oil, gas, and petrochemical plants that combines time series, physics, and language models to analyze sensor data and simulate operations, aiming to help operators use data more effectively.
Proposes ROAM, a framework that uses LLM world knowledge and reasoning to adapt frozen specialist models to unseen scenarios without retraining, achieving over 20% MAE reduction with minimal overhead.
The article explores how Woodside Energy has been integrating AI across its industrial operations for over a decade, moving from predictive analytics to agentic systems like the 'Startup Advisor' copilot for LNG plant startups, aiming for an autonomous enterprise.
Proposes a novel framework combining active learning with masked reconstruction and minimax strategies to improve unsupervised time series anomaly detection, achieving 12.39% AUC improvement over baselines across 28 test cases.
Forgis Labs presents a family of foundation models for time series sensor data in industrial settings, with five papers accepted to ICML 2026 workshops, enabling event prediction and natural language explanation from raw sensor streams.
An analysis of 15 key companies providing physical AI infrastructure, including NVIDIA, that are shaping the next phase of AI in factories, warehouses, and other physical environments.
FactoryLLM is an open-source AI playground for evaluating LLM-based RAG models in smart factory fault diagnostics, supporting local LLMs and dual evaluation metrics. A case study with three LLMs showed groundedness scores above 0.88 across 30 maintenance queries from 600 pages of cross-machine documentation.
This paper proposes a framework for applying tabular foundation models to industrial time series for prognostics and health management, demonstrating strong performance and data efficiency across multiple PHM tasks.
DMAIC-IAD is a multi-agent LLM system inspired by the DMAIC quality-management framework for industrial anomaly detection, using a 'Plan First, Judge Later' approach that formulates strategies via standardized operating procedures and ranks them with an execution-free judge model, achieving 37.76% improvement over agentic baselines across four data modalities.
NVIDIA announced the Factory Operations Blueprint (FOX), a reference design for building autonomous factory manager AI agents that integrate real-time data, automate model training, and orchestrate specialized agents, with early adoption by major manufacturers.