AI is used in manufacturing to optimize production processes, improve quality control, and enhance automation. It employs machine learning algorithms, robotics, and real-time data analysis to increase efficiency, reduce defects, and enable predictive maintenance, leading to improved productivity and cost savings in manufacturing operations.
Researchers at NC State have developed Rainbow, the world’s first multi-robot self-driving laboratory that autonomously discovers high-performance quantum dots. Powered by AI and advanced robotics, Rainbow can run up to 1,000 experiments daily, accelerating discovery and scaling seamlessly from lab to manufacturing.
A Tsinghua University team reviewed the progress of inverse lithography technology (ILT) in semiconductor manufacturing, highlighting how artificial intelligence improves lithography modeling, mask optimization, and computational efficiency. The paper also discusses challenges in scalability, interpretability, and mask fabrication.
Researchers at Nanjing University of Science and Technology and Warsaw University of Technology developed DFAMFPP, a deep learning-enabled 3D imaging system that breaks sensor frame-rate limits. The method reconstructs multiple high-precision 3D frames from a single image, enabling ultrafast visualization of high-speed phenomena.
MIT chemical engineers have developed a machine learning model that predicts molecular solubility in organic solvents with high accuracy, streamlining pharmaceutical synthesis. The freely available tool could accelerate drug development and help identify safer, more sustainable solvents.
Researchers at Northwestern University and Toyota Research Institute used an AI-driven "megalibrary" of millions of nanoparticles to rapidly discover a low-cost hydrogen catalyst. The material matches or exceeds iridium’s performance but is far cheaper and more abundant, boosting clean energy prospects.
Researchers from Zhejiang University have developed Deep3DSketch-im, a deep learning model that transforms a single freehand sketch into a high-quality 3D mesh. The system uses signed distance fields and a pose-estimation network to generate detailed, editable 3D models with minimal user input.
This review from Southeast University outlines the evolution, technologies, applications, and future directions of AI-driven text generation, from rule-based systems to large language models.
It categorizes text generation into utility, creative, and emotive types, and discusses the challenges of quality, ethics, and computational costs.
Viam has partnered with Viking Yachts to automate the labor-intensive fiberglass sanding process in yacht manufacturing using adaptive robotics. This collaboration aims to improve efficiency, consistency, and worker safety, signaling a major step forward in marine industry automation.
Researchers at Empa have developed machine learning algorithms that significantly streamline and enhance laser-based metal manufacturing processes, such as powder bed fusion and welding. By integrating real-time sensor data and adaptive AI, they reduce experimental workload and optimize quality and efficiency, making advanced metalworking more accessible.
Hexion has unveiled SmartQuality, a cutting-edge AI-powered system designed to optimize wood panel manufacturing by providing real-time quality insights and enhancing operational efficiency. Launched at LIGNA 2025, SmartQuality aims to resolve the trade-off between line speed and product quality, supporting sustainable and data-driven production.
A new co-optimization framework for MEMS design, developed by Dr. Chen Wang and collaborators, integrates genetic algorithms with freeform geometry modeling to simultaneously optimize mechanical and electronic subsystems
University of South Australia research shows that simply implementing AI tools in hiring does not automatically improve workplace diversity. Effective diversity outcomes require AI systems to provide explainable decisions, qualitative goals, and strong organisational diversity guidelines.
Researchers at the University of Pennsylvania used AI and lab methods to identify antiviral compounds against enterovirus 71, the leading cause of hand, foot, and mouth disease. Five of eight AI-predicted candidates successfully slowed the virus—ten times the success rate of traditional screening.
Nanjing University researchers unveiled a new AI training framework and benchmark that dramatically improve how AI collaborates with humans, especially when facing unexpected, real-world challenges. Their approach enables AI to communicate more effectively, adapt swiftly, and outperform traditional methods in human-AI teamwork.
Researchers from NOVA IMS have developed Counterfactual SMOTE, an advanced oversampling method that improves minority class detection in imbalanced healthcare datasets. By generating boundary-focused, noise-free synthetic samples, it significantly enhances AI model accuracy, especially for rare but critical outcomes.
Researchers at Waseda University used machine learning to optimize the molecular design and experimental conditions of photo-actuated organic crystals, dramatically increasing their mechanical output. Their approach achieved up to 3.7 times greater blocking force and was 73 times more efficient than traditional methods.
This paper reviews the convergence of artificial intelligence and nanophotonics, highlighting how optical neural networks and metasurfaces are revolutionizing fast, energy-efficient computing and advanced sensing. The authors analyze current challenges and future opportunities for integrating intelligent photonics into real-world AI technologies.
FAMU-FSU College of Engineering researchers are using a novel AI technique called combinatorial generalization to detect hard-to-find defects in powder-based 3D printing. The $2.2M Air Force-backed project could revolutionize high-performance component manufacturing.
Researchers at Iowa State University are creating high-resolution 3D digital twins of plants using AI-driven neural radiance fields (NeRF), transforming simple smartphone videos into dynamic, data-rich models. These digital twins are advancing agriculture, healthcare, and manufacturing by enabling real-time simulations, precision predictions, and enhanced decision-making.
University of Toronto engineers have developed a machine learning framework, AIDED, to rapidly optimize 3D metal printing settings, reducing trial and error.
Terms
While we only use edited and approved content for Azthena
answers, it may on occasions provide incorrect responses.
Please confirm any data provided with the related suppliers or
authors. We do not provide medical advice, if you search for
medical information you must always consult a medical
professional before acting on any information provided.
Your questions, but not your email details will be shared with
OpenAI and retained for 30 days in accordance with their
privacy principles.
Please do not ask questions that use sensitive or confidential
information.
Read the full Terms & Conditions.