PRISM-AI
Platform for Real-world Innovation in Smart Manufacturing and AI
Platform for Real-world Innovation in Smart Manufacturing and AI
We’re pleased to share a presentation and perspective introducing the vision and strategy of the PRISM-AI InnoCORE Research Center, which aims to advance AI-driven innovation in smart manufacturing.
- Presentation slide pdf (in Korean): https://lnkd.in/grDaBT7b
- Perspective preprint available on arXiv: https://lnkd.in/gXH4wwzB
Summary)
[1] AI models can be viewed as functions mapping from the design space (domain) to the performance space (codomain), and under the Universal Approximation Theorem (UAT) and Gaussian Process Regression (GPR), sufficient predictive accuracy can be achieved with well-trained surrogate models.
[2] Predictive performance depends heavily on how uniformly and strategically the training data covers the design space, and addressing poor generalization outside the training distribution remains a key challenge.
[3] Therefore, problems in material, structural, and process design can all be addressed under a unified mathematical framework—yet under limited time and budget, expert-guided sampling strategies are essential.
[4] Our current research focuses on data-efficient physics-informed machine learning (PIML) to address limited resources and improve extrapolation performance beyond the training distribution, as well as on developing user-friendly LLM-based tools for domain experts unfamiliar with AI. These approaches are being applied to real-world use cases such as injection molding control and nuclear reactor operation.
[5] In the mid-term, our core vision is to build a next-generation design-to-manufacturing platform that integrates PIML, multi-agent AI LLM systems, and intuitive graphical user interfaces (GUIs).
PRISM-AI (Platform-based Research Initiative for Smart Manufacturing with AI) is Korea’s national research initiative committed to pioneering industrial innovation through the development of a next-generation AI platform for end-to-end intelligent manufacturing.
PRISM-AI is supported by a broad network of domestic and global collaborators across industry, academia, and research.
Academia
31 faculty members
from KAIST, UNIST, GIST, DGIST, Seoul National University, Korea University, Hanyang University, Dongguk University and more.
Industry and research institute
39 advisory institutions (industry executives and senior research directors)
including LG Electronics, HD Hyundai, Samsung Heavy Industries, Hyundai Motor Company, KIMM, KIST, KRISS and more.
Global mentorship
MIT, UC Berkeley, University of Maryland (UMD), and DTU (Technical University of Denmark).
PRISM-AI pioneers an LLM-powered platform for end-to-end manufacturing
PRISM-AI interprets natural language instructions to coordinate material discovery, process optimization, and anomaly detection, enabling intelligent automation across the full manufacturing lifecycle.
PRISM-AI cultivates a world-class ecosystem led by top-tier postdocs
PRISM-AI empowers InnoCORE Fellows to lead real-world AI manufacturing projects, gaining cross-sector experience and growing into future leaders of Korea’s smart manufacturing ecosystem.
PRISM-AI drives industrial adoption of AI
PRISM-AI promotes industrial adoption by validating AI modules across design, materials, manufacturing, and operations—bridging research and practice through field testbeds and expert advisory networks. It also enables domain experts to interact with AI through natural language, lowering the barrier to adoption and enhancing productivity on the shop floor.
Prof. Seunghwa Ryu
E-mail: ryush@kaist.ac.kr