AE studio 2025
Spring 2025. Instructors: Ming Tang, Samira Sarabandikachyani
This studio provides a comprehensive introduction to architectural design. Students developed proposals for a restaurant located in Over-the-Rhine (OTR), Cincinnati, Ohio.
Exhibition: Views of Cincinnati & Ohio Valley
Exhibition “Views of Cincinnati & Ohio Valley”
Location: Elevar Gallery, 555 Carr St., Cincinnati.
opening hours: May 1- June 27, 2025, Mon-Thu 9-5 pm, Fri 9-6:30 pm
The exhibition is supported by the Creative Asian Society and the ArtsWave Impact grant.
“Infinite Loop” reflects my interpretation of the Ohio Valley—an ever-shifting landscape shaped by both deep geological time and layers of human history. Inspired by the region’s porous limestone caves, exposed rock formations, and the powerful erosive force of the Ohio River, the sculpture evokes the continuous movement and natural evolution embedded in this terrain. The form, looping without a clear beginning or end, draws from the valley’s complex strata—both literal and metaphorical. It echoes the industrial legacy of Cincinnati: a city built along railroads, powered by migration, and continually transformed by waves of innovation, creativity, and technology. Each undulating surface captures a sense of motion and continuity, speaking to the rhythms of the river and the resilience of a city in flux. By blending references to natural erosion, flood, and industrial infrastructure, Infinite Loop invites reflection on how we shape—and are shaped by—the landscapes we inhabit. It is a meditation on flow, transformation, and the unbroken cycles that define both the Ohio River and the city of Cincinnati itself.
XR and Gen-AI Technologies in Design
Left: VR training on welding, Samantha Frickel. Right: Cinematic universes. Carson Edwards
Extended Reality and Generative-AI in Human-Centered Design
UHP + Architecture Seminar
Student work from the University of Cincinnati’s Honors Seminar and Architecture Design Seminar. This video showcases multiple innovative projects intersecting emerging technologies such has AIGC, XR with human-centered design.The projects include a wide range of demonstrations in the following two categories:
Training
The first category centers on Virtual Reality-based training applications designed to simulate real-world tasks and enhance learning through immersive experiences. These projects include simulations for welding, firefighter robotics, and driving and instructional environments such as baby car seat installation. Each scenario provides a controlled, repeatable setting for learners to gain confidence and skills in safety-critical and technical domains, demonstrating the practical potential of XR technologies in professional training and education. Digital 3D content creation was augmented by various AIGC tools such as Rodin, Meshy, Tripo, etc.
Future Environment
This group of projects explores imaginative and speculative environments through immersive technologies. Students and researchers have developed experiences ranging from fictional music spaces, virtual zoos, and animal shelters to emotionally responsive architectural designs and future cityscapes. These environments often incorporate interactive elements, such as Augmented Reality on mobile devices or real-time simulations of natural phenomena like flooding. Advanced material simulation is also a focus, including simulating cloth and other soft fabrics that respond dynamically to user interaction. 2D Content creation was augmented by various AIGC tools such as Midjourney, Stable Diffusion, etc.
SMAT: Scalable Multi-Agent AI for DT
SMAT: Scalable Multi-Agent Machine Learning and Collaborative AI for Digital Twin Platform of Infrastructure and Facility Operations.
Principal Investigators:
- Prof. Sam Anand, Department of Mechanical Engineering, CEAS
- Prof. Ming Tang, Extended Reality Lab, Digital Futures, DAAP
Students: Anuj Gautam, Manish Aryal, Aayush Kumar, Ahmad Alrefai, Rohit Ramesh, Mikhail Nikolaenko, Bozhi Peng
Grant: $40,000. UC Industry 4.0/5.0 Institute Consortium Research Project: 03.2025-01.2026
Partner: Cincinnati Incorporated
paper in JMS & NAMRC
Anuj Gautam, Manish Raj Aryal, Sourabh Deshpande, Shailesh Padalkar, Mikhail Nikolaenko, Ming Tang, Sam Anand, IIoT-enabled digital twin for legacy and smart factory machines with LLM integration, Journal of Manufacturing Systems, Volume 80, 2025, Pages 511-523, ISSN 0278-6125
The paper is also published in the NAMRC 2025 conference.
Anuj Gautam , Manish Raj Aryal, Sourabh Deshpande, Shailesh Padalkar, Mikhail Nikolaenko, Ming Tang, Sam Anand. IIoT-enabled Digital Twin for legacy and smart factory machines with LLM integration. 53rd SME North American Manufacturing Research Conference (NAMRC), Clemson Univ. 06/2025.
Abstract
The recent advancement in Large Language Models (LLMs) has significantly transformed the field of natural data interpretation, translation, and user training. However, a notable gap exists when LLMs are tasked to assist with real-time context-sensitive machine data. The paper presents a multi-agent LLM framework capable of accessing and interpreting real-time and historical data through an Industrial Internet of Things (IIoT) platform for evidence-based inferences. The real-time data is acquired from several legacy machine artifacts (such as seven-segment displays, toggle switches, and knobs), smart machines (such as 3D printers), and building data (such as sound sensors and temperature measurement devices) through MTConnect data streaming protocol. Further, a multi-agent LLM framework that consists of four specialized agents – a supervisor agent, a machine-expertise agent, a data visualization agent, and a fault-diagnostic agent is developed for context-specific manufacturing tasks. This LLM framework is then integrated into a digital twin to visualize the unstructured data in real time. The paper also explores how LLM-based digital twins can serve as real time virtual experts through an avatar, minimizing reliance on traditional manuals or supervisor-based expertise. To demonstrate the functionality and effectiveness of this framework, we present a case study consisting of legacy machine artifacts and modern machines. The results highlight the practical application of LLM to assist and infer real-time machine data in a digital twin environment.
