MIT Researcher Alexander Htet Kyaw Merges Design and Computer Science in Creative AI Applications

Alexander Htet Kyaw, an MIT MAD Fellow and graduate student, is making waves by merging design and computer science. Pursuing dual master’s degrees in architectural studies in computation and electrical engineering and computer science, Kyaw creatively employs technologies like AI, AR, and robotics to revolutionize human-AI workflows. His innovations promise to reshape interactions within built environments, enhance shopping experiences, and transform the creation of complex structures.

One of Kyaw’s standout projects is Curator AI. This platform, developed in collaboration with MIT graduate students Richa Gupta, Bradley Bunch, Nidhish Sagar, and Michael Won, won first prize at the MIT AI Conference’s AI Build: Generative Voice AI Solutions hackathon. Curator AI aims to redefine online furniture shopping using AI and AR to provide context-aware product recommendations.

Curator AI uses AR to measure room dimensions, accounting for windows, doors, and existing furniture. Users can then use voice commands to describe desired furnishings, prompting the system to use a vision-language AI model to find and display suitable options. According to Kyaw, this streamlines the furniture selection process, making it “more intuitive, efficient, and personalized.” While initially designed for furniture, Curator AI holds potential for expansion into other markets.

Another notable project is Estimate, created during the MIT Sloan Product Tech Conference hackathon in March 2024. Kyaw and his team – Guillaume Allegre, May Khine, and Anna Mathy – focused on assisting small businesses by developing a tool for a Cambridge-based painting company. Estimate employs AR and object recognition to precisely measure rooms and generate detailed cost estimates for renovations and paint jobs. The system also uses generative AI to visualize post-renovation appearances and generate invoices upon project completion.

Kyaw will be giving a TEDx talk at Cornell University, where he earned bachelor’s degrees in architecture and computer science, in April. He will present Curator AI, Estimate, and other projects showcasing the use of AI, AR, and robotics in design and construction.

Among these projects is Unlog, which combines AR with gesture recognition to map building component dimensions via fingertip input on material surfaces. This technology facilitated the creation of Unlog, an art sculpture on the Cornell campus made from ash logs. This project reflects Kyaw’s commitment to sustainable building practices by exploring the use of whole logs in construction, bypassing traditional lumber milling processes. A related paper, “Gestural Recognition for Feedback-Based Mixed Reality Fabrication a Case Study of the UnLog Tower,” was published in January 2024.

Kyaw has also developed a system integrating physics simulation, gesture recognition, and AR for designing active bending structures with bamboo poles. Gesture recognition allows users to manipulate digital bamboo modules in AR, while physics simulation visualizes bending and attachment points for structural stability. This work was presented at the 41st Education and Research in Computer Aided Architectural Design in Europe in August 2023 and published as “Active Bending in Physics-Based Mixed Reality: The Design and Fabrication of a Reconfigurable Modular Bamboo System.”

Furthering his commitment to social impact, Kyaw founded BendShelters through the MITdesignX program. BendShelters aims to provide prefabricated, modular bamboo shelters and community spaces for refugees and displaced persons in Myanmar. His work with BendShelters has been recognized by MIT Sandbox, PKG Social Innovation Challenge, and the Amazon Robotics’ Prize for Social Good.

At MIT, Kyaw collaborates with Professor Neil Gershenfeld and PhD student Miana Smith, focusing on using speech recognition, 3D generative AI, and robotic arms to create accessible, on-demand, and sustainable construction methods. Kyaw summarizes his vision: “My research vision is to design and develop systems and products that enable natural interactions between humans, machines, and the world around us.”