Learning to Generate and Manufacture the Next Billion Designs

ABSTRACT

The rapid evolution of advanced manufacturing has brought remarkable progress, yet the increasing demand for customization and complexity continues to outpace traditional methods. Modern AI technologies are revolutionizing the next generation of the global manufacturing landscape, offering solutions to long-standing challenges. However, due to the lack of general engineering intelligence, workflows in design and manufacturing remain fragmented and persist as a critical obstacle, limiting the full potential of these transformative technologies.

In this talk, I will share a bold vision for creating a foundational universal AI system for manufacturing intelligence that can bridge the gaps across manufacturing workflow for smarter, more efficient, and accessible manufacturing. I will showcase cutting-edge AI innovations that move beyond narrow task-specific models to foundational manufacturing intelligence capable of generalizing across unstructured tasks. In particular, I will present state-of-the-art novel generative AI algorithms capable of creating the next billion manufacturable designs efficiently. I will also showcase novel algorithms for manufacturing intelligence that address data efficiency, scalability, and integration challenges with manufacturing hardware. Additionally, my talk will demonstrate a state-of-the-art autonomous manufacturing system that deploys AI algorithms for real-time sensing, planning, and process control to manufacture complex geometry 3D artifacts. Finally, I will talk about the critical challenges and pathways to shape the future of AI-driven manufacturing in the coming decades.

BIOGRAPHY

Ferdous Alam is a postdoctoral associate in the Department of Mechanical Engineering at the Massachusetts Institute of Technology (MIT). Previously, he earned his Ph.D. and M.S. in Mechanical Engineering from the Ohio State University, and B.S. in Mechanical Engineering from Bangladesh University of Engineering and Technology. He also worked as a research intern and later a research collaborator at the Autodesk AI Lab. Ferdous has expertise in generative AI, representation learning, physics-based AI, robotics, and AI software integration in manufacturing hardware. Ferdous is also a recipient of the 2024 Google Research Scholar Award in Applied Science and a Best Paper Award at the 2020 ASME MSEC Conference.

For questions about the speaker, contact Prof. Nicholaus Parziale