CDFAM Tokyo – Computational Design Symposium
October 8–9, 2026 | Tokyo International Forum, Tokyo, Japan
CDFAM makes its Asia-Pacific debut with a two-day symposium bringing together engineers, architects, researchers, and software developers working at the intersection of computational design, AI, and machine learning.
Following events in New York, Berlin, Washington DC, Amsterdam, and Barcelona, CDFAM Tokyo continues the series’ focus on computational design methodologies applied across scales, from architected materials to large-scale architectural and engineering systems.
All presentations to be delivered in English.
Program
The program is currently under development, submissions open to present.
Confirmed speakers and sessions will be announced on a rolling basis.
Keynote | Federico Casalegno | Samsung Research
Presentation Abstract
Speaker Bio
Toward Generative Engineering: Case Studies in Computationally Enhanced Creation of New Design Concepts
Presentation Abstract
Nature Architects Inc. develops a software platform that deeply integrates geometry processing, numerical analysis, and optimization, while also providing design solutions enabled by the platform through its Generative Engineering™ approach. Covering a wide range of manufacturing contexts, from mass production to advanced manufacturing methods, the company dramatically accelerates design exploration and creates new designs beyond existing design paradigms.
This presentation will introduce case studies in which design concepts were generated under complex, large-scale physical phenomena and geometric constraints. Examples include the rapid exploration and creation of new design concepts for electric vehicle bodies, innovative garment design using origami-based techniques, and the design of highly efficient heat exchange structures enabled by additive manufacturing. The presentation will also outline future directions for Generative Engineering™
Speaker Bio
Director and CTO of Nature Architects Inc.
After graduating from the Faculty of Engineering at the University of Tokyo, he entered the University of Tokyo’s Graduate School of Interdisciplinary Information Studies. While pursuing research in design engineering and working as an engineer at a product design studio, he joined Nature Architects as a founding member. He received the Software Japan Award in 2024
The Future of Autonomous Design: From Generative AI to Agentic AI
Presentation Abstract
“How can we develop better products, faster?” This is a fundamental question faced by every manufacturing industry. However, the traditional process, in which humans repeatedly carry out design, simulation, and testing, requires enormous time and cost and is increasingly reaching its limits amid intense global competition.
The rapid advancement of AI over the past few years has opened a new path beyond these constraints. From Design Optimization to Generative Design, we are now entering the era of Autonomous Design, in which Agentic AI can autonomously derive optimal design solutions. The use of AI in the design process is no longer optional, but essential, fundamentally transforming the paradigm of product development.
In this presentation, I will introduce the principles of AI-driven design, AslanX, Narnia Labs’ AI platform that brings these principles into practice, and a range of successful real-world applications across the manufacturing industry.
Speaker Bio
Namwoo Kang is the CEO of Narnia Labs and an Associate Professor at KAIST. He previously worked as a Research Engineer at Hyundai Motor Company.
He received his Ph.D. in Design Science from the University of Michigan. He also earned an M.S. in Technology Management and a B.S. in Mechanical and Aerospace Engineering from Seoul National University.
His research focuses on Agentic AI-driven engineering design through the integration of physics and data. His research interests include generative design, data-driven design, machine learning, deep learning, design optimization, topology optimization, CAD, CAM, CAE, and HCI.
Unlocking the Geometry Bottleneck: Evolving the Simulation Stack
Presentation Abstract
The pressure to compress concept-to-product timelines reveals a critical flaw: the simulation stack cannot scale. Traditional pipelines are bottlenecked by geometry, which constantly changes representations across the lifecycle, moving from Implicit or CAD in design, to meshes, voxels, G-Code in manufacturing, to raw point clouds in QA. Because legacy analysis requires conformal meshing, manual preprocessing is forced at every stage, stalling automated iteration.
To evolve, simulation must become a geometry-agnostic infrastructure. Using immersed grid methods, Intact natively ingests these variable representations without preprocessing, exposing physics as an API-first service. We demonstrate how decoupling physics from geometry eliminates the manual bottlenecks, showcasing a workflow that handles diverse lifecycle formats to accelerate delivery timeframes.
Speaker Bio
SUB OPTIMAL
Presentation Abstract
Our computational design approaches to optimisation are often constrained by the tools at our disposal and by extension the established methods of generating new optimal forms.
With the revolution in AI coding tools, the barrier for designers to develop their own software tools and pipelines has never been lower.
Sub-Optimal explores what becomes possible when the context of optimisation is reframed around two priorities: (i) preserving the original designer’s macro intent, and (ii) embracing, through geometry, the anisotropic surface roughness that plagues additive manufacturing. The resulting approach is neither lattice application nor topology optimisation, but a simulation, surface texture and build orientation driven grown honeycomb structure that remains largely invisible at the macro level.
The talk closes on how the pipeline behind this approach was built in six weeks for $400 of AI tokens, leveraging a rich ecosystem of open-source libraries (including geometry3Sharp, PicoGK and OpenVDB) and formats such as 3MF. At a fraction of the cost of off-the-shelf tools, all that matters now is how creative you, the designer, can be.
Speaker Bio
Sarat Babu is a designer, engineer and strategist who has spent over fifteen years working at the convergence of computational design, materials and advanced manufacturing. He founded and scaled the additive technology consultancy Betatype, building London’s only commercial titanium additive manufacturing site before its acquisition in 2020; served as Chief Digital Officer at Alloyed; and most recently developed AI and AR wearable devices as a Principal Product Design Engineer at Meta. He holds a doctorate and several patents in medical, consumer electronics and additive manufacturing fields. He currently helps technically ambitious companies build products to match their vision, alongside an independent research practice exploring design and materials for product engineering, where he still builds hands-on.
Case Study: Development of Auto-design Workflow for Heat Exchanger
Presentation Abstract
This presentation outlines the development of an automated design workflow in an aerospace R&D project focused on heat exchangers manufactured using metal 3D printing (L-PBF). The project required extensive geometric exploration of the diaphragms in fluid channels by generating large numbers of 3D models by changing multiple parameters that define the geometry. Conventional 3D-CADs proved inefficient for this scale of design iteration, motivating the creation of a more programmable and scalable approach.
To address this challenge, a hybrid workflow was established using Grasshopper and nTop, two computational design platforms with fundamentally different geometric representation methods. Grasshopper, based on B-Rep method, enables detailed manipulation of non-thickness geometries but suffers from inherent mathematical limitations such as self-intersection during thickening operations. In contrast, nTop employs SDF (signed distance field/implicit modeling), which inherently avoid self-intersection and provide robust performance in thickening and boolean operations, though they are less suited for detailed geometric manipulation.
The presentation explains the contrasting characteristics of these two software systems and how to use them to compensate each other for their respective limitations. Through practical examples, it illustrates how the established workflow automates geometry generation, supports large scale parametric exploration, and enhances the efficiency of design iterations for complex AM components.
Speaker Bio
Founder of YAMAJI DESIGN / computational designer (nTop and Grasshopper) – He is an engineer with more than 15 years of experience in DfAM (design for additive manufacturing) across multiple industries. At a service bureau specializing in AM, he provided R&D support and DfAM training for U.S. military bases in Japan. He later worked in an aerospace company, where he contributed to R&D project to develop the heat exchanger for airplane using metal L-PBF.
When Failure Is Not an Option: Bringing Certifiable AI to Engineering Design
Presentation Abstract
Artificial intelligence is poised to automate a large share of design engineering work, yet the technology that excites the commercial world poses a fundamental problem for high-consequence industries. Generative AI is probabilistic by nature. It produces plausible answers, not provably correct ones. In sectors where a single structural failure can ground a fleet, halt a production line, or cost lives, plausibility is not enough. The question is no longer whether AI will transform engineering, but whether we can trust it when failure is not an option.
This talk presents a different path. Cognitive Design Systems is a design exploration platform for mechanical and thermo-mechanical component design. Rather than embedding opaque AI inside traditional CAD software, we bring proven engineering workflows to the AI. Deterministic solvers for topology optimization, finite element analysis, manufacturing-driven design, and cost and carbon assessment produce repeatable, auditable, physically grounded results. A conversational AI layer orchestrates these solvers, interpreting intent and chaining tasks, while the underlying engineering computation remains fully deterministic and traceable. Engineers gain dramatic speed without surrendering verifiability or control.
This is not theoretical. Our approach is shaped by work with demanding industrial leaders including Safran, Thales, MBDA, Toyota, Tetra Pak, and Logitech, spanning aerospace, automotive, defense, and industrial machinery. These are organizations where engineering rigor and certification are non-negotiable.
The implications reach across every engineering sector. As manufacturers face mounting pressure to lightweight structures, accelerate certification, reduce cost and carbon, and modernize their industrial base, the ability to design qualified components faster, with full auditability, becomes a decisive advantage. Trustworthy AI is not a constraint on innovation. It is the precondition for deploying AI in the systems the world depends on. Attendees from industry and policy alike will leave with a clearer view of what responsible, deployable AI for high-consequence engineering actually looks like.
Speaker Bio
Organization:
nTop
Presenter:
Brad Rothenberg
Fast and Robust Design with Implicit Functions and Direct Simulation
Presentation Abstract
Current Computer Aided Design systems excel in static detailed design but are too fragile and slow to support Design Exploration and Multidisciplinary Design Optimization for conceptual and preliminary design. This talk introduces a new approach to modeling products that overcomes these shortcomings based on implicit functions popularized in the animation industry. The main benefits of the approach is that is responsive to the need to design and redesign products in days or weeks and not month or years because of absolute robustness to parametric change minimizing human intervation; lightning fast evaluations leveraging GPUs; and performing analysis directly from the representation w/o the need of human intervention to generate cumbersome and error prone meshes.
Speaker Bio
HYBEX
Presentation Abstract
Speaker Bio
Why Attend
CDFAM Tokyo brings together a senior technical audience of engineers, architects, researchers, and software developers working at the intersection of computational design, AI, and machine learning.
The program is structured around practitioner-led presentations and direct peer exchange. Attendees engage directly with the people doing the work, across disciplines and across scales.
For those working in the Asia-Pacific region, CDFAM Tokyo is the first event in the series to take place locally, offering access to a global network of computational design practitioners without the transatlantic travel.
If your work sits at the intersection of computation and physical design, whether in materials, structures, building systems, or the software that drives them, this is the event to attend.
Register to Attend
Present at CDFAM Tokyo
Submissions are open. We welcome proposals from practitioners and researchers working on computational design, AI and machine learning, across engineering, architecture, and software development.
Sponsor & Partner
CDFAM Tokyo is the first event in the series to take place in the Asia-Pacific region, and we are actively seeking sponsors and regional partners.
Sponsorship provides direct access to a senior technical audience across engineering, architecture, and software development.