CDFAM Computational Design Symposium

Recorded at CDFAM Computational Design Symposium, NYC, October 29-30, 2025https://cdfam.com/nyc-2025/

Organization:MITPresenter:Alfonso Parra RubioCrease, Fold, Transform. Presentation AbstractFolding is a fundamental process found throughout nature on multiple scales. Rather than altering the material itself, folding transforms its shape, offering a powerful means of engineering without compromising integrity.This presentation explores, from an engineering and design perspective, the unique potential of folding and discrete assembly as a design and manufacturing tool across multiple scales in engineering.From millimeter-scale bulk cellular materials to meter-scale structural corrugations and actuated robotic systems, and ultimately to architectural shell structures spanning tens of meters, folding enables the creation of high-performance, architected materials.Speaker BioAlfonso Parra Rubio is a PhD candidate at the Massachusetts Institute of Technology, working at the Center for Bits and Atoms led by Neil Gershenfeld. His research explores how folding and discrete assembly can be combined to design and manufacture architected materials across multiple scales: from bulk cellular materials (millimeters to centimeters), to structural corrugations and actuated systems (centimeters to meters), and up to architectural-scale shell structures (meters to decameters). His work fundamentally explores how materials and structures are designed, engineered, manufactured, and assembled. In addition to his academic research, he founded RnKolektive, a collaborative platform for sculptural exploration. This parallel practice focuses on mixed-media works that merge folding techniques with blown glass, creating pieces that use the same research contributions but with an expressive intention.

Recorded at CDFAM Computational Design Symposium, NYC, October 29-30, 2025https://cdfam.com/nyc-2025/

OrganizationPrinceton UniversityPresenter:Tuo ZhaoSuper-Modular Chiral Origami MetamaterialsPresentation AbstractMetamaterials with multimodal deformation mechanisms resemble machines, especially when endowed with autonomous functionality. A representative architected assembly, with tunable chirality, converts linear motion into rotation (1). These chiral metamaterials with a machine-like dual modality have potential use in areas such as wave manipulation, optical activity related to circular polarization and chiral active fluids. However, the dual motions are essentially coupled and cannot be independently controlled. Moreover, they are restricted to small deformation, that is, strain ≤2%, which limits their applications. Here we establish modular chiral metamaterials (2), consisting of auxetic planar tessellations and origami-inspired columnar arrays, with decoupled actuation. Under single-degree-of-freedom actuation, the assembly twists between 0° and 90°, contracts in-plane up to 25% and shrinks out-of-plane more than 50%. Using experiments and simulations, we show that the deformation of the assembly involves in-plane twist and contraction dominated by the rotating-square tessellations and out-of-plane shrinkage dominated by the tubular Kresling origami arrays. Moreover, we demonstrate two distinct actuation conditions: twist with free translation and linear displacement with free rotation. Our metamaterial is built on a highly modular assembly, which enables reprogrammable instability, local chirality control, tunable loading capacity and scalability. Our concept provides routes towards multimodal, multistable and reprogrammable machines, with applications in robotic transformers, thermoregulation, mechanical memories in hysteresis loops, non-commutative state transition and plug-and-play functional assemblies for energy absorption and information encryption.References:(1) Frenzel, T., Kadic, M. & Wegener, M. Three-dimensional mechanical metamaterials with a twist. Science 358, 1072–1074 (2017).(2) Zhao, Tuo (presenter), Dang, X., Manos, K., Zang, S., Mandal, J., Chen, M., & Paulino, G. H. Modular chiral origami metamaterials. Nature, 640(8060), 931-940 (2025).Speaker BioTuo Zhao is a postdoctoral research associate at Princeton University. His expertise is in computational mechanics, nonlinear topology optimization, soft robotics, and mechanical metamaterials. Tuo is currently addressing the scalability challenge for developing useful metamaterials. By integrating an untethered actuation scheme (e.g., three-dimensional magnetic fields and micro-magnetic responsive materials), he designs micro-robotic machines with tunable properties on demand.

Recorded at CDFAM Computational Design Symposium, NYC, October 29-30, 2025https://cdfam.com/nyc-2025/

Organization: STILFOLD

https://www.stilfold.com/

Presenter:Julia HannuGreener by Every Fold. Strength in Every Curve. Presentation AbstractThis talk introduces STILFOLD’s innovative origami-inspired manufacturing process, where metal sheets are folded into form. The process uses both straight and curved crease folding, expanding the possibilities of how sheets can be transformed into products. This, to make curved crease folding accessible to a wider community of designers and engineers – moving it from a niche research technique into a scalable industrial method. Our aim is to develop a more environmentally friendly way of making things – reducing the number of parts, energy consumption, material use and transportation needs. Achieving this involves multiple layers of complexity: from designing folding patterns of efficient structures to developing dedicated folding systems for production at scale.The presentation will share insights into how STILFOLD is pushing to transform folding into a sustainable and practical approach to manufacturing – and what that could mean for the future of design, engineering, and production.Speaker BioJulia Hannu is a Software Engineer and Computational Design Lead at STILFOLD, where she develops digital tools and algorithms to enable new approaches to sustainable manufacturing and design. Her work centers on transforming complex geometric challenges into practical, efficient, and user-friendly solutions. With a background in architecture and an MSc in Architectural Computation from UCL, she combines experience from practice and academia to bridge technology, design, and sustainability.

Recorded at CDFAM Computational Design Symposium, NYC, October 29-30, 2025https://cdfam.com/nyc-2025/

OrganizationTetmet

https://www.tetmet.net/

Presenter:Rachel AzulayConformal Lattice Design Made Easy: A CAD-Integrated ApproachPresentation AbstractTETMET has developed an innovative process to produce large-scale lattice structures in an automated way, enabling applications across multiple industries.However, existing lattice design software has significant limitations, particularly when it comes to creating efficient, manufacturable conformal lattice structures. Most available tools were developed with general 3D printing in mind, offering only basic latticing capabilities that fail to meet the demands of more advanced applications.Our approach takes a different path by integrating lattice design seamlessly into traditional CAD workflows. By combining the flexibility of CAD with the specific requirements of lattice generation, we significantly enhance the design process—allowing engineers to work with familiar tools while unlocking new possibilities for complex, high-performance structures.Speaker BioRachel holds a PhD in Lattice Structure Design and leads the Application Engineering team at TETMET. She specializes in transforming complex customer challenges into innovative, lightweight lattice solutions, bridging cutting-edge research with real-world applications.

Recorded at CDFAM Computational Design Symposium, NYC, October 29-30, 2025https://cdfam.com/nyc-2025/

OrganizationScawo3DPresenter:Philip Schneider + Timo ZollnerComputational Design for Assembly: Automating Design Workflows for 3D Concrete Printed Freeform StaircasesPresentation AbstractBuilding large freeform reinforced concrete staircases has always been a challenge. Traditional methods rely on labor-intensive wooden or EPS formwork, making many designs too expensive. This can be changed with Selective Paste Intrusion, a new 3D concrete printing technique by Scawo3D using a large particle bed, with no constraints related to print overhangs or angles.While fabrication now allows full geometric freedom, the design process became the bottleneck. Our previous AutoCAD-based solution, initially developed for producing G-codes for CNC-milling EPS formwork blocks, was not viable for 3D printing. Manual 3D modeling made scaling production impossible, leaving the printer underused. To solve this, Timo Harboe Zollner developed an automated workflow that cuts design time by up to 95%. This approach balances automation with intuitive user input, transforming 2D geometry into finely detailed 3D models in minutes. It integrates SubDs, meshes, volumetric modeling, and implicit modeling, achieving in moments what once took days.This presentation highlights the adaptation of computational design to a new production method—one with only few geometric constraints yet capable of achieving material properties comparable to standard concrete.Speaker BioPhilip Schneider Computational & Architectural Design Lead at Scawo3D and founder of Skeno. He holds a M.A. from TU Munich with a focus on computational methods in architecture and specialises in 3D concrete printing by Selective Paste Intrusion at an architectural scale. Since 2022, he has led the design and fabrication of the first projects realised by SPI in academia and industry.Timo Harboe Zollner is the founder of Timo Harboe ApS, a Copenhagen-based consultancy specializing in automating processes related to geometry, particularly within additive manufacturing. With a background in structural engineering and computational design, Timo collaborates with clients to develop parametric workflows and digital tools that streamline complex design and fabrication processes. His recent projects include automating the generation of 3D-printed formwork for freeform concrete staircases together with Scawo3DAbout CDFAM:CDFAM is a global symposium series at the forefront of computational design, advanced manufacturing, and performance-driven engineering. With a strong emphasis on innovation, CDFAM highlights how leading companies and researchers are leveraging AI, machine learning, and simulation technologies to drive the next generation of design tools, workflows, and digital fabrication methods.The symposium fosters cross-disciplinary collaboration and knowledge exchange between designers, engineers, and technologists exploring the cutting edge of digital design — from generative workflows.Past presenters and partners include companies such as NVIDIA, NASA, New Balance, BMW, ARUP, Foster +, Partners, BIG, Autodesk, Dassault Systèmes, nTopology, PyhicsX, Neural Concept, Siemens and more, showcasing how computation and AI are transforming everything from aerospace to footwear.Learn more at

https://cdfam.com

Recorded at CDFAM Computational Design Symposium, NYC, October 29-30, 2025https://cdfam.com/nyc-2025/nTopBradley RothenbergFrom 3 Configurations to 300: Rapid Trades for Advanced Aircraft DesignPresentation AbstractAircraft development timelines have collapsed from 7 years to 18 months, but design tools still assume you have years to iterate. The result: teams freeze architecture in week 2, before they understand the design space, and spend the rest of the program managing the consequences.The core problem is going from requirements-to-design is just too slow. Serial design evaluations, manual CAD updates that fail to parametrize correctly, and expensive simulation cycles create weeks-long iteration loops.nTop solves this through three architectural principles: Parametric models that remain robust under any design change. No geometry failures, no manual repairs; integrated notebooks capturing engineering knowledge in executable form; and GPU-native solvers enabling interactive design-analysis cycles with performance feedback in minutes.What’s the alternative? Exploring 3-4 hand-crafted configurations slowly or quickly committing to a single concept. Neither is likely to win. nTop enables systematic exploration of hundreds of variants in the time that traditional approaches evaluate three.This presentation demonstrates real examples: Group 1-3 UAS configurations generated and flight-tested in weeks, hypersonic vehicle trade studies evaluating hundreds of variants, and rapid weapons platform sizing with integrated CFD.The result: teams explore more, fail fast, and learn faster—improving win rates through comprehensive trade studies and defensible performance predictions.

About CDFAM:CDFAM is a global symposium series at the forefront of computational design, advanced manufacturing, and performance-driven engineering. With a strong emphasis on innovation, CDFAM highlights how leading companies and researchers are leveraging AI, machine learning, and simulation technologies to drive the next generation of design tools, workflows, and digital fabrication methods.The symposium fosters cross-disciplinary collaboration and knowledge exchange between designers, engineers, and technologists exploring the cutting edge of digital design — from generative workflows.Past presenters and partners include companies such as NVIDIA, NASA, New Balance, BMW, ARUP, Foster +, Partners, BIG, Autodesk, Dassault Systèmes, nTopology, PyhicsX, Neural Concept, Siemens and more, showcasing how computation and AI are transforming everything from aerospace to footwear.Learn more at

https://cdfam.com

Recorded at CDFAM Computational Design Symposium, NYC, October 29-30, 2025https://cdfam.com/nyc-2025/

Organization:

Pasteur Labs

Presenter:

Alexander Lavin

The Unreasonable Effectiveness of Simulation Intelligence

Presentation Abstract

Scientific rigor & engineering reliability have always been important yet contentious topics in the AI field. Recent AI trends crank up model sizes, but at what costs? Transparency and verifiability, amongst others that are core to industrial R&D—not to mention the massive spending. These costs are perhaps felt the most in physics simulation and digital engineering. Enter simulation intelligence (SI). SI is not antithetical to AI, rather it is the pragmatic approach to bringing AI capabilities into industrial R&D. Rather than LLMs atop legacy engineering tools or Foundation Models to opaquely replace physics solvers, we look to the combinatorial possibilities available when SI motifs are brought together—namely differentiable physics programming and surrogate modeling, yielding multiphysics modules. This talk will describe the distinction, that is: static CAE simulations vs dynamic simulators, bespoke surrogate models vs flexible multiphysics modules, massive black-box AI vs efficient programmatic SI. Examples from the SI Platform will elucidate end-to-end digital engineering pipelines, in diverse sectors from nuclear energy and data centers, to aerospace and automotive safety.

Speaker Bio

Alexander Lavin is a leading expert in AI-for-science and probabilistic computing. He’s Founder & CEO of Pasteur Labs (and non-profit “sister” Institute for Simulation Intelligence), reshaping R&D with a new class of AI-native simulators, commercializing in energy security, aerospace, materials & manufacturing sectors (

https://simulation.science

). For the last dozen years, Lavin has focused on artificial general intelligence (AGI) research with top startups in neuroscience and robotics (Vicarious, Numenta), and sold his prior ML-simulation startup Latent Sciences to undisclosed pharmaco in neurodegeneration R&D. Lavin also serves as AI Advisor for NASA, overseeing physics-ML efforts for the NASA-ESA “Digital Twin Earth” projects. Previously, Lavin was a spacecraft engineer with NASA and Blue Origin, and won several international awards for work in rocket science and space robotics (including Google Lunar XPrize during graduate studies at Carnegie Mellon). Lavin was named Forbes 30 Under 30 in Science, and a Patrick J. McGovern Tech for Humanity Changemaker

About CDFAM:CDFAM is a global symposium series at the forefront of computational design, advanced manufacturing, and performance-driven engineering. With a strong emphasis on innovation, CDFAM highlights how leading companies and researchers are leveraging AI, machine learning, and simulation technologies to drive the next generation of design tools, workflows, and digital fabrication methods.The symposium fosters cross-disciplinary collaboration and knowledge exchange between designers, engineers, and technologists exploring the cutting edge of digital design — from generative workflows.Past presenters and partners include companies such as NVIDIA, NASA, New Balance, BMW, ARUP, Foster +, Partners, BIG, Autodesk, Dassault Systèmes, nTopology, PyhicsX, Neural Concept, Siemens and more, showcasing how computation and AI are transforming everything from aerospace to footwear.Learn more at

https://cdfam.com

.

Recorded at CDFAM Computational Design Symposium, NYC, October 29-30, 2025https://cdfam.com/nyc-2025/

Organization:

ARENA-AI

Presenter:

Pratap Ranade

Artificial Intuition: Building an AI Mind for Electromagnetic Design

Presentation Abstract

Most advances in computational design focus on mechanical structure — domains we can visualize and have evolved an intuition for. But as modern hardware becomes increasingly software defined, the unseen and unintuitive world of electromagnetism is taking center stage. Conventional solvers can simulate fields, yet they cannot imagine new ones. In this talk, I’ll share how we’re pushing past that frontier by creating artificial intuition — AI systems that learn physical behavior inductively, not deductively. Drawing inspiration from quantum experiments like the Kondo mirage, where discovery outpaced simulation, I’ll show how our team built Atlas: an AI that learns directly from electromagnetic test data to verify, optimize, and eventually postulate new designs. We’ll share results from realworld applications in semiconductors and aerospace, and offer a teaser of what’s to come over the next twelve months.

Speaker Bio

Pratap Ranade, CEO and Founder of ARENA-AI

Join us at CDFAM Barcelona April 8-9, 2026, the premier symposium for computational design, AI, and engineering innovation.

Don’t miss your chance to connect with global leaders in design and technology.Register by February 1st to secure the early bird rate and be part of the conversation shaping the future of design, architecture, and advanced manufacturing.

Recorded at CDFAM Computational Design Symposium, NYC, October 29-30, 2025https://cdfam.com/nyc-2025/

Organization:

University of Southern California

Presenter:

David Gerber

Digital Twining a Living Lab

Presentation Abstract

The Living Lab Project is an innovative Viterbi initiative designed to enhance academic research and provide practical learning experiences through real-time monitoring and analysis of the new Ginsburg Hall building. Leveraging sensors embedded in the building’s systems and integrating cutting-edge digital twin technology, this project captures and analyzes data on energy usage, water consumption, building health and occupant well being, and more, offering a comprehensive dataset for faculty and student research. The project treats our newest building, a LEED platinum accredited building, as a scientific instrument to support both near term and longitudinal research across a multitude of disciplines including but not limited to Human Building Interaction, to AI, and sustainability related research fields

Speaker Bio

Dr. Gerber holds a joint appointment at USC’s Viterbi School of Engineering and the USC School of Architecture as a Professor of Civil and Environmental Engineering Practice and of Architecture. Dr. Gerber is the program Director for the Civil Engineering Building Science undergraduate program and the program Director for the Masters of Science in Emerging Technologies for Construction Program. Dr. Gerber is an associate director in the Office of Technology Innovation and Entrepreneurship. He teaches in the Viterbi School of Engineering, the School of Architecture and at the Viterbi Startup Garage. Dr. Gerber’s professional experience includes working in architectural, engineering and technology practices in the United States, Europe, India and Asia for Zaha Hadid Architects in London; for Gehry Technologies in Los Angeles; for Moshe Safdie Architects in Massachusetts; The Steinberg Group Architects in California; and for Arup as the Global Research Manager. Dr. Gerber’s research has been industry, fellowship, DoD, and NSF funded and is focussed on the development of innovative systems, tools, methods for design of the built environment. He has developed digital twin technologies and advises, and co advises PhD students from Architecture and Engineering on topics that integrate computer science, robotics, engineering, with architecture. David Gerber received his undergraduate architectural education at the University of California Berkeley (Bachelor of Arts in Architecture, 1996). He completed his first professional degree at the Design Research Laboratory of the Architectural Association in London (Master of Architecture, 2000), his post professional research degree (Master of Design Studies, 2003) and his Doctoral studies (Doctor of Design, June 2007) at the Harvard University Graduate School of Design. Dr. Gerber was the recipient of the Frederick Sheldon Fellowship at Harvard University and was a Research Fellow at MIT’s Media Lab in the Smart Cities group.

Recorded at CDFAM Computational Design Symposium, NYC, October 29-30, 2025https://cdfam.com/nyc-2025/

Organization:

CORE studio | Thornton Tomasetti

Presenter:

Sergey Pigach

Engineering Intelligence: Practical Applications of AI in Structural Engineering Practice

Presentation Abstract

Artificial Intelligence is no longer a distant future. It is actively shaping how structural engineers work, collaborate, and innovate. This session offers a practical look into how Thornton Tomasetti’s CORE studio is advancing AI integration within the firm, with a focus on real-world tools and workflows that enhance engineering practice. Attendees will explore the firm’s hands-on experimentation with generative models, domain-specific co-pilots, and applications of agentic workflows, as well as strategies for cross-disciplinary collaboration that ensure AI tools align with engineering priorities. The presentation will also share lessons learned in promoting firmwide adoption, cultivating technical fluency, and building an inclusive innovation culture that empowers all team members to contribute to AI-driven transformation.

Speaker Bio

Sergey Pigach is a Senior Associate Applications Engineer at CORE studio | Thornton Tomasetti. Sergey’s work builds on his architectural training by bridging the domains of technology and design, driving him to develop computational tools for architects, designers, and engineers. Since joining CORE studio he has worked on desktop and web-based projects including Swarm, a cloud compute solution for Grasshopper; ShapeDiver, a desktop client integration following a merger; and—most recently—Cortex, CORE Studio’s new MLOps platform.