|
Manuel Ladron de Guevara
Senior Machine Learning Engineer, Higharc · New York
I am a Senior Machine Learning Engineer at Higharc, where I have worked since February 2024 on machine learning for residential building design. My work focuses on how to represent buildings for machine learning models, and on models that furnish rooms inside a BIM (Building Information Modeling) tool: our DDEP model places furniture and fixtures in a room and runs in Higharc's product. Our paper on this work, BIM-Native Tokenization for Constraint-Aware Room Layout Synthesis, received the Best Industrial Paper Award at EUVIP 2026.
I received my PhD in Computational Design from Carnegie Mellon University in 2024, advised by Ramesh Krishnamurti and Daragh Byrne, with Jun-Yan Zhu on my committee. My dissertation, Parametric-Based Models for Artistic Representations, studied optimization and learning methods that paint with parametric brush strokes. During the PhD I was a research scientist intern at Adobe Research in 2021, with Aaron Hertzmann and Matt Fisher, and in 2022, with Daichi Ito, Jose Echevarria, Yannick Hold-Geoffroy, Yijun Li and Cameron Smith. I also taught as a studio instructor at the CMU School of Architecture.
Before the PhD, I completed a Master's in Advanced Architectural Design at CMU, focused on robotic fabrication with Jeremy Ficca, and a B.Arch and M.Arch at the Polytechnic University of Catalonia, with honors for my thesis project. I practiced as an architect in Spain, and I co-founded Flumio, a text-to-fabrication furniture startup, and CRAIDL, a creative AI group at CMU.
Email: rldg.manuel [at] gmail [dot] com
Email /
Google Scholar /
LinkedIn /
Twitter /
Github
|
|
|
BIM-Native Tokenization for Constraint-Aware Room Layout Synthesis
Manuel Ladron de Guevara,
Jinmo Rhee,
Ardavan Bidgoli,
Vaidas Razgaitis,
Michael Bergin
European Conference on Visual Information Processing (EUVIP), 2026
Best Industrial Paper Award
[Project Page]
[Paper]
[arXiv]
[Slides]
[Video]
|
|
Segmentation-Based Parametric Painting
Manuel Ladron de Guevara,
Matt Fisher,
Aaron Hertzmann
IEEE International Conference on Multimedia and Expo Workshops (ICMEW), 2024
[Project Page]
[arXiv]
[Code]
|
|
Parametric-Based Models for Artistic Representations
Manuel Ladron de Guevara
PhD Dissertation, Carnegie Mellon University, 2024
Advisors: Ramesh Krishnamurti and Daragh Byrne. Committee: Jun-Yan Zhu
[Dissertation]
|
|
|
Cross-modal Latent Space Alignment for Image to Avatar Translation
Manuel Ladron de Guevara,
Jose Echevarria,
Yijun Li,
Yannick Hold-Geoffroy,
Cameron Smith,
Daichi Ito
IEEE/CVF International Conference on Computer Vision (ICCV), 2023
[Paper]
[Supplementary]
|
|
|
Design Intents Disentanglement: A Multimodal Approach for Grounding Design Attributes in Objects
Manuel Ladron de Guevara,
Alexander Schneidman,
Daragh Byrne,
Ramesh Krishnamurti
CAADRIA, 2022
[Paper]
[Code]
|
|
|
Bubble2Floor: A Pedagogical Experience With Deep Learning for Floor Plan Generation
Pedro Veloso,
Jinmo Rhee,
Ardavan Bidgoli,
Manuel Ladron de Guevara
CAADRIA, 2022
[Paper]
|
|
|
MixerGAN: An MLP-Based Architecture for Unpaired Image-to-Image Translation
George Cazenavette,
Manuel Ladron de Guevara
Preprint, 2021
[Paper]
|
|
|
Artistic style in robotic painting; a machine learning approach to learning brushstroke from human artists
Ardavan Bidgoli,
Manuel Ladron de Guevara,
Cinnie Hsiung,
Jean Oh,
Eunsu Kang
IEEE International Conference on Robot and Human Interactive Communication (RO-MAN), 2020
[Paper]
[Presentation]
[Video]
[Code]
|
|
|
Multimodal Word Sense Disambiguation in Creative Practice
Manuel Ladron de Guevara,
Christopher George,
Akshat Gupta,
Daragh Byrne,
Ramesh Krishnamurti
IEEE International Conference on Machine Learning and Applications (ICMLA), 2020
[Paper]
|
|
|
Multi-resolution in architecture as a design driver for additive manufacturing applications
Manuel Ladron de Guevara,
Luis Borunda,
Daragh Byrne,
Ramesh Krishnamurti
International Journal of Architectural Computing (IJAC), 2020
[Paper]
|
|
|
A multi-resolution design methodology based on discrete models
Manuel Ladron de Guevara,
Luis Borunda,
Ramesh Krishnamurti
CAAD Futures, 2019
[Paper]
|
|
|
Robotic free-oriented additive manufacturing technique for thermoplastic lattice and cellular structures
Manuel Ladron de Guevara,
Luis Borunda,
Jeremy Ficca,
Daragh Byrne,
Ramesh Krishnamurti
CAADRIA, 2019
[Paper]
|
|
|
Design Method for Optimized Infills in Additive Manufacturing Thermoplastic Components
Luis Borunda,
Manuel Ladron de Guevara,
Jesus Anaya
eCAADE, 2019
[Paper]
|
|
|
Optimized Additive Manufacturing Building Components
Luis Borunda,
Manuel Ladron de Guevara,
Gianluca Pugliese,
Rafael Claramunt,
Marta Muñoz,
Jesus Anaya
IV International Conference on Technological Innovation in Building, 2019
[Paper]
|
Startups and Research Labs Founded
|
|
