Portrait
Junpeng Gao
PhD Student
Carnegie Mellon University

Hello, I am a PhD student advised by Prof. Andrew Spielberg in the Computational Invention Lab at CMU ECE. Previously, I earned my Master's degree in Computational Science and Engineering from ETH Zurich and my Bachelor's in Physics from ShanghaiTech University. I enjoy solving real-world geometry problems in computational design and fabrication, as well as simulation problems in animation and robotics. I believe, to understand better physics simulation, we need to learn more about geometry processing and shape modeling. Happy to chat if you have interest if our interests align.

During my master study, I worked on modeling soft robots with Mike Y. Michelis and Prof. Andrew Spielberg. I finished my master thesis at Interactive Geometry Lab supervised by Prof. Olga Sorkine-Hornung. I was also an open-source contributer in Julia community before and implemented some high-performance numerical ODE solvers.

In my spare time, I enjoyed board games, manga and anime. I also had a great time doing Super Kondi when I was in Zurich.

Education
  • Carnegie Mellon University
    Carnegie Mellon University
    Electrical and Computer Engineering
    Ph.D. Student
    2025 - present
  • ETH Zurich
    ETH Zurich
    M.Sc. in Computational Science and Engineering
  • ShanghaiTech University
    ShanghaiTech University
    B.S. in Physics
Honors & Awards
  • IEEE RA-L Best Paper Award
    2024
  • Julia Community News
    2021
News
2025
Our paper received the RA-L Best Paper Award as one of only five papers for the year 2024 from among more than 1,500 papers published in RA-L during 2024!
Jan 13
2024
Our paper Sim-to-Real of Soft Robots with Learned Residual Physics has been accepted by RA-L. Check the project page
Jul 24
2021
My first open source contribution of three ODE solvers has been merged! Check the community news
May 24
Selected Publications (view all )
Retrofitting Existing 3D Objects with Surface-Conforming Capacitive Sensing
Retrofitting Existing 3D Objects with Surface-Conforming Capacitive Sensing

Andjela Ilic, Junpeng Gao, Zhipeng Li, Yijing Jiang, Rachel Schuchert, Manuel Meier, Philipp Herholz, Christian Holz

ACM SIGGRAPH 2026

A computational fabrication pipeline that retrofits existing 3D objects with mutual-capacitance touch sensing conforming to their curved surfaces. I contributed the geometry modeling part of the project, including surface curve sampling and the 3D-to-2D unfolding that turns the sensor layout into fabrication-ready stencils.

Retrofitting Existing 3D Objects with Surface-Conforming Capacitive Sensing

Andjela Ilic, Junpeng Gao, Zhipeng Li, Yijing Jiang, Rachel Schuchert, Manuel Meier, Philipp Herholz, Christian Holz

ACM SIGGRAPH 2026

A computational fabrication pipeline that retrofits existing 3D objects with mutual-capacitance touch sensing conforming to their curved surfaces. I contributed the geometry modeling part of the project, including surface curve sampling and the 3D-to-2D unfolding that turns the sensor layout into fabrication-ready stencils.

Sim-to-Real of Soft Robots with Learned Residual Physics
Sim-to-Real of Soft Robots with Learned Residual Physics

Junpeng Gao, Mike Y. Michelis, Andrew Spielberg, Robert K. Katzschmann

IEEE Robotics and Automation Letters (RA-L) 2024 Best Paper Award 2024

Our paper on sim-to-real transfer of soft robots using learned residual physics was accepted by RA-L and received the Best Paper Award as one of only five papers for the year 2024 from among more than 1,500 papers published in RA-L during 2024.

Sim-to-Real of Soft Robots with Learned Residual Physics

Junpeng Gao, Mike Y. Michelis, Andrew Spielberg, Robert K. Katzschmann

IEEE Robotics and Automation Letters (RA-L) 2024 Best Paper Award 2024

Our paper on sim-to-real transfer of soft robots using learned residual physics was accepted by RA-L and received the Best Paper Award as one of only five papers for the year 2024 from among more than 1,500 papers published in RA-L during 2024.

All publications