PeopleofSuperintelligence

Researcher

Hyung Ju Suh

Also known as Terry Suh, Hyung Ju Terry Suh, H.J. Terry Suh

Hyung Ju Suh is a robotics researcher and company co-founder who develops artificial intelligence, optimization, and control methods for contact-rich robot manipulation. He earned a B.S. in mechanical engineering and computer science at Caltech, where he received the Jack E. Froehlich Memorial Award and the Henry Ford II Scholar Award in 2018, and completed a Ph.D. in electrical engineering and computer science at MIT CSAIL under Russ Tedrake in 2024. During his doctoral studies, he interned at Toyota Research Institute in 2020 and the Boston Dynamics AI Institute in 2023, won an ICML 2022 Outstanding Paper award for work on policy gradients in differentiable simulators, and coauthored MIT studies on whole-body contact planning in 2023 and the PhysicsGen simulation pipeline in 2025. Since 2025, he is CTO and co-founder of CarbonSix, which raised a $4 million seed round in May 2025 to build AI-based manipulation systems for manufacturing.

Now at
CarbonSix
Badges

Timeline

  1. 2018

    Caltech Froehlich and Ford awards

    In 2018, Caltech gives him the Jack E. Froehlich Memorial Award, which goes to a junior in the upper five percent of the class with promise for a creative professional career. By June 2018, as a mechanical engineering student advised by Joel Burdick, he also receives the 2018 Henry Ford II Scholar Award.

  2. 2020

    Linear models for object piles

    During June 2020, he interns for the summer on the manipulation team at Toyota Research Institute with Naveen Kuppuswamy. With Russ Tedrake, he coauthors “The Surprising Effectiveness of Linear Models for Visual Foresight in Object Pile Manipulation” in 2020 for the International Workshop on the Algorithmic Foundations of Robotics.

  3. 2022

    An ICML Outstanding Paper

    Working with Max Simchowitz, Kaiqing Zhang, and Russ Tedrake in 2022, he coauthors “Do Differentiable Simulators Give Better Policy Gradients?”, which finds that stiffness or discontinuities in physical systems can compromise first-order policy-gradient estimates. The authors propose an α-order estimator that combines first-order efficiency with zero-order robustness, and ICML names the paper an Outstanding Paper in 2022.

  4. June 2023

    Boston Dynamics AI Institute internship

    In June 2023, he starts an internship at the Boston Dynamics AI Institute, where he works with Tao Pang and Jiuguang Wang.

  5. August 2023

    Planning with whole-body contact

    At MIT CSAIL in August 2023, he co-leads a study that uses smoothing to simplify contact-rich manipulation planning for robots. The method produces effective plans in about a minute on a standard laptop and appears in IEEE Transactions on Robotics.

  6. October 2024

    A contact-rich manipulation thesis

    In October 2024, he defends “Leveraging Structure for Efficient and Dexterous Contact-Rich Manipulation” with MIT CSAIL's Robot Locomotion Group, completing a Ph.D. in electrical engineering and computer science in 2024. The thesis uses smoothing to support gradient-based local control and connects it with sampling-based planners for long-horizon plans.

  7. 2025

    PhysicsGen simulation data

    As an MIT Ph.D. student in July 2025, he coauthors MIT's PhysicsGen paper. The system turns a few dozen virtual-reality demonstrations into nearly 3,000 simulations per machine for robotic arms and hands.

  8. Since 2025

    CarbonSix CTO and co-founder

    In May 2025, CarbonSix announces a $4 million seed round for AI-based manipulation in manufacturing, with Suh as CTO and founding member alongside Co-CEO Jehyeok Kim. As CTO and co-founder of CarbonSix, he focuses on AI, optimization, and control for contact-rich robot manipulation, holding a Ph.D. from MIT CSAIL under Russ Tedrake and a B.S. in mechanical engineering and computer science from Caltech.

Career

  1. NowCarbonSixCTO, Co-founder

Education

  1. 2024MIT CSAILPhD
  2. California Institute of TechnologyB.S.

From the biography.

  1. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes Massachusetts Institute of Technology. We estimate where the people shaping AI studied and where their careers led. Massachusetts Institute of Technology leads with 467 former students, including 291 recorded doctorates.
  2. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other universityIncludes Massachusetts Institute of Technology. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other university. We compare doctorate and 5+ year employment links, career timing and current workplaces for 187 major-prize and 1,111 best-paper winners.
  3. Google had the most people shaping AI every year from 2014 to 2025Includes Massachusetts Institute of Technology. Our estimates of which organizations employed the most people shaping AI each year from 1955 to 2025, tracing the shift from university labs to companies.
  4. The company share of AI researchers’ top papers was 31% in 2020–2024 and 8% in 1970–1974Includes Massachusetts Institute of Technology. We estimate where the people shaping AI worked when their most-cited papers appeared: the company share was 31% in 2020–2024 and 8% in 1970–1974, and Google led all organizations in 2020–2024.

Colleagues

People named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Hyung Ju Suh yet. Send us a free-licensed photo.

  1. IST Meeting of the Minds 2018 - Computing + Mathematical Sciences cms.caltech.edu. Checked 22 October 2026.
  2. Terry Suh Receives 2018 Henry Ford II Scholar Award eas.caltech.edu. Checked 22 October 2026.
  3. Home page - HJ Robotics hjrobotics.net. Checked 22 October 2026.
  4. Publications - HJ Robotics hjrobotics.net. Checked 22 October 2026.
  5. Do Differentiable Simulators Give Better Policy Gradients? proceedings.mlr.press. Checked 22 October 2026.
  6. ICML 2022 Awards icml.cc. Checked 22 October 2026.
  7. AI helps robots manipulate objects with their whole bodies csail.mit.edu. Checked 22 October 2026.
  8. Thesis Defense, H.J. Terry Suh. Leveraging Structure for Efficient and Dexterous Contact-Rich Manipulation csail.mit.edu. Checked 22 October 2026.
  9. Robot Locomotion Group locomotion.csail.mit.edu. Checked 22 October 2026.
  10. Simulation-based pipeline tailors training data for dexterous robots eecs.mit.edu. Checked 22 October 2026.
  11. Carbonsix: $4 Million Seed Funding Raised For AI-Based Manipulation For Manufacturing pulse2.com. Checked 22 October 2026.
  12. H.J. Terry Suh Ph.D. | CarbonSix carbon6robotics.com. Checked 22 October 2026.