PeopleofSuperintelligence

Researcher

Jinhyung Park

Also known as David Park

Jinhyung Park is a robotics researcher whose work spans geolocation privacy, camera-only 3D vision, depth completion, human modeling and humanoid robotics. He earned a bachelor's degree in computer science at CMU in 2022 and completed a PhD at its Robotics Institute in August 2026 under Kris M. Kitani. His papers include Time Will Tell, Flexible Depth Completion and ATLAS, while GRAIL generates humanoid loco-manipulation from 3D assets and video priors. As of October 2026, he is a research scientist in NVIDIA Research's DAIR team, working on embodied intelligence, 3D scene understanding and human modeling.

Now at
NVIDIA
Works
34
Citations
384
h-index
7
Badges

Publication numbers from OpenAlex, as of 22 October 2026.

Timeline

  1. 2017

    Protecting location privacy

    At SIGSPATIAL LocalRec in 2017, he coauthors Protecting User Privacy: Obfuscating Discriminative Spatio-Temporal Footprints, a paper that considers entropy-based and adversarial obfuscation of geolocation trajectories for online identity protection.

  2. 2022

    A bachelor's degree at CMU

    He earns a bachelor's degree in computer science at CMU in 2022 while working with Kris Kitani.

  3. 2023

    Camera-only 3D detection

    At ICLR 2023, he coauthors Time Will Tell, a camera-only 3D detector that combines long-term, low-resolution matching with short-term, high-resolution matching.

  4. 2024

    Flexible depth completion

    At CVPR 2024, he coauthors Flexible Depth Completion for Sparse and Varying Point Densities, which uses Affinity-Based Shift Correction to align depth predictions with sparse and variable depth points.

  5. 2025

    A parametric human model

    At ICCV 2025, he coauthors ATLAS, a body model learned from 600,000 high-resolution scans that separates skeletal and shape parameters for fine-grained body control.

  6. 2026

    GRAIL for humanoid robotics

    In 2026, he coauthors GRAIL, a CoRL oral presentation that uses 3D assets and video priors to generate humanoid loco-manipulation demonstrations.

  7. August 2026

    A PhD on 4D scenes

    He completes a PhD at CMU's Robotics Institute in August 2026, advised by Kris M. Kitani, with a thesis titled Consistent Modeling of 4D Scenes for Perception and Generation.

  8. As of October 2026

    Research at NVIDIA DAIR

    As of October 2026, he is a research scientist in NVIDIA Research's Data-Driven AI for Robotics (DAIR) team, working on embodied intelligence, 3D scene understanding and human modeling.

Career

  1. NowNVIDIAResearch scientist
  2. 2013–2017Ministry of Science and ICT

Education

  1. 2026Carnegie Mellon UniversityPhD
  2. 2022Carnegie Mellon UniversityBachelor's degree

From the biography and OpenAlex affiliations (the years of papers that list the organization), so some years are approximate.

Most-cited works

  1. A Novel Multistage Transfer Learning for Ultrasound Breast Cancer Image Classification2022 · Diagnostics · 128 citations
  2. Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detection2022 · 68 citations
  3. Modality-Agnostic Learning for Radar-Lidar Fusion in Vehicle Detection2022 · IEEE Computer Society Conference on Computer Vision and Pattern Recognition · 50 citations
  4. Patchless Multi-Stage Transfer Learning for Improved Mammographic Breast Mass Classification2022 · Cancers · 44 citations
  5. netShip2013 · ACM IEEE Design Automation Conference · 14 citations

From OpenAlex, as of 21 October 2026.

  1. 16% of AI career moves in the 2020s went from a university to a companyIncludes Jinhyung Park. We estimate that 16% of AI career moves in the 2020s went from a university to a company; 29% of moves starting at a university went to a company, and 76% ended the university role.
  2. Google has the highest combined h-index among AI organizationsIncludes NVIDIA. We estimate that Google holds the highest combined h-index at 8,016, while universities account for 73% of the deduplicated total across AI organizations.
  3. 20% of people at companies who shape AI also hold a university role, led by Google and Stanford UniversityIncludes NVIDIA. We estimate that 539 of the 6,766 people with a known current organization (8%) hold both a university role and a company role, including 20% of people at companies and 13% of people at universities.
  4. Google alumni have founded or led 133 other organizations, more than any other AI labIncludes NVIDIA. We estimate that alumni of 17 major AI labs went on to found or lead 350 other organizations, including 226 they founded, and we trace 472 career moves directly between 23 labs since 2010.

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 Jinhyung Park yet. Send us a free-licensed photo.

  1. Jinhyung (David) Park jindapark.github.io. Checked 21 October 2026.
  2. Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detection arxiv.org. Checked 21 October 2026.
  3. Flexible Depth Completion for Sparse and Varying Point Densities openaccess.thecvf.com. Checked 21 October 2026.
  4. ATLAS: Decoupling Skeletal and Shape Parameters for Expressive Parametric Human Modeling openaccess.thecvf.com. Checked 21 October 2026.
  5. GRAIL: Generating Humanoid Loco-Manipulation from 3D Assets and Video Priors research.nvidia.com. Checked 21 October 2026.
  6. Jinhyung Park - Robotics Institute Carnegie Mellon University ri.cmu.edu. Checked 21 October 2026.
  7. DAIR @ NVIDIA Research research.nvidia.com. Checked 21 October 2026.