PeopleofSuperintelligence

Researcher

Jae-Hyun Jung

Also known as Jaehyun Jung

Jae-Hyun Jung is a senior research scientist in the Human Performance and Experience (HPX) group at NVIDIA Research, where his work explores human-inspired AI and spatial intelligence. After a BS in electrical engineering at Pusan National University in 2007, he earned a PhD at Seoul National University in 2012 under Byoungho Lee, designing 3D displays and studying light-field imaging and binocular vision. From 2012 to 2024 he worked at Harvard Medical School and Mass Eye and Ear's Schepens Eye Research Institute, first as a postdoctoral fellow and then as an assistant professor of ophthalmology, designing prism eyeglasses for hemianopia and confocal imaging for visual prostheses. He became a Fellow of the American Academy of Optometry in 2019. At NVIDIA, which he joined in March 2024, he coauthored a real-time method for showing radiance fields on light field displays and Spatial-IQ, a 2026 benchmark that tests spatial reasoning in multimodal language models.

Timeline

  1. 2007–2012

    A PhD on 3D displays

    He earns a BS in electrical engineering from Pusan National University in 2007, graduating magna cum laude. In 2012, he completes a PhD in electrical engineering and computer science at Seoul National University with advisor Byoungho Lee, designing 3D displays and studying light-field imaging and binocular vision.

  2. 2012–2015

    Postdoc in the Peli Lab

    In 2012, he becomes a postdoctoral fellow in the Peli Lab at the Schepens Eye Research Institute of Mass. Eye and Ear and Harvard, where he stays until 2015. His paper "Active Confocal Imaging for Visual Prostheses" receives the fellows' Best Paper of the Year Award at Schepens in May 2015.

  3. 2015–2024

    Assistant professor at Harvard

    From 2015 to 2024, he is an assistant professor of ophthalmology in the Mobility Enhancement and Vision Rehabilitation Center of Excellence at Harvard Medical School and an assistant scientist at Mass Eye and Ear. His research covers applied visual perception, optical and display engineering for AR/VR, computational photography, vision restoration and human behavior.

  4. 2016–2017

    Prism eyeglasses for hemianopia

    In 2016, he coauthors three eyeglass designs with Eli Peli and Alex Bowers that use high-power prisms to expand the visual fields of patients with hemianopia, described in Optometry and Vision Science. In 2017, he receives the $30,000 Alice J. Adler Fellowship of the Schepens Eye Research Institute for a project on multiplexing prisms for homonymous hemianopia.

  5. 2019–2020

    Optometry fellowship and NIH grant

    He becomes a Fellow of the American Academy of Optometry at its annual meeting in Orlando in October 2019. In 2020, he wins an NIH/NEI R01 grant as principal investigator for Monocular Visual Confusion for Field Expansion, a project that develops optical devices to expand the visual field.

  6. March 2024

    Joining NVIDIA's HPX group

    In March 2024, he joins the Human Performance and Experience (HPX) group at NVIDIA Research to study human perception and its interaction with computational systems. His interests there include modeling walking and driving behavior, visual perception and optical devices in AR/VR, and human-computer interaction.

  7. 2025–2026

    Radiance fields on light field displays

    With Jonghyun Kim, Cheng Sun, Michael Stengel and other NVIDIA colleagues, he coauthors a framework for real-time radiance field rendering on light field displays, posted to arXiv in August 2025. On a Looking Glass display, it reaches more than 200 frames per second across 45 views, and the paper appears at High-Performance Graphics 2026 in July 2026.

  8. As of October 2026

    Spatial-IQ and human-inspired AI

    In July 2026, he and coauthors led by Patrick Rim release Spatial-IQ, a benchmark built with NVIDIA Isaac Sim that breaks object counting in stacked 3D structures into nine perceptual and cognitive sub-tasks to diagnose spatial reasoning in multimodal large language models; it is accepted to NeurIPS 2026. He is a senior research scientist in the HPX group at NVIDIA Research, working on human-inspired AI and spatial intelligence.

  1. Google had the most people shaping AI every year from 2014 to 2025Our estimates of which organizations employed the most people shaping AI from 1961 to 2025, with a year-by-year chart.
  2. The United States employs an estimated 53% of people in our data with a known employment countryOur estimates of where AI careers are concentrated now and how countries’ shares of dated positions changed over time.
  3. 46% of living people in our data with known birth and employment countries work outside their birth countryOur estimate of cross-border careers in AI, from country of birth and the country of each current organization.
  4. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionOur estimates of where the people shaping AI studied and where their careers led, from education records in cited biographies.

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 Jae-Hyun Jung yet. Send us a free-licensed photo.

  1. Home — Jae-Hyun Jung jjunglab.com. Checked 19 October 2026.
  2. Jae-Hyun Jung | Research research.nvidia.com. Checked 19 October 2026.
  3. News — Jae-Hyun Jung jjunglab.com. Checked 19 October 2026.
  4. High-power prismatic devices may further expand visual fields for patients with hemianopia | EurekAlert! eurekalert.org. Checked 19 October 2026.
  5. Jae-Hyun Jung, PhD, receives 2017 Alice J. Adler Fellowship | Harvard Medical School Department of Ophthalmology research.bidmc.org. Checked 19 October 2026.
  6. [2508.18540] Real-time 3D Visualization of Radiance Fields on Light Field Displays arxiv.org. Checked 19 October 2026.
  7. Real-time 3D Visualization of Radiance Fields on Light Field Displays research.nvidia.com. Checked 19 October 2026.
  8. [2607.22864] Spatial-IQ: Deconstructing Spatial Intelligence via Hierarchical Capability Tests arxiv.org. Checked 19 October 2026.