PeopleofSuperintelligence

Researcher

Davis Rempe

Davis Rempe is an NVIDIA researcher whose machine-learning work models object dynamics and human motion. He completed a Stanford computer science PhD in 2023 under Leonidas Guibas with NVIDIA Graduate Fellowship support for 2022–2023, after undergraduate work in computer science and mathematics at Nebraska with a physics minor. His work spans point-cloud learning, 3D pose recovery, AI-generated traffic scenarios, and the human-motion systems GEM and Kimodo. As of October 2026, he is a Senior Research Scientist at NVIDIA, focused on models for generating and perceiving human and humanoid motion.

Now at
NVIDIA
Works
34
Citations
1,356
h-index
13
Badges

Publication numbers from OpenAlex, as of 19 October 2026.

Timeline

  1. 2019

    Learning object dynamics

    In 2019, he coauthors a neural model that predicts final position and rotation of unseen 3D rigid objects from point clouds.

  2. 2020

    CaSPR point-cloud representations

    In 2020, he coauthors CaSPR, which learns canonical spatiotemporal point-cloud representations and receives a NeurIPS Spotlight.

  3. 2021

    HuMoR motion model

    In 2021, he coauthors HuMoR, a learned generative 3D human-motion model that helps recover pose and shape from observations.

  4. 2022–2023

    A Stanford doctorate

    He studies computer science and mathematics at the University of Nebraska with a physics minor, completes a Stanford computer science PhD in 2023 under Leonidas Guibas, and receives NVIDIA Graduate Fellowship support for 2022–2023.

  5. 2023

    Generating traffic scenarios

    In 2023, he and Or Litany present STRIVE, which generates realistic potential accidents for autonomous-vehicle planners with an AI traffic model trained on real-world data.

  6. 2025

    GEM for human motion

    In 2025, he coauthors GEM, a unified human-motion model that combines estimation with generation.

  7. 2026

    Kimodo motion generation

    In 2026, he coauthors Kimodo, a kinematic motion diffusion model trained on 700 hours of optical motion-capture data for expressive, controllable human-motion generation.

  8. As of October 2026

    Senior research scientist

    As of October 2026, he is a Senior Research Scientist at NVIDIA, focused on learned models for generating and perceiving human and humanoid motion.

Career

  1. Since 2022NVIDIASenior Research Scientist

Education

  1. 2023Stanford UniversityPhD in computer science
  2. University of NebraskaUndergraduate study in computer science and mathematics (physics minor)

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

Most-cited works

  1. A point-cloud deep learning framework for prediction of fluid flow fields on irregular geometries2021 · Physics of Fluids · 307 citationsWith Leonidas Guibas
  2. HuMoR: 3D Human Motion Model for Robust Pose Estimation2021 · IEEE/CVF International Conference on Computer Vision (ICCV) · 305 citationsWith Aaron Hertzmann
  3. Generating Useful Accident-Prone Driving Scenarios via a Learned Traffic Prior2022 · IEEE Computer Society Conference on Computer Vision and Pattern Recognition · 149 citationsWith Sanja Fidler
  4. Guided Conditional Diffusion for Controllable Traffic Simulation2023 · IEEE International Conference on Robotics and Automation · 126 citationsWith Marco Pavone
  5. Contact and Human Dynamics from Monocular Video2020 · Lecture notes in computer science · 104 citationsWith Aaron Hertzmann

From OpenAlex, as of 19 October 2026.

  1. 14% of AI career moves in the 2020s went from a university to a companyIncludes Davis Rempe. Our estimates of how university-to-company career transitions changed by decade, including roles added alongside an earlier job.
  2. Google alumni founded or led 87 other organizations, the most among the labs we compareIncludes NVIDIA. We trace 212 organizations founded or led by AI lab alumni, and 223 career moves between the labs.
  3. 44% of AI career moves go from one university to anotherIncludes NVIDIA. We estimate how 14,272 AI career moves link universities, companies, labs and government research centers, with net flows and the most common paths.
  4. Google has the highest combined h-index among AI organizationsIncludes NVIDIA. Our estimates of combined and median h-index at AI organizations, using current affiliations and OpenAlex records.

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 Davis Rempe yet. Send us a free-licensed photo.

  1. Learning Generalizable Physical Dynamics of 3D Rigid Objects arxiv.org. Checked 19 October 2026.
  2. Guibas Lab geometry.stanford.edu. Checked 19 October 2026.
  3. HuMoR: 3D Human Motion Model for Robust Pose Estimation arxiv.org. Checked 19 October 2026.
  4. Davis Rempe davrempe.github.io. Checked 19 October 2026.
  5. Davis Rempe | DAIR @ NVIDIA Research research.nvidia.com. Checked 19 October 2026.
  6. Generating AI-Based Potential Accident Scenarios for Autonomous Vehicles | NVIDIA Technical Blog developer.nvidia.com. Checked 19 October 2026.
  7. Davis Rempe davrempe.github.io. Checked 19 October 2026.
  8. Kimodo: Scaling Controllable Human Motion Generation arxiv.org. Checked 19 October 2026.