Jiahao Ji
Jiahao Ji standing beside a white-haired anime character

Algorithm Researcher · Noitom Robotics

Jiahao Ji 季嘉豪

I am a full-time Algorithm Researcher at Noitom Robotics. My work focuses on exploring and advancing scaling laws for embodied data.

My research interests include embodied foundation models, world models, and loco-manipulation. Before joining Noitom Robotics, I worked with Seed Robotics at ByteDance on digital asset reconstruction and dexterous manipulation. I’m always happy to chat about related research or potential collaborations—feel free to reach out.

Email Google Scholar LinkedIn GitHub

Updates

News

  • HiPHI and OmniContact have been accepted to CoRL 2026! Many thanks to all our collaborators!

  • Delighted to represent Noitom Robotics at IEEE RO-MAN 2026 with an invited talk on how human data scales embodied intelligence. See you in Kitakyushu!

  • Joined Noitom Robotics as a full-time Algorithm Researcher.

Selected research

Publications

HiPHI Figure 1, showing diverse whole-body and human-object motions forming the HiPHI wordmark

CoRL 2026

HiPHI: A Large-Scale Benchmark for High-Precision Human Motion and Object-Interaction

Jiahao Ji, Ji Ma, Runhan Zhang, Runyi Yu, Wenjia Wang, Weiheng Chi, Qianqian Peng, Weichao Yan, Yongfei Gu, Ye Tian, Ting Wu, Longwei Li, Chun Yuan, Ruoli Dai, Lei Han

A FrameNet-guided, 617.5-hour optical MoCap benchmark pairing diverse whole-body motion with synchronized object trajectories and meshes for scalable humanoid learning.

Paper Project GitHub Hugging Face
OmniContact Figure 1: humanoid meta-skills, skill chaining, generalization, and VLM integration

CoRL 2026

OmniContact: Chaining Meta-Skills via Contact Flow for Generalizable Humanoid Loco-Manipulation

Runyi Yu, Xiaoyi Lin, Ji Ma, Yinhuai Wang, Koukou Luo, Jiahao Ji, Huayi Wang, Wenjia Wang, Runhan Zhang, Ping Tan, Ting Wu, Ruoli Dai, Qifeng Chen, Lei Han

A contact-flow framework that chains humanoid loco-manipulation skills for long-horizon tasks with closed-loop planning and autonomous failure recovery.

Paper Project GitHub

Background

Experience

Present

Noitom Robotics

Algorithm Researcher

  • Motion Scaling
  • Loco-Manipulation
  • Human–Object Interaction
  • Robot Learning
2025

ByteDance · Seed Robotics

Algorithm Researcher

  • Real2Sim2Real
  • Articulated Asset Reconstruction
  • Dexterous Manipulation
  • Teleoperation

Training

Education

2024 — 2026

National University of Singapore

M.Sc. in Electrical Engineering

2023 — 2024

NUS Suzhou Research Institute

Joint Training Program

2020 — 2024

Beijing Institute of Technology

B.Eng. in Electronic Information Engineering