Yao He

I am currently a second-year Master’s student at Stanford, working on computer vision and robotics. I work with Prof. Ehsan Adeli and Prof. Youngjoong Kwon as part of the Stanford Translation AI Lab (STAI) and Stanford Vision and Learning (SVL). I am also a member of the Toddlerbot team, advised by Prof. Shuran Song and Prof. Karen Liu.

Previously, I served as a research associate and one of the main engineers at AirLab, CMU Robotics Institute, advised by Prof. Sebastian Scherer. During my time at CMU, I was focusing on building effecient and versatile mobile robot systems that can robustly perceive and safely navigate in unstructured environments. I was also a 2021 CMU Robotics Institute Summer Scholar.

🎓 I will join Stanford as a PhD student in Computer Science this Fall, stay tuned!

Research

Repurposing 2D Diffusion Models for 3D Shape Completion

Yao He, Youngjoong Kwon, Tiange Xiang, and 2 more authors

In Submission, 2026

Website
Feed-forward Monocular Human Performance Capture

YoungJoong Kwon, Yao He, Hee Jung Choi, and 4 more authors

In The Fourteenth International Conference on Learning Representations (ICLR), 2026

PDF Code Website
Artist-Created Mesh Generation from Raw Observation

Yao He, Youngjoong Kwon, Wenxiao Cai, and 1 more author

In International Conference on Computer Vision (ICCV) End-to-End 3D Learning workshop, 2025

PDF
Robust Visual Odometry using Rigidly-Bundled Arbitrarily-Arranged Multi-Cameras

Huai Yu, Junhao Wang, Yao He, and 2 more authors

In IEEE Robotics and Automation Letters (RA-L), 2025

PDF Code
Robot Trains Robot: Automatic Real-World Policy Adaptation and Learning for Humanoids

Kaizhe Hu^*, Haochen Shi^*, Yao He, and 3 more authors

In Conference on Robot Learning (CoRL), 2025

PDF Code Website
Stem-OB: Generalizable Visual Imitation Learning with Stem-Like Convergent Observation through Diffusion Inversion

Kaizhe Hu^*, Zihang Rui^*, Yao He, and 3 more authors

In The Thirteenth International Conference on Learning Representations (ICLR, Spotlight), 2025

PDF Code Website
Demonstrating ViSafe: Vision-enabled Safety for High-speed Detect and Avoid

Parv Kapoor^*, Ian Higgins^*, Nikhil Keetha^*, and 9 more authors

In Robotics: Science and Systems (RSS), 2025

PDF Website
FIReStereo: Forest InfraRed Stereo Dataset for UAS Depth Perception in Visually Degraded Environments

Devansh Dhrafani^*, Yifei Liu^*, Andrew Jong, and 6 more authors

In IEEE Robotics and Automation Letters (RA-L), 2025

DOI PDF Code Website
FoundLoc: Vision-based Onboard Aerial Localization in the Wild

Yao He^*, Ivan Cisneros^*, Nikhil Keetha, and 6 more authors

In arXiv preprint arXiv:2310.16299 , 2023

DOI PDF Website
Towards Robust Visual-Inertial Odometry with Multiple Non-Overlapping Monocular Cameras

Yao He, Huai Yu, Wen Yang, and 1 more author

In 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022

PDF Video Code
Computational Efficient Simulation of Kelvin Wake for Unmanned Surface Vehicles

Yao He, Qinbo Sun, Weimin Qi, and 2 more authors

In 2021 IEEE International Conference on Real-time Computing and Robotics (RCAR), 2021

DOI PDF Code

Teaching and Professional Service

Teaching Assistant:

EE/CS 227 Robot Perception (Fall 2025) - Stanford
MAT2002 Ordinary Differential Equations (Spring 2022) - CUHK-Shenzhen
CSC3002 Introduction to Computer Science: Programming Paradigms (Spring 2021) - CUHK-Shenzhen
MAT1002 Calculus II (Spring 2020) - CUHK-Shenzhen
PHY1001 Mechanics (Fall 2019) - CUHK-Shenzhen

CMU MRSD Mentor: Resilient Subcanopy UAS Navigation Through Smoke for Wildfire Application (EmberEye)

Co-organized Events:

Tartan Planning Series - Spring 2023 interactive series of talks, tutorials, and learning on Robot Planning
ICCV 2023 SLAM Challenge - Multi-Robot, Multi-Degraded SLAM Challenge with TartanAir and SubT-MRS datasets

Reviewer: IJRR, RA-L, IROS, ICRA, CVPR