SCS Students Earn Qualcomm Innovation Fellowships for Pose Estimation, Distributed Deep Learning

SCS Ph.D. students Byungsoo Jeon and Zhengyi Luo have earned 2022 Qualcomm Innovation Fellowships.

Two School of Computer Science students were part of teams awarded 2022 Qualcomm Innovation Fellowships for their work in pose estimation and optimization in distributed deep learning. As part of the program, each team will receive $100,000 in funding and mentoring from Qualcomm engineers.

Zhengyi Luo, a Ph.D. student in the Robotics Institute (RI), and Yu-Jhe Li, a Ph.D. student in the Electrical and Computer Engineering Department, are researching pose estimation, an essential component for human-like 3D avatars in games or sci-fi-like telepresence. They were nominated for their proposal "Near- and Far-Field Sensor Fusion for 3D Body Pose Estimation and Tracking," which merges the two sensing techniques and leverages the advantages of each. By fusing the two data streams, their work could enhance the quality of immersive mixed-reality experiences.

Byungsoo Jeon, a Ph.D. student in the Computer Science Department, and Sunghyun Kim, a Ph.D. student at Massachusetts Institute of Technology, were selected for their proposal, "Holistic Distributed Deep Learning Compilation With Automated Cross-Stack Optimization." Their work aims to integrate and automate parallelization techniques needed for distributed deep learning compilation — crucial for running large AI models — by distributing their computation across multiple machines to speed up the process. The pair also want to explore an automated approach that captures the interaction between hardware-independent and hardware-dependent optimizations and combines them effectively. Their work will improve the way machines run AI models for human use.

A third CMU project out of the College of Engineering was also among this year's awardees.

Learn more about the awards on the Qualcomm Innovation Fellowships website.

For More Information, Contact:

Aaron Aupperlee | 412-268-9068 |