Portrait of Yijiahao (Friedrich) Qi

Yijiahao (Friedrich) Qi

Ithaca, NY

I work on optimizing large-scale GPU systems for more efficient machine learning systems.

I am a 1st-year PhD student in the Computer System Lab of ECE Department at Cornell University. Before joining Cornell, I received my B.S. in Applied Physics from Peking University (EECS Department) in 2026, advised by Prof. Meng Li. During my undergraduate studies, I spent a year as a research intern in the SHARC Lab at Georgia Tech, working with Prof. Cong (Callie) Hao on efficient Mixture-of-Agents (MoA) serving systems.

Recent papers

  1. 2022 Peking University B.S. in Applied Physics
  2. 2025 Georgia Tech Undergraduate Research Intern, SHARC Lab
  3. 2026 Now Cornell University Ph.D. in Electrical and Computer Engineering

Experience

  1. Undergraduate Research Intern, SHARC Lab

    Georgia Institute of Technology

    Mar 2025 – Feb 2026, Atlanta, GA

    With Prof. Cong (Callie) Hao on efficient Mixture-of-Agents serving (Faster-MoA).

  2. Undergraduate Researcher, SEC Lab

    Peking University

    Jul 2024 – May 2025, Beijing, China

    With Prof. Meng Li on reliable embodied AI (CREATE) and efficient VLA inference (DySL-VLA).

Education

  1. Ph.D. in Electrical and Computer Engineering

    Cornell University

    2026 – Present, Ithaca, NY

    Computer Systems Lab

  2. B.S. in Applied Physics

    Peking University

    Sep 2022 – Jul 2026, Beijing, China

    EECS Department · Advisor: Prof. Meng Li

News

  • Fall 2026

    Started my Ph.D. in Electrical and Computer Engineering at Cornell University, in the Computer Systems Lab.

  • Jul 2026

    Received my B.S. in Applied Physics from Peking University (EECS Department).

  • 2026

    Faster-MoA (co-first author) and DySL-VLA were published at DAC 2026.

  • 2026

    CREATE (co-first author) was published at ASPLOS 2026.

Earlier updatesShow fewer
  • Mar 2025

    Joined the SHARC Lab at Georgia Tech as an undergraduate research intern with Prof. Cong (Callie) Hao.

Skills

Languages & frameworks
  • C++
  • Python
  • PyTorch
  • Verilog
Tools
  • Vivado
  • Vitis
  • Linux
  • Git
  • Docker

Research Interests

Optimizing large-scale GPU systems for more efficient machine learning systems.

  1. Efficient agentic systems

    Agentic systems

    Achieving lower serving latency via co-designing scheduling policy and universal memory management.

    • Scheduling
    • Memory management
    • Multi-agent serving

  2. Hardware-aware system/algorithms design

    Hardware-aware design

    Designing tailored system/algorithms on resource-constrained platforms to enable higher performance.

    • Embodied AI
    • VLA inference
    • Reliability

Hands-on experience

  • Efficient embodied agents

    Fault-tolerant embodied AI (CREATE) and robotic-manipulation acceleration (DySL-VLA).

  • Algorithms

    PEFT fine-tuning of small models with LLaMA-Factory; customized metrics for dynamic early exit.

  • Systems

    KV-cache management and transmission; prefill–decode scheduling and partitioning in multi-agent serving.

  • Hardware

    Sparse matrix-matrix multiplication (SpMM) accelerator and systolic-array design in Verilog.

Selected Publications

Papers from my undergraduate research at Peking University and Georgia Tech. * Equal contribution.

2026

CREATE: Cross-Layer Resilience Characterization and Optimization for Efficient yet Reliable Embodied AI Systems

T. Xie*, Y. Qi*, J. Wen, Z. Wan, Y. Dong, Z. Wang, S. Cai, Y. Liang, T. Jia, Y. Wang, R. Wang, M. Li

In ASPLOS 2026 [PDF] [Details]
[Cite]

T. Xie*, Y. Qi*, J. Wen, Z. Wan, Y. Dong, Z. Wang, S. Cai, Y. Liang, T. Jia, Y. Wang, R. Wang, and M. Li. "CREATE: Cross-Layer Resilience Characterization and Optimization for Efficient yet Reliable Embodied AI Systems." International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS), 2026. (*Equal contribution)

All publications Google Scholar