cv

Curriculum vitae.

General Information

Full Name Jiamu (Morris) Zhang
Email mz81@rice.edu
Languages English, Mandarin Chinese

Research

  • Efficient and scalable LLM and agentic systems — system–method co-design — and rigorous ways to measure whether the efficiency is real.

Education

  • 08/2024 - Present
    Ph.D. in Computer Science
    Rice University, Houston, TX
    • Advisor: Prof. Hanjie Chen, Chili Lab (08/2025 - Present)
    • Advisor: Prof. Xia "Ben" Hu, Data Lab (08/2024 - 08/2025)
  • 05/2024
    B.S. in Computer Science
    Case Western Reserve University, Cleveland, OH
    • Department of Computer and Data Science.
    • Advisors: Prof. Shuai Xu and Prof. Vipin Chaudhary.

Research Interests

  • Memory-bound LLM inference. KV cache compression, quantization and transform coding for long-context and agentic workloads.
  • Conditional computation. Mixture-of-Experts and training-free routing that turn static redundancy in pretrained models into input-dependent sparsity — and the serving systems that realize it under real memory budgets.
  • Efficient and verifiable agentic systems. Cutting redundant computation and communication in LLM agents and multi-agent systems — and rigorously evaluating whether reported efficiency gains are real.

Experience

  • 05/2026 - Present
    Research Intern, AI Research & Development
    Nokia, Sunnyvale, CA
    • Efficiency and system–method co-design for large-model inference.
    • Led the design and open-source release of AnyJev.

Open Source

  • 2026
    AnyJev — lead author and principal maintainer
    Nokia Applied Research
    • Turns any LLM into a typed decision model with calibrated probabilities, training-free by default — served through vLLM as a pooling endpoint plus a few kilobytes of closed-form head.
    • Cuts option-order sensitivity 0.230 to 0.073 and calibration error 0.240 to 0.095 with zero labels; raises the share auto-decidable at 5% risk from 7.7% to 52.0% with 100-500 labels.
    • Passed 1,000 GitHub stars in its first ten days.
    GitHub
    PyPI

Selected Publications

  • See the publications page for a full list with short digests.

Honors and Awards

  • 2026
    EMNLP 2026 Outstanding Paper Award
    EMNLP 2026, Main Conference
    • For "Rethinking the Evaluation of Efficiency Methods for Multi-Agent Systems".
  • 2024
    Swanger Graduate Fellowship
    Case Western Reserve University
  • 2024
    The Computer and Data Science Research Award
    Case Western Reserve University
  • 2024
    Dean's High Honor List & Latin Honors
    Case Western Reserve University

Professional Service

  • Conference Reviewer
    • NeurIPS, ICML, ACL
  • Journal Reviewer
    • IEEE TPAMI, IEEE TCDS, ACM TIST, ACM TCH, and Neurocomputing.

Teaching

  • 2026 Fall
    Guest Lecture, COMP 640 - Graduate Seminar in Machine Learning: Large Language Models
    Rice University
    • "A Simple Intro to Test-Time Scaling & Reasoning: Thinking longer, thinking better"
    Course page
  • 2026 Spring
    TA, COMP 584 - Natural Language Processing
    Rice University
  • 2025 Spring
    TA, COMP 631 - Introduction to Information Retrieval
    Rice University
  • 2022, 2023, 2024
    TA, CSDS 302 - Discrete Mathematics
    Case Western Reserve University
  • 2023 Spring
    TA, CSDS 386 - Quantum Computing, Information, and Devices
    Case Western Reserve University