Fanjiang Ye|叶繁江

Ph.D. Student · Computer Science · Rice University

Portrait of Fanjiang Ye

I am a Ph.D. student in Computer Science at Rice University, advised by Dr. Yuke Wang. Before that, I got my M.S. degree in Computer Science at Indiana University Bloomington, advised by Dr. Dingwen Tao. I obtained my B.S. degree from the Department of Physics at University of Science and Technology of China (USTC).


Research Interests

Fanjiang's research interests lie in system-level optimization of ML and GPU-based distributed computing, with a focus on Generative AI, LLM/Diffusion Model serving, efficient LLM inference, and communication compression and overlapping. His long-term goal is to enable fast, scalable, and resource-aware AI systems.


Publications

  1. DUO: No Compromise to Accuracy Degradation

    [Paper]

  2. Model Steering: Learning with a Reference Model Improves Generalization Bounds and Scaling Laws

    [Paper]

  3. BMQSim: Overcoming Memory Constraints in Quantum Circuit Simulation with a High-Fidelity Compression Framework

    [Paper]

  4. High-performance Visual Semantics Compression for AI-Driven Science

    [Paper]

  5. Accelerating Communication in Deep Learning Recommendation Model Training with Dual-Level Adaptive Lossy Compression

    [Paper]

Show 6 more preprints Show less
  1. SUPERGEN: An Efficient Ultra-high-resolution Video Generation System with Sketching and Tiling

    [Preprint]

  2. TIDE: Text-Informed Dynamic Extrapolation with Step-Aware Temperature Control for Diffusion Transformers

    [Preprint]

  3. Teach to Fish, Not to Feed: Internalizing Retrieval for External Memory in Large Language Models

  4. SDiT: Semantic Region-Adaptive for Diffusion Transformers

    [Preprint]

  5. An Efficient and Adaptive Watermark Detection System with Tile-based Error Correction

    [Preprint]

  6. FastCLIP: A Suite of Optimization Techniques to Accelerate CLIP Training with Limited Resources

    [Preprint]


Education

  1. Rice University

    Ph.D. in Computer Science

    Advisor: Dr. Yuke Wang

  2. Indiana University Bloomington

    M.S. in Computer Science

    Advisor: Dr. Dingwen Tao

  3. University of Science and Technology of China

    B.S. in Physics

    Advisor: Dr. Changling Zou


Experience

  1. Amazon Web Services

    Applied Scientist Intern, Annapurna Lab

    Advisor: Dr. Zhuang Wang


Professional Services

Artifact Evaluation Committee

Reviewer


Teaching


Miscellaneous

Designed © 2026 Fanjiang Ye. All rights reserved.
Last updated 2026-04-05 · Feel free to steal this website's source code