Skip to content
View SunnyHaze's full-sized avatar

Highlights

  • Pro

Block or report SunnyHaze

Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Sunnyhaze/README.md

Welcome to my Profile 👋

Github Overview 😄


Self-introduction

  • 🎓 I am currently a Ph.D. student in Computer Science and Engineering (CSE) at HKUST (since Jan. 2026), advised by
    Prof. Binhang Yuan and Prof. Wentao Zhang.
  • 🧠 My research mainly focuses on LLM Systems and Deep Learning Systems, including system design and optimization for large-scale models.
  • 🏖️ Previously, I worked as a Research Assistant at Peking University, conducting research on LLMs and Multimodal LLMs (MLLMs), advised by Prof. Wentao Zhang.
  • 📫 Before that, I was a Research Assistant at Sichuan University, focusing on Image Manipulation Detection and Localization, advised by Prof. Jizhe Zhou.
  • 🎓 I hold a B.Eng. in Computer Science from Sichuan University, China.

Research Interests

  • 🔧 LLM Systems & Deep Learning Systems
  • ⚙️ System design and optimization for large-scale deep learning
  • 🖼️ Image Forensics & Image Manipulation Detection
  • 🤖 Multimodal Large Models (MLLMs)

Representative Works

My repositories have accumulated 3000+ GitHub stars in total.


For More Info

Pinned Loading

  1. OpenDCAI/DataFlow OpenDCAI/DataFlow Public

    [SIGMOD'27] Easy Data Preparation with latest LLMs-based Operators and Pipelines.

    Python 8.2k 1.2k

  2. scu-zjz/IMDLBenCo scu-zjz/IMDLBenCo Public

    [NeurIPS'24 Spotlight] A comprehensive benchmark & codebase for Image manipulation detection/localization.

    Python 319 54

  3. IML-ViT IML-ViT Public

    Official repository of paper “IML-ViT: Benchmarking Image manipulation localization by Vision Transformer”

    Jupyter Notebook 310 38

  4. scu-zjz/ForensicHub scu-zjz/ForensicHub Public

    [NeurlPS 2025] A Unified Benchmark & Codebase for All-Domain Fake Image Detection and Localization

    Python 229 28

  5. scu-zjz/Mesorch scu-zjz/Mesorch Public

    [AAAI 2025] Official repository of paper “Mesoscopic Insights: Orchestrating Multi-scale & Hybrid Architecture for Image Manipulation Localization”

    Python 107 7

  6. OpenDCAI/Flash-MinerU OpenDCAI/Flash-MinerU Public

    Ray-powered accelerator for MinerU, turning PDF → Markdown into a scalable, cluster-ready data infrastructure. 基于 Ray 的 MinerU 加速层,将 PDF → Markdown 构建为可扩展、面向集群的数据基础设施。

    Python 71 6