-
🎓 From September 2022, Haiyang started his Ph.D. degree in computer software and theory in School of Computer Science of Peking University.
-
🏅 Haiyang received his B.E degree from School of Computer Science in Northwestern Polytechnical University in June 2022.
-
🌱 My research interests lie in agents based on large models (LLMs/MLMs). Specifically, I am interested in:
- 🔗 The integration of LMs with APIs (tools).
- 🛠 The software engineering challenges associated with the integration.
- 📱 The applications of LMs on edge devices.
-
📚 My research group primarily focuses on system software, including machine learning systems, serverless computing, web systems, software engineering, and etc. In my first year of Ph.D., I studied anomaly detection, federated learning, inference optimization for LLMs in the cloud, etc.
-
🔍 Throughout my studies from system software to deep learning, I have gained knowledge in various areas including methods and applications of natural language processing, retrieval systems, data analysis and mining, acceleration, and application of machine learning systems.
- 🖋 My introduction at here.
- fifty-six/Scarab - An installer for Hollow Knight mods written in Avalonia. (1 week ago)
- Hongcheng-Gao/Awesome-Long2short-on-LRMs - Awesome-Long2short-on-LRMs is a collection of state-of-the-art, novel, exciting long2short methods on large reasoning models. It contains papers, codes, datasets, evaluations, and analyses. (1 month ago)
- aqpower/obsidian-Latex2MathJax - Convert LaTeX math formulas generated by large models (e.g., ChatGPT) into MathJax format supported by Markdown. (1 month ago)
- MIT-MI/MEM1 - (1 month ago)
- StigLidu/DualDistill - [EMNLP 2025] The official implementation for paper "Agentic-R1: Distilled Dual-Strategy Reasoning" (1 month ago)