Skip to content
View EachSheep's full-sized avatar
🎯
Focusing
🎯
Focusing

Highlights

  • Pro

Block or report EachSheep

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

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

Report abuse
EachSheep/README.md

Hi there👋

GitHub RSS

Short Bio

  • 🎓 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.

📫 Correspondence

🌟 Others

  • 🖋 My introduction at here.

📓 Gists I wrote

⭐ Recent Stars

  • irlab-sdu/fuzi.mingcha - 夫子•明察司法大模型是由山东大学、浪潮云、中国政法大学联合研发,以 ChatGLM 为大模型底座,基于海量中文无监督司法语料与有监督司法微调数据训练的中文司法大模型。该模型支持法条检索、案例分析、三段论推理判决以及司法对话等功能,旨在为用户提供全方位、高精准的法律咨询与解答服务。 (1 day ago)
  • SkyRiver-2000/RuleArena - Codes and data for our paper - RuleArena: A Benchmark for Rule-Guided Reasoning with LLMs in Real-World Scenarios (6 days ago)
  • idootop/MagicMirror - 🪞 Instant AI Face Swap, Hairstyles & Outfits — One click to a brand new you! 一键 AI 换脸、发型、穿搭,发现更美的你 (1 week ago)
  • R0bk/killedbyllm - (1 week ago)
  • OSU-NLP-Group/HippoRAG - [NeurIPS'24] HippoRAG is a novel RAG framework inspired by human long-term memory that enables LLMs to continuously integrate knowledge across external documents. RAG + Knowledge Graphs + Personalized PageRank. (3 weeks ago)

Pinned Loading

  1. blog blog Public

    My personal introduction

    HTML 1

  2. ShortcutsBench ShortcutsBench Public

    ShortcutsBench: A Large-Scale Real-World Benchmark for API-Based Agents

    Python 78 1