Skip to content
View he-yufeng's full-sized avatar

Block or report he-yufeng

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.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. 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
he-yufeng/README.md

Hey, I'm Yufeng 👋

Agent AI engineer at Moonshot AI (Kimi), CS Master's student at HKU. I build things with LLMs and occasionally break compilers.

Previously competed in ACM-ICPC (silver medals, BUPT). These days I mostly think about how to make AI agents actually work in production.

Projects

Project Stars What it does
MTSIR3-GAN 135+ Adapting R3GAN (NeurIPS 2024) to multivariate time series imputation + adversarial refinement study
FindJobs-Agent 73+ LLM-powered job toolkit — skill gap analysis, mock interviews, resume optimization
DRL-MultiFactorTrading 52+ Deep RL trading strategies with Double DQN and multi-factor alpha signals
Arxiv Paper Coding Agent 31+ Multi-LLM crew that reads a paper and produces a working implementation
ContractGuard new AI agent that reviews contracts for red flags before you sign
TokenTracker new Drop-in LLM cost tracker — change one import line, see where your money goes
AgentProbe new Pytest plugin for regression-testing AI agents — snapshot baselines, semantic comparison, mock LLMs
GitSense new AI-powered open source contribution finder — tell it your skills, it finds issues

Tech

Python, C++, Go. Comfortable with CUDA kernels, MLIR, reinforcement learning, and the OpenAI/Anthropic API stack. I enjoy working at the intersection of systems and ML.

Elsewhere

  • LinkedIn: yufenghe
  • Location: Hong Kong

嘿,我是宇峰 👋

Moonshot AI(Kimi)Agent AI 工程师,香港大学计算机硕士在读。

之前在北邮打 ACM-ICPC(银牌)。现在主要琢磨怎么让 AI Agent 在生产环境里真正跑起来。

项目

项目 Stars 简介
MTSIR3-GAN 135+ 将 R3GAN (NeurIPS 2024) 适配到多变量时序插补 + 对抗精炼实证研究
FindJobs-Agent 73+ LLM 求职工具箱 — 技能差距分析、模拟面试、简历优化
DRL-MultiFactorTrading 52+ 深度强化学习量化交易,Double DQN + 多因子 Alpha
Arxiv Paper Coding Agent 31+ 多 LLM 协作 Agent,读论文自动生成可运行代码
ContractGuard new AI 合同审查 Agent,签字前帮你找出霸王条款
TokenTracker new LLM 开销追踪,改一行 import 就能用
AgentProbe new AI Agent 回归测试 pytest 插件 — 快照基线、语义比较、Mock LLM
GitSense new AI 驱动的开源贡献发现器,输入技能自动找 issue

技术栈

Python, C++, Go。搞过 CUDA kernel、MLIR、强化学习、OpenAI/Anthropic API。喜欢在系统和 ML 的交叉地带干活。

联系

Pinned Loading

  1. MTSIR3-GAN MTSIR3-GAN Public

    The code and resources for the thesis project "Exploring Generative Adversarial Networks for Multivariate Time Series Data Imputation"

    Python 135 16

  2. FindJobs-Agent FindJobs-Agent Public

    LLM-powered toolkit for skill analysis, AI interviews, resume scoring, and job structuring. Automates professional skill taxonomy and interview processes with adaptive difficulty.

    Python 76 7