Skip to content
View yanfeid's full-sized avatar
🏠
Working from home
🏠
Working from home
0 followers · 1 following

Achievements

Achievement: Pull Sharkx2Achievement: YOLO

Achievements

Achievement: Pull Sharkx2Achievement: YOLO

Block or report yanfeid

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 is supported. This note will only be visible to you.
Report abuse

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

Report abuse
yanfeid/README.md

header

typing

🧭 What I work on

Agentic AI   →  multi-agent systems on MCP that investigate, reason, and act
LLM          →  RLHF / alignment, RAG, tool-use, agent orchestration
Fraud & Risk →  anomaly detection, feature attribution, human-in-the-loop review
RecSys       →  deep CTR ranking, multi-objective, two-tower retrieval

I’m currently researching in-context learning with Claude Fable, building multi-agent fraud investigation systems, and chasing a few other ambitious ideas at the edge of agents and large-scale ML — self-improving pipelines, LLM-as-investigator workflows, and autonomous research agents. Lately I’ve also been vibe-coding 3D games for fun.

⚙️ Stack

📊 GitHub

stats streak

🐍 Watch the snake eat my contributions

snake eating my github contributions

🎓 Affiliations

Cornell University — Computing & Information Science · @CornellCIS
Nanjing University — LAMDA Lab · @LAMDA-NJU

From large-scale RecSys & risk systems to LLM agents that reason and act.

Pinned Loading

  1. claude-amber claude-amber Public

    🟠 Amber — zero-dependency context survival kit for Claude Code. Survive compaction. Stay focused. Three Markdown files, two hooks, four skills.

    JavaScript 2

  2. agentic-fraud-analysis agentic-fraud-analysis Public

    An intelligent, multi-agent fraud management system using MCP

    Python 7 1

  3. rlhf-alignment-template rlhf-alignment-template Public

    A comprehensive template for LLM alignment using RLHF

    Python 1

  4. MultiObjective-Recommendation MultiObjective-Recommendation Public

    AMORe - an agnostic multi-objective framework for recommendation (paper code and datasets)

    Python 1

  5. DarkGameHub/BlackCommission DarkGameHub/BlackCommission Public

    1-4 player co-op outsourcing agency survival-horror game

    C# 4 1

  6. yanfeid yanfeid Public

    GitHub profile

    1