Hanning Wang

theunknownthing@sjtu.edu.cn acm.sjtu.edu.cn/~theunknownthing/

Profile

Undergraduate in the SJTU ACM Class (2024–Present) at Shanghai Jiao Tong University.
My current research focus is on Large Language Models, especially their pre-training and post-training. I actively keep up with the rapid developments in the field and build side projects to learn new paradigms, protocols, and programming languages.

Education

  1. Shanghai Jiao Tong University, B.S. Computer Science (ACM Class) 2024 - Present

    GPA: 3.9 / 4.3

Research Experience

  1. GAIR Lab (plms.ai), Research Intern (Advisor: Dr. Pengfei Liu) Summer 2025

    Researching Large Language Models with interests in mid-training and post-training stages. Working on providing efficient training data which incentivizes model's agentic capabilities.

Teaching Experience

  1. Teaching Assistant, Programming (C++) CS1953 Fall 2025

    • Gave lectures on shell usage and Git workflows, and supported students in hands-on sessions.
    • Provided an interactive learning platform (adapted from pwn.college) with challenge-based exercises to reinforce shell and Git concepts. Open-sourced our platform on: acmdojo and shell-dojo-core.

Selected Projects

  1. Networking Systems Summer 2025

    • Transparent QUIC Proxy: Implemented a proxy layer to handle QUIC session forwarding and address translation.
    • NeoFRP: Built a lightweight reverse proxy (Fast Reverse Proxy style) for tunneling internal services. 70% faster than original FRP in throughput under same setting.
    • SOCKS5 Server with FullCone UDP: Added UDP FullCone behavior for broader NAT traversal and improved compatibility.

  2. RISC-V Simulator Summer 2025

    A RISC-V simulator (RV32-I) with Tomasulo algorithm for out-of-order execution.

  3. vscode-acmoj Spring 2025

    A simple integration of ACMOJ into VSCode, which allows you to browse problemsets (contests/homework), view problems, submit your code, and check submission results without leaving your editor.


Contributed

  1. volcengine/verl

    verl: Volcano Engine Reinforcement Learning for LLMs (contributed).

Skills

Selected Coursework