Skip to content
View zhangchen-xu's full-sized avatar
🎯
Focusing
🎯
Focusing
61 followers · 12 following

Achievements

Achievement: Starstruckx3Achievement: Pull SharkAchievement: Arctic Code Vault Contributor

Achievements

Achievement: Starstruckx3Achievement: Pull SharkAchievement: Arctic Code Vault Contributor

Highlights

  • Pro

Organizations

@microsoft @uw-nsl @magpie-align

Block or report zhangchen-xu

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
zhangchen-xu/README.md

Hi there 👋. It's Zhangchen Xu here.

I am a third-year PhD student at the University of Washington, advised by Prof. Radha Poovendran. I work on LLM related topics (e.g., safety, alignment, reasoning, post-training, synthetic data).

🕸️ Website | 🤗 HuggingFace | 🐦 X

github contribution grid snake animation

Pinned Loading

  1. uw-nsl/SafeDecoding uw-nsl/SafeDecoding Public

    Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding

    Jupyter Notebook 129 11

  2. magpie-align/magpie magpie-align/magpie Public

    [ICLR 2025] Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing. Your efficient and high-quality synthetic data generation pipeline!

    Python 675 60

  3. KodCode-AI/kodcode KodCode-AI/kodcode Public

    ✨ A synthetic dataset generation framework that produces diverse coding questions and verifiable solutions - all in one framwork

    Python 197 10

  4. WildEval/ZeroEval WildEval/ZeroEval Public

    Forked from allenai/WildBench

    A simple unified framework for evaluating LLMs

    HTML 210 23