👋 Open to Work

Junxiao Yang

yangjunxiao2021

·

https://yangjunx21.github.io/

yangjunx21

AI & ML interests

Alignment/AI safety

Recent Activity

liked a Space 2 days ago

huggingface/moe-blogpost

upvoted a paper 11 days ago

RSI Arena: Towards Recursive Self-Improvement with Human Feedback

published a dataset 21 days ago

yangjunxiao2021/terminal-bench-science-trajectories

View all activity

Organizations

Papers 11

arxiv:2605.29801

arxiv:2604.12710

arxiv:2509.03059

arxiv:2505.15656

models 2

yangjunxiao2021/safe_unlearning

yangjunxiao2021/LASA_Models

datasets 4

yangjunxiao2021/terminal-bench-science-trajectories

Viewer • Updated 21 days ago • 2.61k • 2.04k

yangjunxiao2021/mle-trajectories

Viewer • Updated Sep 20 • 42 • 205

yangjunxiao2021/Syncred-Bench

Updated Jun 3 • 4 • 2

yangjunxiao2021/CTF_Crypto_demo

Viewer • Updated Mar 25, 2025 • 2 • 21