Junxiao Yang's picture

Junxiao Yang

yangjunxiao2021

·

https://yangjunx21.github.io/

yangjunx21

AI & ML interests

Alignment/AI safety

Recent Activity

authored a paper about 23 hours ago

LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety

upvoted a paper 1 day ago

LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety

submitted a paper 1 day ago

LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety

View all activity

Organizations

Papers 10

arxiv:2604.12710

arxiv:2509.03059

arxiv:2505.15656

arxiv:2505.15404

models 2

yangjunxiao2021/safe_unlearning

yangjunxiao2021/LASA_Models

datasets 1

yangjunxiao2021/CTF_Crypto_demo

Viewer • Updated Mar 25, 2025 • 2 • 10