Junxiao Yang's picture

Junxiao Yang

yangjunxiao2021

·

https://yangjunx21.github.io/

yangjunx21

AI & ML interests

Alignment/AI safety

Recent Activity

new activity about 4 hours ago

thu-coai/Syncred-Bench:Add task categories, paper and code links

authored a paper 3 days ago

AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security

upvoted a paper 4 days ago

SynCred-Bench: Benchmarking Synthetic Credibility in AI-Generated Visual Misinformation

View all activity

Organizations

yangjunxiao2021 's papers 11

arxiv:2605.29801

arxiv:2604.12710

arxiv:2509.03059

arxiv:2505.15656

arxiv:2505.15404

arxiv:2505.13529

arxiv:2503.01865

arxiv:2502.16776

arxiv:2412.14470

arxiv:2407.02855

arxiv:2311.09096