arxiv:2605.29801
Junxiao Yang
yangjunxiao2021
AI & ML interests
Alignment/AI safety
Recent Activity
authored a paper 2 days ago
AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security submitted a paper 3 days ago
SynCred-Bench: Benchmarking Synthetic Credibility in AI-Generated Visual Misinformation