arxiv:2510.21285
Yingz
KigYzi
AI & ML interests
None yet
Recent Activity
liked
a dataset
3 days ago
Forceless/UltraPresent
authored
a paper
3 months ago
When Models Outthink Their Safety: Mitigating Self-Jailbreak in Large
Reasoning Models with Chain-of-Guardrails
Organizations
None yet