resource languages have significantly lower attack success rate, which suggests that the cross-lingual vulnerability mainly applies to low-resource languages. Previously, limited training on low-resource languages primarily affects speakers of those languages, causing technological disparities. However, our ...
《Resource-Aware Collaborative Monte Carlo Localization with Distribution Compression》(2024) GitHub: github.com/idsia-robotics/Collaborative-Monte-Carlo-Localization [fig4]《Jailbreaking as a Reward Misspecification Problem》(2024) GitHub: github.com/zhxieml/remiss-jailbreak [fig5]...