A Contrastive Safety Loss is derived with a suppression weight that controls the tradeoff between emphasizing the safety instruction on harmful queries while suppressing it on harmless queries, supporting the hypothesis that the operator's eigenvalue acts as a continuous dial for the instruction's influence.
Benoit Dherin, Michael Munn, X. Gonzalvo et al.· 0 citations
Findings show that task utility does not imply privacy or authorization compliance and that authorization in community settings remains an unresolved security challenge for persistent LLM agents.
Hao Chen, Wen-Hui Dong, Ye Chen et al.· arXiv.org· 1 citation
Experiments on locomotion, navigation and manipulation show consistent gains in interaction efficiency, imitation performance, and robustness, indicating that RECON directs real-environment interaction toward recovery regions around the expert distribution that are underexplored by prior methods, and thereby learns a w...
Xuan-Lin Chen, Zi-Yue Wang, Xunlan Zhou et al.· 0 citations
DashAct is introduced, to the authors' knowledge the first benchmark to diagnose failures at a fine-grained level within the same dashboard task, and measures the minimum support an agent needs to recover rather than scoring isolated skills.
Chu-Han Zhang, Qinghongbing Xie, Zi-Yue Wang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.