Technology
Leveraging Catastrophic Forgetting to Develop Safe Diffusion Models against Malicious Finetuning Jiadong Pan
WARNING: This paper contains offensive images generated by models.
Mixture of Adversarial LoRAs: Boosting Robust Generalization in Meta-Tuning Xu Y ang 1 Chen Liu 1 Ying Wei 2 1 City University of Hong Kong
Extensive evaluations demonstrate that AMT yields significant improvements, up to 12.92% in
AutoSurvey: Large Language Models Can Automatically Write Surveys
"Large Language Model" in their titles or abstracts were submitted to arXiv.
Offline Behavior Distillation
Inspired by dataset distillation (DD) [Wang et al., 2018, Zhao et al., (Corollary 1). Extensive experiments on nine datasets of D4RL benchmark [Fu et al., 2020] with multiple environments and data qualities illustrate that our Av-PBC remarkably promotes the OBD performance, Moreover, Av-PBC has a significant convergence speed and requires only a quarter of distillation steps compared to DBC and PBC.
Amortized Fourier Neural Operators
Fourier Neural Operators (FNOs) have shown promise for solving partial differential equations (PDEs).
Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack
To further verify this finding, we empirically show that these dormant backdoors can be easily re-activated during inference stage, by manipulating the original trigger with well-designed tiny perturbation using universal adversarial attack.
Graph Coarsening with Message-Passing Guarantees
Interestingly, and in a sharp departure from previous proposals, this operation on coarsened graphs is often oriented, even when the original graph is undirected.