no code implementations • 6 May 2024 • Hang Yuan, Zhongyue Che, Shao Li, Yue Zhang, Xiaomeng Hu, Siyang Luo
However, to ensure that artificial intelligence models benefit human society, we must first fully understand the similarities and differences between the human-like characteristics exhibited by artificial intelligence models and real humans, as well as the cultural stereotypes and biases that artificial intelligence models may exhibit in the process of interacting with humans.
no code implementations • 21 Dec 2023 • Siyang Luo, Ziyi Jiang, Zhenghan Chen, Xiaoxuan Liang
Moreover, our approach incorporates adaptive perturbations into the dual branches, which align the source and target distribution to address domain discrepancies.