1 code implementation • 23 Apr 2024 • Zhen Yang, Fang Liu, Zhongxing Yu, Jacky Wai Keung, Jia Li, Shuo Liu, Yifan Hong, Xiaoxue Ma, Zhi Jin, Ge Li
This paper investigates diverse LLMs and learning-based transpilers for automated code translation tasks, finding that: although certain LLMs have outperformed current transpilers, they still have some accuracy issues, where most of the failures are induced by a lack of comprehension of source programs, missing clear instructions on I/O types in translation, and ignoring discrepancies between source and target programs.
no code implementations • 22 May 2023 • Yifan Hong, Chen Wang
Tests on the ${\tt CIFAR-10H}$ dataset demonstrate that mPPCA with only a single principal component for each category effectively predicts human categorization of natural images.