Výsledky vyhledávání

Report

Enhancing Code Generation Performance of Smaller Models by Distilling the Reasoning Ability of LLMs

Autor: Sun, Zhihong, Lyu, Chen, Li, Bolun, Wan, Yao, Zhang, Hongyu, Li, Ge, Jin, Zhi

Large Language Models (LLMs) have recently made significant advances in code generation through the 'Chain-of-Thought' prompting technique. This technique empowers the model to autonomously devise "solution plans" to tackle intricate programming chal

Externí odkaz: http://arxiv.org/abs/2403.13271

Zobrazit plný text záznamu

Report

IRCoCo: Immediate Rewards-Guided Deep Reinforcement Learning for Code Completion

Autor: Li, Bolun, Sun, Zhihong, Huang, Tao, Zhang, Hongyu, Wan, Yao, Li, Ge, Jin, Zhi, Lyu, Chen

Code completion aims to enhance programming productivity by predicting potential code based on the current programming context. Recently, pretrained language models (LMs) have become prominent in this field. Various approaches have been proposed to f

Externí odkaz: http://arxiv.org/abs/2401.16637

Zobrazit plný text záznamu

Akademický článek

Echocardiographic mitral valve segmentation model

Autor: Liu, Chunxia, Dong, Shanshan, Xiong, Feng, Wang, Luqing, Li, Bolun, Wang, Hongjun

Publikováno v: In Journal of King Saud University - Computer and Information Sciences November 2024 36(9)

Zobrazit plný text záznamu

Report

OJXPerf: Featherlight Object Replica Detection for Java Programs

Autor: Li, Bolun, Xu, Hao, Zhao, Qidong, Su, Pengfei, Chabbi, Milind, Jiao, Shuyin, Liu, Xu

Publikováno v: 44th International Conference on Software Engineering (ICSE 2022)

Memory bloat is an important source of inefficiency in complex production software, especially in software written in managed languages such as Java. Prior approaches to this problem have focused on identifying objects that outlive their life span. F

Externí odkaz: http://arxiv.org/abs/2203.12712

Zobrazit plný text záznamu