Výsledky vyhledávání

Report

Sifting through the Chaff: On Utilizing Execution Feedback for Ranking the Generated Code Candidates

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

Large Language Models (LLMs), such as GPT-4, StarCoder, and CodeLlama, are transforming the way developers approach programming by automatically generating code based on given natural language descriptions. Despite advancements, generating syntactica

Externí odkaz: http://arxiv.org/abs/2408.13976

Zobrazit plný text záznamu

Akademický článek

The complete mitogenome sequence of the coral lily (Lilium pumilum) and the Lanzhou lily (Lilium davidii) in China

Autor: Qi Xiangying, Wang Kaiqi, Yang Liping, Deng Zhenshan, Sun Zhihong

Publikováno v: Open Life Sciences, Vol 15, Iss 1, Pp 1060-1067 (2020)

The mitogenomes of higher plants are conserved. This study was performed to complete the mitogenome of two China Lilium species (Lilium pumilum Redouté and Lilium davidii var. unicolor (Hoog) cotton).

Externí odkaz: https://doaj.org/article/28f634ca022746128709ff9d854447c1

Zobrazit plný text záznamu

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

Knowledge-Aware Code Generation with Large Language Models

Autor: Huang, Tao, Sun, Zhihong, Jin, Zhi, Li, Ge, Lyu, Chen

Large Language Models (LLMs) perform well on basic programming problems. However, they encounter challenges when dealing with complex tasks involving the use of diverse algorithmic and data structure skills, particularly programming competition-level

Externí odkaz: http://arxiv.org/abs/2401.15940

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

Report

TACO: Topics in Algorithmic COde generation dataset

Autor: Li, Rongao, Fu, Jie, Zhang, Bo-Wen, Huang, Tao, Sun, Zhihong, Lyu, Chen, Liu, Guang, Jin, Zhi, Li, Ge

We introduce TACO, an open-source, large-scale code generation dataset, with a focus on the optics of algorithms, designed to provide a more challenging training dataset and evaluation benchmark in the field of code generation models. TACO includes c

Externí odkaz: http://arxiv.org/abs/2312.14852

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání