Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Tang, Ningzhi"'
Autor:
Bansal, Aakash, Wallace, Robert, Karas, Zachary, Tang, Ningzhi, Huang, Yu, Li, Toby Jia-Jun, McMillan, Collin
Abridged: Programmer attention represents the visual focus of programmers on parts of the source code in pursuit of programming tasks. We conducted an in-depth human study with XY Java programmers, where each programmer generated summaries for 40 met
Externí odkaz:
http://arxiv.org/abs/2405.18573
Upon deployment to edge devices, it is often desirable for a model to further learn from streaming data to improve accuracy. However, extracting representative features from such data is challenging because it is typically unlabeled, non-independent
Externí odkaz:
http://arxiv.org/abs/2405.16113
Autor:
Tang, Ningzhi, Chen, Meng, Ning, Zheng, Bansal, Aakash, Huang, Yu, McMillan, Collin, Li, Toby Jia-Jun
The increasing use of large language model (LLM)-powered code generation tools, such as GitHub Copilot, is transforming software engineering practices. This paper investigates how developers validate and repair code generated by Copilot and examines
Externí odkaz:
http://arxiv.org/abs/2405.16081
Autor:
Qu, Liang, Tang, Ningzhi, Zheng, Ruiqi, Nguyen, Quoc Viet Hung, Huang, Zi, Shi, Yuhui, Yin, Hongzhi
Collaborative filtering (CF) based recommender systems are typically trained based on personal interaction data (e.g., clicks and purchases) that could be naturally represented as ego graphs. However, most existing recommendation methods collect thes
Externí odkaz:
http://arxiv.org/abs/2302.10900
As a crucial component of most modern deep recommender systems, feature embedding maps high-dimensional sparse user/item features into low-dimensional dense embeddings. However, these embeddings are usually assigned a unified dimension, which suffers
Externí odkaz:
http://arxiv.org/abs/2204.03281
Autor:
Tang, Ningzhi, Chen, Meng, Ning, Zheng, Bansal, Aakash, Huang, Yu, McMillan, Collin, Li, Toby Jia-Jun
Recent advances in AI-based code generation tools such as GitHub Copilot show great promise in assisting developers with programming tasks. However, there are few empirical studies that used objective measures to investigate the behavior of programme
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6cfc325c1e02e12b57d508644bd84fa4