Zobrazeno 1 - 10
of 20
pro vyhledávání: '"Hai-Nam Le"'
Autor:
Manh, Dung Nguyen, Chau, Thang Phan, Hai, Nam Le, Doan, Thong T., Nguyen, Nam V., Pham, Quang, Bui, Nghi D. Q.
Recent advancements in Code Large Language Models (CodeLLMs) have predominantly focused on open-ended code generation tasks, often neglecting the critical aspect of code understanding and comprehension. To bridge this gap, we present CodeMMLU, a comp
Externí odkaz:
http://arxiv.org/abs/2410.01999
Autor:
Tran, Quyen, Thanh, Nguyen Xuan, Anh, Nguyen Hoang, Hai, Nam Le, Le, Trung, Van Ngo, Linh, Nguyen, Thien Huu
Few-shot Continual Relations Extraction (FCRE) is an emerging and dynamic area of study where models can sequentially integrate knowledge from new relations with limited labeled data while circumventing catastrophic forgetting and preserving prior kn
Externí odkaz:
http://arxiv.org/abs/2410.00334
Autor:
Hai, Nam Le, Bui, Nghi D. Q.
Code comments provide important information for understanding the source code. They can help developers understand the overall purpose of a function or class, as well as identify bugs and technical debt. However, an overabundance of comments is meani
Externí odkaz:
http://arxiv.org/abs/2408.04663
CodeLLMs have gained widespread adoption for code generation tasks, yet their capacity to handle repository-level code generation with complex contextual dependencies remains underexplored. Our work underscores the critical importance of leveraging r
Externí odkaz:
http://arxiv.org/abs/2406.11927
Autor:
Manh, Dung Nguyen, Hai, Nam Le, Dau, Anh T. V., Nguyen, Anh Minh, Nghiem, Khanh, Guo, Jin, Bui, Nghi D. Q.
We present The Vault, a dataset of high-quality code-text pairs in multiple programming languages for training large language models to understand and generate code. We present methods for thoroughly extracting samples that use both rule-based and de
Externí odkaz:
http://arxiv.org/abs/2305.06156
Autor:
Hai, Nam Le, Gerald, Thomas, Formal, Thibault, Nie, Jian-Yun, Piwowarski, Benjamin, Soulier, Laure
Conversational search is a difficult task as it aims at retrieving documents based not only on the current user query but also on the full conversation history. Most of the previous methods have focused on a multi-stage ranking approach relying on qu
Externí odkaz:
http://arxiv.org/abs/2301.04413
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
Machine Learning; Jan2024, Vol. 113 Issue 1, p281-323, 43p
Autor:
Thi-Hong-Tham Tran, Hai-Nam Le, Ngoc-Anh Vu, Nghia Pham Minh, Tien-Hoa Nguyen, Quang-Kien Trinh
Publikováno v:
Physical Communication. 59:102059
Autor:
Quang-Kien Trinh, Ngoc-Anh Vu, Hai-Nam Le, Thi-Hong-Tham Tran, Trung-Kien Hoang, Dinh-Chi Tran, Xuan-Nghia Pham
Publikováno v:
2022 International Conference on Advanced Technologies for Communications (ATC).