Zobrazeno 1 - 10
of 583
pro vyhledávání: '"Tung, Hoang"'
Representation Misdirection for Unlearning (RMU), which steers model representation in the intermediate layer to a target random representation, is an effective method for large language model (LLM) unlearning. Despite its high performance, the under
Externí odkaz:
http://arxiv.org/abs/2408.06223
Autor:
Nguyen, Quang H., Ngoc-Hieu, Nguyen, Ta, The-Anh, Nguyen-Tang, Thanh, Wong, Kok-Seng, Thanh-Tung, Hoang, Doan, Khoa D.
Deep neural networks are vulnerable to backdoor attacks, a type of adversarial attack that poisons the training data to manipulate the behavior of models trained on such data. Clean-label attacks are a more stealthy form of backdoor attacks that can
Externí odkaz:
http://arxiv.org/abs/2407.10825
Background: Software Vulnerability (SV) prediction in emerging languages is increasingly important to ensure software security in modern systems. However, these languages usually have limited SV data for developing high-performing prediction models.
Externí odkaz:
http://arxiv.org/abs/2404.17110
Genetically predicted dietary intake and risks of colorectal cancer: a Mendelian randomisation study
Publikováno v:
BMC Cancer, Vol 24, Iss 1, Pp 1-13 (2024)
Abstract Background Effects of confounders on associations between diet and colorectal cancer (CRC) in observational studies can be minimized in Mendelian randomization (MR) approach. This study aimed to investigate observational and genetically pred
Externí odkaz:
https://doaj.org/article/4eda8a5d0caf4371a6ec40e603456aff
Autor:
Ngoc-Hieu, Nguyen, Hung-Quang, Nguyen, Ta, The-Anh, Nguyen-Tang, Thanh, Doan, Khoa D, Thanh-Tung, Hoang
The ability to detect OOD data is a crucial aspect of practical machine learning applications. In this work, we show that cosine similarity between the test feature and the typical ID feature is a good indicator of OOD data. We propose Class Typical
Externí odkaz:
http://arxiv.org/abs/2306.14920
Autor:
Nguyen-Duc, Thang, Thanh-Tung, Hoang, Tran, Quan Hung, Huu-Tien, Dang, Nguyen, Hieu Ngoc, Dau, Anh T. V., Bui, Nghi D. Q.
Influence functions (IFs) are a powerful tool for detecting anomalous examples in large scale datasets. However, they are unstable when applied to deep networks. In this paper, we provide an explanation for the instability of IFs and develop a soluti
Externí odkaz:
http://arxiv.org/abs/2305.01384
Autor:
Anh Thuy Hoang, Tung Hoang Tran, Hai Minh Vu, Hoa Thi Do, Thuc Minh Thi Vu, Linh Gia Vu, Cuong Tat Nguyen, Huyen Phuc Do, Carl A. Latkin, Roger C. M. Ho, Cyrus S. H. Ho
Publikováno v:
Scientific Reports, Vol 14, Iss 1, Pp 1-9 (2024)
Abstract Traumatic brain injury (TBI) is among the leading causes of death in Vietnam. Survivors of TBI suffer from functional and cognitive deficits. Understanding that Activities of Daily Living (ADLs) and Instrumental Activities of Daily Living (I
Externí odkaz:
https://doaj.org/article/e319e0ea5f7346b088aba4d95371a40a
Despite the recent trend of developing and applying neural source code models to software engineering tasks, the quality of such models is insufficient for real-world use. This is because there could be noise in the source code corpora used to train
Externí odkaz:
http://arxiv.org/abs/2205.13022
Autor:
Van Thinh Truong, Sota Hirayama, Duong Cao Phan, Thanh Tung Hoang, Takeo Tadono, Kenlo Nishida Nasahara
Publikováno v:
Scientific Reports, Vol 14, Iss 1, Pp 1-20 (2024)
Abstract Land use land cover (LULC) maps are crucial for various applications, such as disaster management, natural resource conservation, biodiversity evaluation, climate modeling, etc. The Japan Aerospace Exploration Agency (JAXA) has released seve
Externí odkaz:
https://doaj.org/article/096b07e070774f6c8590dfb8756942fe
Autor:
Hai Minh Vu, Linh Gia Vu, Tung Hoang Tran, Laurent Boyer, Pascal Auquier, Guillaume Fond, Tham Thi Nguyen, Linh Khanh Le, Hoa Thi Do, Huyen Phuc Do, Son Nghiem, Carl A. Latkin, Roger C. M. Ho, Cyrus S. H. Ho
Publikováno v:
Scientific Reports, Vol 13, Iss 1, Pp 1-7 (2023)
Abstract Falls are a leading cause of death among elderly people. However, research on the cost of fall-related injuries is limited in Vietnam. We estimated treatment costs and associated factors among 405 elderly patients in Thai Binh hospitals. Cos
Externí odkaz:
https://doaj.org/article/3b9e105f72234b84836d2633dd91248c