Zobrazeno 1 - 10
of 3 101
pro vyhledávání: '"Nguyen, The Duy"'
Autor:
Le, Duc-Truyen, Nguyen, Vu-Linh, Ha, Triet Minh, Nguyen, Cong-Ha, Nguyen, Quoc-Hung, Nguyen, Van-Duy
In this study, we delved into several optimization methods, both classical and quantum, and analyzed the quantum advantage that each of these methods offered, and then we proposed a new combinatorial optimization scheme, deemed as QN-SPSA+PSR which c
Externí odkaz:
http://arxiv.org/abs/2412.19176
To equip artificial intelligence with a comprehensive understanding towards a temporal world, video and 4D panoptic scene graph generation abstracts visual data into nodes to represent entities and edges to capture temporal relations. Existing method
Externí odkaz:
http://arxiv.org/abs/2412.07160
Autor:
Nguyen, Thong Thanh, Bin, Yi, Wu, Xiaobao, Hu, Zhiyuan, Nguyen, Cong-Duy T, Ng, See-Kiong, Luu, Anh Tuan
Temporal grounding, which localizes video moments related to a natural language query, is a core problem of vision-language learning and video understanding. To encode video moments of varying lengths, recent methods employ a multi-level structure kn
Externí odkaz:
http://arxiv.org/abs/2412.07157
Autor:
Nguyen, Quang Vinh, Son, Vo Hoang Thanh, Hoang, Chau Truong Vinh, Nguyen, Duc Duy, Minh, Nhat Huy Nguyen, Kim, Soo-Hyung
Naturalistic driving action localization task aims to recognize and comprehend human behaviors and actions from video data captured during real-world driving scenarios. Previous studies have shown great action localization performance by applying a r
Externí odkaz:
http://arxiv.org/abs/2411.12525
Autor:
Li, Sha, Reddy, Revanth Gangi, Nguyen, Khanh Duy, Wang, Qingyun, Fung, May, Han, Chi, Han, Jiawei, Natarajan, Kartik, Voss, Clare R., Ji, Heng
Complex news events, such as natural disasters and socio-political conflicts, require swift responses from the government and society. Relying on historical events to project the future is insufficient as such events are sparse and do not cover all p
Externí odkaz:
http://arxiv.org/abs/2410.18935
Parameter-efficient fine-tuning (PEFT) can bridge the gap between large language models (LLMs) and downstream tasks. However, PEFT has been proven vulnerable to malicious attacks. Research indicates that poisoned LLMs, even after PEFT, retain the cap
Externí odkaz:
http://arxiv.org/abs/2410.14425
Autor:
Garmroudi, Fabian, Serhiienko, Illia, Parzer, Michael, Ghosh, Sanyukta, Ziolkowski, Pawel, Oppitz, Gregor, Nguyen, Hieu Duy, Bourgès, Cédric, Hattori, Yuya, Riss, Alexander, Steyrer, Sebastian, Rogl, Gerda, Rogl, Peter, Schafler, Erhard, Kawamoto, Naoyuki, Müller, Eckhard, Bauer, Ernst, de Boor, Johannes, Mori, Takao
Decoupling charge and heat transport is essential for optimizing thermoelectric materials. Strategies to inhibit lattice-driven heat transport, however, also compromise carrier mobility, limiting the performance of most thermoelectrics, including Fe$
Externí odkaz:
http://arxiv.org/abs/2410.07785
Autor:
Zhao, Shuai, Gan, Leilei, Guo, Zhongliang, Wu, Xiaobao, Xiao, Luwei, Xu, Xiaoyu, Nguyen, Cong-Duy, Tuan, Luu Anh
Despite being widely applied due to their exceptional capabilities, Large Language Models (LLMs) have been proven to be vulnerable to backdoor attacks. These attacks introduce targeted vulnerabilities into LLMs by poisoning training samples and full-
Externí odkaz:
http://arxiv.org/abs/2409.17946
In this paper, we first provide a simple variational proof of the existence of Nash equilibrium in Hilbert spaces by using optimality conditions in convex minimization and Schauder's fixed-point theorem. Then applications of convex analysis and gener
Externí odkaz:
http://arxiv.org/abs/2408.14433
We investigate the use of derivative information for Batch Active Learning in Gaussian Process regression models. The proposed approach employs the predictive covariance matrix for selection of data batches to exploit full correlation of samples. We
Externí odkaz:
http://arxiv.org/abs/2408.01861