Zobrazeno 1 - 10
of 19 218
pro vyhledávání: '"Han, DONG"'
With the advancement of face reconstruction (FR) systems, privacy-preserving face recognition (PPFR) has gained popularity for its secure face recognition, enhanced facial privacy protection, and robustness to various attacks. Besides, specific model
Externí odkaz:
http://arxiv.org/abs/2411.18165
Autor:
Mei, Yongsheng, Yuan, Liangqi, Han, Dong-Jun, Chan, Kevin S., Brinton, Christopher G., Lan, Tian
Federated learning (FL) has become a cornerstone in decentralized learning, where, in many scenarios, the incoming data distribution will change dynamically over time, introducing continuous learning (CL) problems. This continual federated learning (
Externí odkaz:
http://arxiv.org/abs/2411.06618
Autor:
Chang, Zhan-Lun, Han, Dong-Jun, Parasnis, Rohit, Hosseinalipour, Seyyedali, Brinton, Christopher G.
While most existing federated learning (FL) approaches assume a fixed set of clients in the system, in practice, clients can dynamically leave or join the system depending on their needs or interest in the specific task. This dynamic FL setting intro
Externí odkaz:
http://arxiv.org/abs/2410.05662
Autor:
Zhang, Daoan, Lan, Guangchen, Han, Dong-Jun, Yao, Wenlin, Pan, Xiaoman, Zhang, Hongming, Li, Mingxiao, Chen, Pengcheng, Dong, Yu, Brinton, Christopher, Luo, Jiebo
Reinforcement learning from human feedback (RLHF) methods are emerging as a way to fine-tune diffusion models (DMs) for visual generation. However, commonly used on-policy strategies are limited by the generalization capability of the reward model, w
Externí odkaz:
http://arxiv.org/abs/2410.05255
With the advance of generative AI, the text-to-image (T2I) model has the ability to generate various contents. However, the generated contents cannot be fully controlled. There is a potential risk that T2I model can generate unsafe images with uncomf
Externí odkaz:
http://arxiv.org/abs/2410.05309
Text-to-image (T2I) models have significantly advanced the development of artificial intelligence, enabling the generation of high-quality images in diverse contexts based on specific text prompts. However, existing T2I-based methods often struggle t
Externí odkaz:
http://arxiv.org/abs/2409.19111
While traditional federated learning (FL) typically focuses on a star topology where clients are directly connected to a central server, real-world distributed systems often exhibit hierarchical architectures. Hierarchical FL (HFL) has emerged as a p
Externí odkaz:
http://arxiv.org/abs/2409.18448
Autor:
Han, Dong, Moon, Jihye, Díaz, Luís Roberto Mercado, Chen, Darren, Williams, Devan, Ding, Eric Y., Tran, Khanh-Van, McManus, David D., Chon, Ki H.
Most deep learning models of multiclass arrhythmia classification are tested on fingertip photoplethysmographic (PPG) data, which has higher signal-to-noise ratios compared to smartwatch-derived PPG, and the best reported sensitivity value for premat
Externí odkaz:
http://arxiv.org/abs/2409.06147
Over the past several years, various federated learning (FL) methodologies have been developed to improve model accuracy, a primary performance metric in machine learning. However, to utilize FL in practical decision-making scenarios, beyond consider
Externí odkaz:
http://arxiv.org/abs/2409.04901
Autor:
Lee, Ji-Eun, Wang, Aifeng, Chen, Shuzhang, Kwon, Minseong, Hwang, Jinwoong, Cho, Minhyun, Son, Ki-Hoon, Han, Dong-Soo, Choi, Jun Woo, Kim, Young Duck, Mo, Sung-Kwan, Petrovic, Cedomir, Hwang, Choongyu, Park, Se Young, Jang, Chaun, Ryu, Hyejin
Publikováno v:
Nature Communications 15, 3971 (2024)
The Berry curvature dipole (BCD) serves as a one of the fundamental contributors to emergence of the nonlinear Hall effect (NLHE). Despite intense interest due to its potential for new technologies reaching beyond the quantum efficiency limit, the in
Externí odkaz:
http://arxiv.org/abs/2408.11658