Zobrazeno 1 - 10
of 9 203
pro vyhledávání: '"An, Zhenyi"'
Publikováno v:
Universe 2024, 10, 282
In terms of the variable nature of normal active galaxy nuclei (AGN) and luminous quasars, a so-called flux variation gradient (FVG) method has been widely utilized to estimate the underlying non-variable host galaxy fluxes. The FVG method assumes an
Externí odkaz:
http://arxiv.org/abs/2407.03597
The large-scale integration of intermittent renewable energy resources introduces increased uncertainty and volatility to the supply side of power systems, thereby complicating system operation and control. Recently, data-driven approaches, particula
Externí odkaz:
http://arxiv.org/abs/2407.00681
Diffusion models (DMs) have achieved significant success in generating imaginative images given textual descriptions. However, they are likely to fall short when it comes to real-life scenarios with intricate details.The low-quality, unrealistic huma
Externí odkaz:
http://arxiv.org/abs/2406.17100
Efficient fine-tuning of large language models for task-specific applications is imperative, yet the vast number of parameters in these models makes their training increasingly challenging. Despite numerous proposals for effective methods, a substant
Externí odkaz:
http://arxiv.org/abs/2406.15480
In the era of large language models, model merging is a promising way to combine multiple task-specific models into a single multitask model without extra training. However, two challenges remain: (a) interference between different models and (b) het
Externí odkaz:
http://arxiv.org/abs/2406.15479
Text classification is a crucial task encountered frequently in practical scenarios, yet it is still under-explored in the era of large language models (LLMs). This study shows that LLMs are vulnerable to changes in the number and arrangement of opti
Externí odkaz:
http://arxiv.org/abs/2406.07001
Distilling large latent diffusion models (LDMs) into ones that are fast to sample from is attracting growing research interest. However, the majority of existing methods face a dilemma where they either (i) depend on multiple individual distilled mod
Externí odkaz:
http://arxiv.org/abs/2406.05768
Data-Free Meta-Learning (DFML) aims to derive knowledge from a collection of pre-trained models without accessing their original data, enabling the rapid adaptation to new unseen tasks. Current methods often overlook the heterogeneity among pre-train
Externí odkaz:
http://arxiv.org/abs/2405.16560
Autor:
Qian, Ziyun, Xiao, Zeyu, Wu, Zhenyi, Yang, Dingkang, Li, Mingcheng, Wang, Shunli, Wang, Shuaibing, Kou, Dongliang, Zhang, Lihua
Motion style transfer is a significant research direction in multimedia applications. It enables the rapid switching of different styles of the same motion for virtual digital humans, thus vastly increasing the diversity and realism of movements. It
Externí odkaz:
http://arxiv.org/abs/2405.02844
Data-Free Meta-Learning (DFML) aims to extract knowledge from a collection of pre-trained models without requiring the original data, presenting practical benefits in contexts constrained by data privacy concerns. Current DFML methods primarily focus
Externí odkaz:
http://arxiv.org/abs/2405.00984