Zobrazeno 1 - 10
of 38 349
pro vyhledávání: '"An, Zeyu"'
Autor:
Li, Shuaiting, Wang, Chengxuan, Deng, Juncan, Wang, Zeyu, Ye, Zewen, Wang, Zongsheng, Shen, Haibin, Huang, Kejie
Vector quantization(VQ) is a hardware-friendly DNN compression method that can reduce the storage cost and weight-loading datawidth of hardware accelerators. However, conventional VQ techniques lead to significant accuracy loss because the important
Externí odkaz:
http://arxiv.org/abs/2412.10261
Object detection in Unmanned Aerial Vehicle (UAV) images has emerged as a focal area of research, which presents two significant challenges: i) objects are typically small and dense within vast images; ii) computational resource constraints render mo
Externí odkaz:
http://arxiv.org/abs/2412.10040
Deep learning models in computer vision have achieved significant success but pose increasing concerns about energy consumption and sustainability. Despite these concerns, there is a lack of comprehensive understanding of their energy efficiency duri
Externí odkaz:
http://arxiv.org/abs/2412.09731
Autor:
Shao, Jinsong, Gong, Qineng, Yin, Zeyu, Chen, Yu, Hao, Yajie, Zhang, Lei, Jiang, Linlin, Yao, Min, Li, Jinlong, Wang, Fubo, Wang, Li
The imperfect modeling of ternary complexes has limited the application of computer-aided drug discovery tools in PROTAC research and development. In this study, an AI-assisted approach for PROTAC molecule design pipeline named LM-PROTAC was develope
Externí odkaz:
http://arxiv.org/abs/2412.09661
Publikováno v:
The VLDB Journal 33.6 (2024): 1887-1911
Data series indexes are necessary for managing and analyzing the increasing amounts of data series collections that are nowadays available. These indexes support both exact and approximate similarity search, with approximate search providing high-qua
Externí odkaz:
http://arxiv.org/abs/2412.09448
The rapid growth of the big neural network models puts forward new requirements for lightweight network representation methods. The traditional methods based on model compression have achieved great success, especially VQ technology which realizes th
Externí odkaz:
http://arxiv.org/abs/2412.06875
Text-to-image generation of Stable Diffusion models has achieved notable success due to its remarkable generation ability. However, the repetitive denoising process is computationally intensive during inference, which renders Diffusion models less su
Externí odkaz:
http://arxiv.org/abs/2412.06661
Scene Coordinate Regression (SCR) is a visual localization technique that utilizes deep neural networks (DNN) to directly regress 2D-3D correspondences for camera pose estimation. However, current SCR methods often face challenges in handling repetit
Externí odkaz:
http://arxiv.org/abs/2412.06488
We propose to transfer representational knowledge from multiple sources to a target noisy matrix completion task by aggregating singular subspaces information. Under our representational similarity framework, we first integrate linear representation
Externí odkaz:
http://arxiv.org/abs/2412.06233
SplaXBERT, built on ALBERT-xlarge with context-splitting and mixed precision training, achieves high efficiency in question-answering tasks on lengthy texts. Tested on SQuAD v1.1, it attains an Exact Match of 85.95% and an F1 Score of 92.97%, outperf
Externí odkaz:
http://arxiv.org/abs/2412.05499