Zobrazeno 1 - 10
of 17 990
pro vyhledávání: '"An Hongxiang"'
Controllable human image animation aims to generate videos from reference images using driving videos. Due to the limited control signals provided by sparse guidance (e.g., skeleton pose), recent works have attempted to introduce additional dense con
Externí odkaz:
http://arxiv.org/abs/2412.09349
Autor:
Huang, Xiaoshuang, Shen, Lingdong, Liu, Jia, Shang, Fangxin, Li, Hongxiang, Huang, Haifeng, Yang, Yehui
In recent years, Multimodal Large Language Models (MLLM) have achieved notable advancements, demonstrating the feasibility of developing an intelligent biomedical assistant. However, current biomedical MLLMs predominantly focus on image-level underst
Externí odkaz:
http://arxiv.org/abs/2412.09278
Hard negative generation aims to generate informative negative samples that help to determine the decision boundaries and thus facilitate advancing deep metric learning. Current works select pair/triplet samples, learn their correlations, and fuse th
Externí odkaz:
http://arxiv.org/abs/2411.13145
Networks representation aims to encode vertices into a low-dimensional space, while preserving the original network structures and properties. Most existing methods focus on static network structure without considering temporal dynamics. However, in
Externí odkaz:
http://arxiv.org/abs/2410.20627
Autor:
Chen, Hao Mark, Tan, Fuwen, Kouris, Alexandros, Lee, Royson, Fan, Hongxiang, Venieris, Stylianos I.
In spite of the great potential of large language models (LLMs) across various tasks, their deployment on resource-constrained devices remains challenging due to their excessive computational and memory demands. Quantization has emerged as an effecti
Externí odkaz:
http://arxiv.org/abs/2410.13461
Text-to-image (T2I) diffusion models have drawn attention for their ability to generate high-quality images with precise text alignment. However, these models can also be misused to produce inappropriate content. Existing safety measures, which typic
Externí odkaz:
http://arxiv.org/abs/2410.02710
Autor:
Feng, Yiting, Zhang, Shen, Zeng, Qingqi, Lyu, Meng, Liu, Junyan, Yang, Jinying, Wang, Yibo, Ren, Qiusa, Liu, Yang, Wang, Binbin, Wei, Hongxiang, Liu, Enke
All-d-metal full-Heusler alloys possess superior mechanical properties and high spin polarization, which would play an important role in spintronic applications. Despite this, their electrical and thermal transport properties have not been comprehens
Externí odkaz:
http://arxiv.org/abs/2409.09718
Autor:
Liu, Junyan, Wang, Yibo, Dong, Xuebin, Yang, Jinying, Zhang, Shen, Lyu, Meng, Wang, Binbin, Wei, Hongxiang, Wang, Shouguo, Liu, Enke, Shen, Baogen
Nodal chain semimetals protected by nonsymmorphic symmetries are distinct from Dirac and Weyl semimetals, featuring unconventional topological surface states and resulting in anomalous magnetotransport properties. Here, we reveal that the ferromagnet
Externí odkaz:
http://arxiv.org/abs/2409.09712
Autor:
Zhang, Shen, Yang, Jinying, Lyu, Meng, Liu, Junyan, Wang, Binbin, Wei, Hongxiang, Felser, Claudia, Zhang, Wenqing, Liu, Enke, Shen, Baogen
Magnetic topological semimetals are increasingly fueling interests in exotic electronic-thermal physics including thermoelectrics and spintronics. To control the transports of topological carriers in such materials becomes a central issue. However, t
Externí odkaz:
http://arxiv.org/abs/2409.09709
This paper presents an innovative approach to reducing Peak-to-Average Power Ratio (PAPR) in Coherent Optical Orthogonal Frequency Division Multiplexing (CO-OFDM) systems. The proposed deep learning autoencoder-based model eliminates the computationa
Externí odkaz:
http://arxiv.org/abs/2408.14248