Zobrazeno 1 - 10
of 2 764
pro vyhledávání: '"An Hongliu"'
Autor:
Cao, Hongliu
The rapid advancement of Language Model technologies has opened new opportunities, but also introduced new challenges related to bias and fairness. This paper explores the uncharted territory of potential biases in state-of-the-art universal text emb
Externí odkaz:
http://arxiv.org/abs/2411.13173
Autor:
Dong, Jiahua, Liang, Wenqi, Li, Hongliu, Zhang, Duzhen, Cao, Meng, Ding, Henghui, Khan, Salman, Khan, Fahad Shahbaz
Custom diffusion models (CDMs) have attracted widespread attention due to their astonishing generative ability for personalized concepts. However, most existing CDMs unreasonably assume that personalized concepts are fixed and cannot change over time
Externí odkaz:
http://arxiv.org/abs/2410.17594
Few-shot medical image segmentation has achieved great progress in improving accuracy and efficiency of medical analysis in the biomedical imaging field. However, most existing methods cannot explore inter-class relations among base and novel medical
Externí odkaz:
http://arxiv.org/abs/2406.05054
Autor:
Dong, Jiahua, Yin, Hui, Li, Hongliu, Li, Wenbo, Zhang, Yulun, Khan, Salman, Khan, Fahad Shahbaz
Deep unfolding methods have made impressive progress in restoring 3D hyperspectral images (HSIs) from 2D measurements through convolution neural networks or Transformers in spectral compressive imaging. However, they cannot efficiently capture long-r
Externí odkaz:
http://arxiv.org/abs/2406.00449
Autor:
Cao, Hongliu
Text embedding methods have become increasingly popular in both industrial and academic fields due to their critical role in a variety of natural language processing tasks. The significance of universal text embeddings has been further highlighted wi
Externí odkaz:
http://arxiv.org/abs/2406.01607
Autor:
Cao, Hongliu
To comply with new legal requirements and policies committed to privacy protection, more and more companies start to deploy cross-silo Federated Learning at global scale, where several clients/silos collaboratively train a global model under the coor
Externí odkaz:
http://arxiv.org/abs/2312.14628
Face recognition has been used more and more in real world applications in recent years. However, when the skin color bias is coupled with intra-personal variations like harsh illumination, the face recognition task is more likely to fail, even durin
Externí odkaz:
http://arxiv.org/abs/2312.14544
As the digitization of travel industry accelerates, analyzing and understanding travelers' behaviors becomes increasingly important. However, traveler data frequently exhibit high data sparsity due to the relatively low frequency of user interactions
Externí odkaz:
http://arxiv.org/abs/2312.14533
Publikováno v:
Scientific Reports, Vol 14, Iss 1, Pp 1-11 (2024)
Abstract Transcutaneous electrical nerve stimulation (TENS) has been used to treat chronic pain. However, the potential efficacy and mechanism of the effect of applying TENS for a short time in chronic pain patients remains unclear. To identify the e
Externí odkaz:
https://doaj.org/article/d47a2ba20247453683c41beb7aec8cc6
Publikováno v:
Nature Communications, Vol 15, Iss 1, Pp 1-13 (2024)
Abstract To prevent zinc (Zn) dendrite formation and improve electrochemical stability, it is essential to understand Zn dendrite growth, particularly in terms of morphology and relation with the solid electrolyte interface (SEI) film. In this study,
Externí odkaz:
https://doaj.org/article/b9e284e180e248a1959b7fd5973cd02e