Zobrazeno 1 - 10
of 13 737
pro vyhledávání: '"Li, Wu"'
This paper analyzes the impact of causal manner in the text encoder of text-to-image (T2I) diffusion models, which can lead to information bias and loss. Previous works have focused on addressing the issues through the denoising process. However, the
Externí odkaz:
http://arxiv.org/abs/2410.00321
Autor:
Han, Zhao-Qi-Zhi, Ge, Zheng, Luo, Wen-Tao, Cai, Yi-Fu, Wang, Xiao-Hua, Chen, Li, Li, Wu-Zhen, Zhou, Zhi-Yuan, Shi, Bao-Sen
Detecting mid-infrared (MIR) radiation has significant astronomical applications, although limited by unsatisfactory MIR detectors. Here we reported on the realization of a MIR up-conversion interferometer based on synthetic long base-line (SLBL) in
Externí odkaz:
http://arxiv.org/abs/2408.14902
Order flow modeling stands as the most fundamental and essential financial task, as orders embody the minimal unit within a financial market. However, current approaches often result in unsatisfactory fidelity in generating order flow, and their gene
Externí odkaz:
http://arxiv.org/abs/2408.12991
Autor:
Li, Wu-Zhen, Zhou, Chun, Wang, Yang, Chen, Li, Chen, Ren-Hui, Han, Zhao-Qi-Zhi, Gao, Ming-Yuan, Wang, Xiao-Hua, Zheng, Di-Yuan, Xie, Meng-Yu, Li, Yin-Hai, Zhou, Zhi-Yuan, Bao, Wan-Su, Shi, Bao-Sen
Due to the high noise caused by solar background radiation, the existing satellite-based free-space quantum key distribution (QKD) experiments are mainly carried out at night, hindering the establishment of a practical all-day real-time global-scale
Externí odkaz:
http://arxiv.org/abs/2408.07552
Virtual screening (VS) is a critical step in computer-aided drug discovery, aiming to identify molecules that bind to a specific target receptor like protein. Traditional VS methods, such as docking, are often too time-consuming for screening large-s
Externí odkaz:
http://arxiv.org/abs/2407.19790
Distributed learning is indispensable for training large-scale deep models. Asynchronous SGD~(ASGD) and its variants are commonly used distributed learning methods in many scenarios where the computing capabilities of workers in the cluster are heter
Externí odkaz:
http://arxiv.org/abs/2407.19234
Asynchronous federated learning (AFL) is an effective method to address the challenge of device heterogeneity in cross-device federated learning. However, AFL is usually incompatible with existing secure aggregation protocols used to protect user pri
Externí odkaz:
http://arxiv.org/abs/2406.03516
Autor:
Cai, Wen-Pu, Li, Wu-Jun
Large language models~(LLMs) have recently demonstrated promising performance in many tasks. However, the high storage and computational cost of LLMs has become a challenge for deploying LLMs. Weight quantization has been widely used for model compre
Externí odkaz:
http://arxiv.org/abs/2405.20973
Recently, many works have proposed various financial large language models (FinLLMs) by pre-training from scratch or fine-tuning open-sourced LLMs on financial corpora. However, existing FinLLMs exhibit unsatisfactory performance in understanding fin
Externí odkaz:
http://arxiv.org/abs/2405.00566
Autor:
Liang, Yan-Shuo, Li, Wu-Jun
Continual learning requires the model to learn multiple tasks sequentially. In continual learning, the model should possess the ability to maintain its performance on old tasks (stability) and the ability to adapt to new tasks continuously (plasticit
Externí odkaz:
http://arxiv.org/abs/2404.00228