Zobrazeno 1 - 10
of 3 360
pro vyhledávání: '"LIU Zhenhua"'
Autor:
Liang, Cong, Song, Xiangli, Cheng, Jing, Wang, Mowei, Liu, Yashe, Liu, Zhenhua, Zhao, Shizhen, Cui, Yong
Recent advances in fast optical switching technology show promise in meeting the high goodput and low latency requirements of datacenter networks (DCN). We present NegotiaToR, a simple network architecture for optical reconfigurable DCNs that utilize
Externí odkaz:
http://arxiv.org/abs/2407.20045
Large language models (LLMs) exhibit remarkable capabilities in understanding and generating natural language. However, these models can inadvertently memorize private information, posing significant privacy risks. This study addresses the challenge
Externí odkaz:
http://arxiv.org/abs/2407.10058
Large Language Models (LLMs) have shown their impressive capabilities, while also raising concerns about the data contamination problems due to privacy issues and leakage of benchmark datasets in the pre-training phase. Therefore, it is vital to dete
Externí odkaz:
http://arxiv.org/abs/2406.01333
The demand for large language model (LLM) inference is gradually dominating the artificial intelligence workloads. Therefore, there is an urgent need for cost-efficient inference serving. Existing work focuses on single-worker optimization and lacks
Externí odkaz:
http://arxiv.org/abs/2405.06856
Speculative decoding has demonstrated its effectiveness in accelerating the inference of large language models while maintaining a consistent sampling distribution. However, the conventional approach of training a separate draft model to achieve a sa
Externí odkaz:
http://arxiv.org/abs/2404.18911
Compact neural networks are specially designed for applications on edge devices with faster inference speed yet modest performance. However, training strategies of compact models are borrowed from that of conventional models at present, which ignores
Externí odkaz:
http://arxiv.org/abs/2404.11202
In real-life conversations, the content is diverse, and there exists the one-to-many problem that requires diverse generation. Previous studies attempted to introduce discrete or Gaussian-based continuous latent variables to address the one-to-many p
Externí odkaz:
http://arxiv.org/abs/2404.06760
Data augmentation (DA) is crucial to mitigate model training instability and over-fitting problems in low-resource open-domain dialogue generation. However, traditional DA methods often neglect semantic data diversity, restricting the overall quality
Externí odkaz:
http://arxiv.org/abs/2404.00361
Adjusting batch sizes and adaptively tuning other hyperparameters can significantly speed up deep neural network (DNN) training. Despite the ubiquity of heterogeneous clusters, existing adaptive DNN training techniques solely consider homogeneous env
Externí odkaz:
http://arxiv.org/abs/2402.05302
Autor:
Liu, Zhenhua
De Lellis and coauthors have proved a sharp regularity theorem for area-minimizing currents in finite coefficient homology. They prove that area-minimizing mod $v$ currents are smooth outside of a singular set of codimension at least $1.$ Classical e
Externí odkaz:
http://arxiv.org/abs/2401.18074