Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Li, Huixia"'
Autor:
Ma, Yuexiao, Li, Huixia, Zheng, Xiawu, Ling, Feng, Xiao, Xuefeng, Wang, Rui, Wen, Shilei, Chao, Fei, Ji, Rongrong
The significant resource requirements associated with Large-scale Language Models (LLMs) have generated considerable interest in the development of techniques aimed at compressing and accelerating neural networks. Among these techniques, Post-Trainin
Externí odkaz:
http://arxiv.org/abs/2403.12544
Autor:
Cheng, Jiaxiang, Xie, Pan, Xia, Xin, Li, Jiashi, Wu, Jie, Ren, Yuxi, Li, Huixia, Xiao, Xuefeng, Zheng, Min, Fu, Lean
Recent advancement in text-to-image models (e.g., Stable Diffusion) and corresponding personalized technologies (e.g., DreamBooth and LoRA) enables individuals to generate high-quality and imaginative images. However, they often suffer from limitatio
Externí odkaz:
http://arxiv.org/abs/2403.02084
Autor:
Li, Lijiang, Li, Huixia, Zheng, Xiawu, Wu, Jie, Xiao, Xuefeng, Wang, Rui, Zheng, Min, Pan, Xin, Chao, Fei, Ji, Rongrong
Diffusion models are emerging expressive generative models, in which a large number of time steps (inference steps) are required for a single image generation. To accelerate such tedious process, reducing steps uniformly is considered as an undispute
Externí odkaz:
http://arxiv.org/abs/2309.10438
Autor:
Ma, Yuexiao, Li, Huixia, Zheng, Xiawu, Xiao, Xuefeng, Wang, Rui, Wen, Shilei, Pan, Xin, Chao, Fei, Ji, Rongrong
Post-training quantization (PTQ) is widely regarded as one of the most efficient compression methods practically, benefitting from its data privacy and low computation costs. We argue that an overlooked problem of oscillation is in the PTQ methods. I
Externí odkaz:
http://arxiv.org/abs/2303.11906
We present an event-by-event study of photon production in early stage of high energy nuclear collisions, where the system is dominant by highly occupied of gluons and initialized by McLerran-Venugopalan model. The photons are produced through the gl
Externí odkaz:
http://arxiv.org/abs/2211.16770
Autor:
Li, Jiashi, Xia, Xin, Li, Wei, Li, Huixia, Wang, Xing, Xiao, Xuefeng, Wang, Rui, Zheng, Min, Pan, Xin
Due to the complex attention mechanisms and model design, most existing vision Transformers (ViTs) can not perform as efficiently as convolutional neural networks (CNNs) in realistic industrial deployment scenarios, e.g. TensorRT and CoreML. This pos
Externí odkaz:
http://arxiv.org/abs/2207.05501
Autor:
Ma, Yuexiao, Jin, Taisong, Zheng, Xiawu, Wang, Yan, Li, Huixia, Wu, Yongjian, Jiang, Guannan, Zhang, Wei, Ji, Rongrong
To bridge the ever increasing gap between deep neural networks' complexity and hardware capability, network quantization has attracted more and more research attention. The latest trend of mixed precision quantization takes advantage of hardware's mu
Externí odkaz:
http://arxiv.org/abs/2109.07865
Autor:
Li, Huixia, Yan, Chenqian, Lin, Shaohui, Zheng, Xiawu, Li, Yuchao, Zhang, Baochang, Yang, Fan, Ji, Rongrong
Deep convolutional neural networks (DCNNs) have shown dominant performance in the task of super-resolution (SR). However, their heavy memory cost and computation overhead significantly restrict their practical deployments on resource-limited devices,
Externí odkaz:
http://arxiv.org/abs/2011.04212
In this paper, we study two-dimensional, three-dimensional monotonic and nonmonotonic immune responses in viral infection systems. Our results show that the viral infection systems with monotonic immune response has no bistability appear. However, th
Externí odkaz:
http://arxiv.org/abs/1908.00687