Zobrazeno 1 - 10
of 312
pro vyhledávání: '"LIU Shengping"'
Publikováno v:
智慧农业, Vol 4, Iss 1, Pp 140-149 (2022)
Objects in farmlands often have characteristic of small volume and high density with variable light and complex background, and the available object detection models could not get satisfactory recognition results. Taking bees as research objects, a m
Externí odkaz:
https://doaj.org/article/e9f48158491c4b2094cb7971adf91bf7
Publikováno v:
Nanophotonics, Vol 11, Iss 2, Pp 329-344 (2021)
Photonic computation has garnered huge attention due to its great potential to accelerate artificial neural network tasks at much higher clock rate to digital electronic alternatives. Especially, reconfigurable photonic processor consisting of Mach
Externí odkaz:
https://doaj.org/article/b0b8ed4f432b49888115d516c3115742
Publikováno v:
智慧农业, Vol 3, Iss 2, Pp 35-44 (2021)
The frequent occurrence of waterlogging stress in winter wheat not only seriously affects regional food security and ecological security, but also threatens social and economic stability and sustainable development. In order to identify the waterlogg
Externí odkaz:
https://doaj.org/article/5f1fb70f616544b0b98baba5c3c7b6a2
Publikováno v:
智慧农业, Vol 2, Iss 2, Pp 105-114 (2020)
The pollination during bees’ foraging is vital to continue species on the earth. However, bee colonies in some areas of America and Europe frequently appeared colony collapse disorder in the past decade due to many possible factors such as climate
Externí odkaz:
https://doaj.org/article/0d6c81d7a388446390920c71b39c450a
Autor:
Liao, Huanxuan, He, Shizhu, Xu, Yao, Zhang, Yuanzhe, Hao, Yanchao, Liu, Shengping, Liu, Kang, Zhao, Jun
Large language models (LLMs) have acquired the ability to solve general tasks by utilizing instruction finetuning (IFT). However, IFT still relies heavily on instance training of extensive task data, which greatly limits the adaptability of LLMs to r
Externí odkaz:
http://arxiv.org/abs/2406.12382
Autor:
Ouyang, Jiayi, Liu, Shengping, Yang, Ziyue, Wang, Wei, Feng, Xue, Li, Yongzhuo, Huang, Yidong
In this article, we proposed a programmable 16-channel photonic solver for quadratic unconstrained binary optimization (QUBO) problems. The solver is based on a hybrid optoelectronic scheme including a photonic chip and the corresponding electronic d
Externí odkaz:
http://arxiv.org/abs/2407.04713
Retrieval-Augmented-Generation and Generation-Augmented-Generation have been proposed to enhance the knowledge required for question answering with Large Language Models (LLMs) by leveraging richer context. However, the former relies on external reso
Externí odkaz:
http://arxiv.org/abs/2403.15268
Large language models (LLMs) store extensive factual knowledge, but the underlying mechanisms remain unclear. Previous research suggests that factual knowledge is stored within multi-layer perceptron weights, and some storage units exhibit degeneracy
Externí odkaz:
http://arxiv.org/abs/2402.13731
Large language models internalize enormous parametric knowledge during pre-training. Concurrently, realistic applications necessitate external contextual knowledge to aid models on the underlying tasks. This raises a crucial dilemma known as knowledg
Externí odkaz:
http://arxiv.org/abs/2402.11893
As language models continue to scale in size and capability, they display an array of emerging behaviors, both beneficial and concerning. This heightens the need to control model behaviors. We hope to be able to control the personality traits of lang
Externí odkaz:
http://arxiv.org/abs/2402.10151