Zobrazeno 1 - 10
of 2 169
pro vyhledávání: '"Li Changsheng"'
Autor:
Jiang Zhuangde, Li Changsheng, Sun Lin, Duan Duanzhi, Kang Chengwei, Chen Shanshan, Lin Qijing, Yang Shuming
Publikováno v:
中国工程科学, Vol 25, Iss 1, Pp 131-141 (2023)
High-end optical elements determine the performance of high-end equipment. Researching the ultra-precision machining technology and equipment for high-end optical elements is crucial for strengthening China's manufacturing industry and satisfying the
Externí odkaz:
https://doaj.org/article/9a1fdd7013e14c99947a83fedc7aeb40
The development of large language models (LLMs) has significantly enhanced the capabilities of multimodal LLMs (MLLMs) as general assistants. However, lack of user-specific knowledge still restricts their application in human's daily life. In this pa
Externí odkaz:
http://arxiv.org/abs/2410.13360
Low-rank training has emerged as a promising approach for reducing memory usage in training Large Language Models (LLMs). Previous methods either rely on decomposing weight matrices (e.g., LoRA), or seek to decompose gradient matrices (e.g., GaLore)
Externí odkaz:
http://arxiv.org/abs/2410.01623
Publikováno v:
中国工程科学, Vol 23, Iss 1, Pp 32-41 (2021)
Based on the strategic background, positioning, and objectives of the planning and construction of the Xiongan New Area, an analysis model framework is established for the requirements for energy revolution during the planning and construction of thi
Externí odkaz:
https://doaj.org/article/6033f4154b8341ab81ae02b1f2bf4ee4
Chain-of-thought distillation is a powerful technique for transferring reasoning abilities from large language models (LLMs) to smaller student models. Previous methods typically require the student to mimic the step-by-step rationale produced by LLM
Externí odkaz:
http://arxiv.org/abs/2405.16064
Autor:
Tian, Huanyu, Huber, Martin, Mower, Christopher E., Han, Zhe, Li, Changsheng, Duan, Xingguang, Bergeles, Christos
In this study, we introduce a novel shared-control system for key-hole docking operations, combining a commercial camera with occlusion-robust pose estimation and a hand-eye information fusion technique. This system is used to enhance docking precisi
Externí odkaz:
http://arxiv.org/abs/2405.05817
End-to-end motion planning models equipped with deep neural networks have shown great potential for enabling full autonomous driving. However, the oversized neural networks render them impractical for deployment on resource-constrained systems, which
Externí odkaz:
http://arxiv.org/abs/2403.01238
Autor:
Tian, Huanyu, Huber, Martin, Mower, Christopher E., Han, Zhe, Li, Changsheng, Duan, Xingguang, Bergeles, Christos
This paper proposes a novel, more computationally efficient method for optimizing robot excitation trajectories for dynamic parameter identification, emphasizing self-collision avoidance. This addresses the system identification challenges for gettin
Externí odkaz:
http://arxiv.org/abs/2401.16566
Typical Convolutional Neural Networks (ConvNets) depend heavily on large amounts of image data and resort to an iterative optimization algorithm (e.g., SGD or Adam) to learn network parameters, which makes training very time- and resource-intensive.
Externí odkaz:
http://arxiv.org/abs/2310.11862
Deep learning models are usually black boxes when deployed on machine learning platforms. Prior works have shown that the attributes ($e.g.$, the number of convolutional layers) of a target black-box neural network can be exposed through a sequence o
Externí odkaz:
http://arxiv.org/abs/2307.10997