检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Cheng, Yifei Shen, Li Xu, Linli Qian, Xun Wu, Shiwei Zhou, Yiming Zhang, Tie Tao, Dacheng Chen, Enhong The Anhui Province Key Lab of Big Data Analysis and Application State Key Laboratory of Cognitive Intelligence School of Data Science School of Computer Science University of Science and Technology China The JD Explore Academy China The Shanghai Artificial Intelligence Laboratory China

Gradient compression with error compensation has attracted significant attention with the target of reducing the heavy communication overhead in distributed learning. However, existing compression methods either perform only unidirectional compression in one iteration with higher communication cost, or bidirectional compression with slower convergence rate. In this work, we propose the Local Immediate Error Compensated SGD (LIEC-SGD) optimization algorithm to break the above bottlenecks based on bidirectional compression and carefully designed compensation approaches. Specifically, the bidirectional compression technique is to reduce the communication cost, and the compensation technique compensates the local compression error to the model update immediately while only maintaining the global error variable on the server throughout the iterations to boost its efficacy. Theoretically, we prove that LIEC-SGD is superior to previous works in either the convergence rate or the communication cost, which indicates that LIEC-SGD could inherit the dual advantages from unidirectional compression and bidirectional compression. Finally, experiments of training deep neural networks validate the effectiveness of the proposed LIEC-SGD algorithm. Copyright © 2024, The Authors. All rights reserved.

关键词： Error compensation

来源：评论

学校读者我要写书评

暂无评论

A Silk-Based Minimally Invasive Stent-Electrode system for Vasospasm Monitoring and In-Situ Treatment 38

A Silk-Based Minimally Invasive Stent-Electrode System for V...

引用

38th IEEE International Conference on Micro Electro Mechanical systems, MEMS 2025

作者： Diao, Yihan He, Hailang Fang, Zuyong Wei, Xiaoling Sun, Liuyang Tao, Tiger H. Zhou, Zhitao 2020 X-Lab Shanghai Institute of Microsystem and Information Technology Chinese Academy of Sciences Shanghai China School of Graduate Study University of Chinese Academy of Sciences Beijing China State Key Laboratory of Transducer Technology Shanghai Institute of Microsystem and Information Technology Chinese Academy of Sciences Shanghai China Center of Materials Science and Optoelectronics Engineering University of Chinese Academy of Sciences Beijing China School of Physical Science and Technology ShanghaiTech University Shanghai China Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Shanghai China Jiangxi Nanchang China Guangdong Institute of Intelligence Science and Technology Zhuhai Guangdong Hengqin China Tianqiao and Chrissy Chen Institute for Translational Research Shanghai China

ISBN: (纸本)9798331508890

We report a flexible silk-based stent-electrode system designed for minimally invasive vascular implantation with controllable drug release, featuring vasospasm monitoring and real-time drug delivery capabilities. Comprehensive characterization of its mechanical properties, electrical performance, and drug release functionality has been conducted, with the feasibility of the system successfully demonstrated in vitro. The silk-based stent exhibits outstanding mechanical strength and biocompatibility, enabling precise control over drug release. The electrode array, constructed on a flexible PI substrate, is produced using a double-sided MEMS process, ensuring conformal implantation and optimal integration within vascular environments. Therefore, our vascular stent-electrode system demonstrates great potential for monitoring vascular electrophysiological activity, detecting vasospasm, and providing real-time therapeutic drug delivery for treating vascular-related diseases. © 2025 IEEE.

关键词： Silk

来源：评论

学校读者我要写书评

暂无评论

DiC: Rethinking Conv3x3 Designs in Diffusion Models

arXiv

引用

arXiv 2024年

作者： Tian, Yuchuan Han, Jing Wang, Chengcheng Liang, Yuchen Xu, Chao Chen, Hanting State Key Lab of General AI School of Intelligence Science and Technology Peking University China School of Physics Peking University China Huawei Noah's Ark Lab Hong Kong

Diffusion models have shown exceptional performance in visual generation tasks. Recently, these models have shifted from traditional U-Shaped CNN-Attention hybrid structures to fully transformer-based isotropic architectures. While these transformers exhibit strong scalability and performance, their reliance on complicated self-attention operation results in slow inference speeds. Contrary to these works, we rethink one of the simplest yet fastest module in deep learning, 3x3 Convolution, to construct a scaled-up purely convolutional diffusion model. We first discover that an Encoder-Decoder Hourglass design outperforms scalable isotropic architectures for Conv3x3, but still under-performing our expectation. Further improving the architecture, we introduce sparse skip connections to reduce redundancy and improve scalability. Based on the architecture, we introduce conditioning improvements including stage-specific embeddings, mid-block condition injection, and conditional gating. These improvements lead to our proposed Diffusion CNN (DiC), which serves as a swift yet competitive diffusion architecture baseline. Experiments on various scales and settings show that DiC surpasses existing diffusion transformers by considerable margins in terms of performance while keeping a good speed advantage. Project page: https://***/YuchuanTian/DiC. Copyright © 2024, The Authors. All rights reserved.

关键词： Scalability

来源：评论

学校读者我要写书评

暂无评论

Visual-Language Prompt Tuning with Knowledge-Guided Context Optimization

Visual-Language Prompt Tuning with Knowledge-Guided Context ...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Hantao Yao Rui Zhang Changsheng Xu State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation CAS State Key Lab of Processors Institute of Computing Technology CAS University of Chinese Academy of Sciences(CAS)

Prompt tuning is an effective way to adapt the pretrained visual-language model (VLM) to the downstream task using task-related textual tokens. Representative CoOp-based work combines the learnable textual tokens with the class tokens to obtain specific textual knowledge. However, the specific textual knowledge is worse generalization to the unseen classes because it forgets the essential general textual knowledge having a strong generalization ability. To tackle this issue, we introduce a novel Knowledge-guided Context Optimization (KgCoOp) to enhance the generalization ability of the learnable prompt for unseen classes. The key insight of KgCoOp is that the forgetting about essential knowledge can be alleviated by reducing the discrepancy between the learnable prompt and the hand-crafted prompt. Especially, KgCoOp minimizes the discrepancy between the textual embeddings generated by learned prompts and the hand-crafted prompts. Finally, adding the KgCoOp upon the contrastive loss can make a discriminative prompt for both seen and unseen tasks. Extensive evaluation of several benchmarks demonstrates that the proposed Knowledge-guided Context Optimization is an efficient method for prompt tuning, i.e., achieves better performance with less training time. code.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Grid4D: 4D decomposed hash encoding for high-fidelity dynamic Gaussian splatting 24

Grid4D: 4D decomposed hash encoding for high-fidelity dynami...

引用

Proceedings of the 38th International Conference on Neural Information Processing systems

作者： Jiawei Xu Zexin Fan Jian Yang Jij Xie PCA Lab VCIP College of Computer Science Nankai University State Key Laboratory for Novel Software Technology Nanjing University Nanjing China and School of Intelligence Science and Technology Nanjing University Suzhou China

ISBN: (纸本)9798331314385

Recently, Gaussian splatting has received more and more attention in the field of static scene rendering. Due to the low computational overhead and inherent flexibility of explicit representations, plane-based explicit methods are popular ways to predict deformations for Gaussian-based dynamic scene rendering models. However, plane-based methods rely on the inappropriate low-rank assumption and excessively decompose the space-time 4D encoding, resulting in overmuch feature overlap and unsatisfactory rendering quality. To tackle these problems, we propose Grid4D, a dynamic scene rendering model based on Gaussian splatting and employing a novel explicit encoding method for the 4D input through the hash encoding. Different from plane-based explicit representations, we decompose the 4D encoding into one spatial and three temporal 3D hash encodings without the low-rank assumption. Additionally, we design a novel attention module that generates the attention scores in a directional range to aggregate the spatial and temporal features. The directional attention enables Grid4D to more accurately fit the diverse deformations across distinct scene components based on the spatial encoded features. Moreover, to mitigate the inherent lack of smoothness in explicit representation methods, we introduce a smooth regularization term that keeps our model from the chaos of deformation prediction. Our experiments demonstrate that Grid4D significantly outperforms the state-of-the-art models in visual quality and rendering speed. Project page: https://***/Grid4D-web/.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MEMS-based High-Density Ultra-Conformal μeCOG Electrode Array for Real-Time Motor Decoding 38

MEMS-based High-Density Ultra-Conformal μeCOG Electrode Arr...

引用

38th IEEE International Conference on Micro Electro Mechanical systems, MEMS 2025

作者： Zhou, Erda Liu, Changjiang Wang, Xiner Wei, Xiaoling Sun, Liuyang Tao, Tiger H. Zhou, Zhitao 2020 X-lab Shanghai Institute of Microsystem and Information Technology Chinese Academy of Sciences Shanghai China State Key Laboratory of Transducer Technology Shanghai Institute of Microsystem and Information Technology Chinese Academy of Sciences Shanghai China School of Graduate Study University of Chinese Academy of Sciences Beijing China Center of Materials Science and Optoelectronics Engineering University of Chinese Academy of Sciences Beijing China Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Shanghai China Neuroxess Co. Ltd. Shanghai China Guangdong Institute of Intelligence Science and Technology Zhuhai Guangdong Hengqin China Tianqiao and Chrissy Chen Institute for Translation Research Shanghai China

ISBN: (纸本)9798331508890

In this study, we present a high-density, high-channel-count micro-electrocorticographic (μECoG) electrode array for real-time motor decoding. The 256-channel μECoG electrode arrays, based on MEMS processes, possess excellent flexibility and mechanical robustness, allowing them to conform to the cortical surface and enabling the acquisition of high-quality ECoG signals. The advanced brain-computer interface (BCI) system was applied to a labrador dog and high accurate real-time motor decoding was achieved, showing the advantages of high-resolution ECoG sampling. Our method demonstrates the potential for controlling a cursor with the ECoG signals, offering the possibility of reconstructing motor functions and synthesizing avatars. © 2025 IEEE.

关键词： Brain computer interface

来源：评论

学校读者我要写书评

暂无评论

Top-Down Meets Bottom-Up for Multi-Person Pose Estimation

Top-Down Meets Bottom-Up for Multi-Person Pose Estimation

引用

Chinese Control and Decision Conference, CCDC

作者： Jingyao Wang Naigong Yu Faculty of Information Technology Beijing University of Technology Beijing Beijing Key Lab of the Computational Intelligence and Intelligent System Beijing University of Technology Beijing

ISBN: (纸本)9781665478977

Body posture, as a basic feature of humans, occupies an important position in human-computer interaction and other fields. In order to accurately recognize human body posture features and eliminate misrecognition caused by different human movements. This paper proposes a human body posture detection method that combines top-down and bottom-up two-way. This method divides the input image into two forks, and uses the Mask R-CNN model to extract key point features and human target location features. The key point recognition feature map is divided into two, and using CNN to extract Part Affinity Fields and Part Confidence Maps. The obtained confidence map is added with the human body position feature map. Then use PAFs to segment the key points of different individuals in the result. Finally, the Hungarian Algorithm is used to process the maximum matching of the bipartite graph to obtain the human body posture detection result. Experimental results show that this method can accurately recognize human posture. It has good performance on different data sets and eliminates the estimation accuracy defects of traditional models due to the complex high-dimensional motion of the target.

关键词： Human computer interaction Biological system modeling Delay effects Pose estimation Feature extraction Data models Bipartite graph

来源：评论

学校读者我要写书评

暂无评论

COMMUNICATION-EFFICIENT PERSONALIZED FEDERATED LEARNING FOR SPEECH-TO-TEXT TASKS

arXiv

引用

arXiv 2024年

作者： Du, Yichao Zhang, Zhirui Yue, Linan Huang, Xu Zhang, Yuqing Xu, Tong Xu, Linli Chen, Enhong University of Science and Technology of China State Key Laboratory of Cognitive Intelligence China Tencent AI Lab China Nanjing University China Anhui Xinhua University China

To protect privacy and meet legal regulations, federated learning (FL) has gained significant attention for training speech-to-text (S2T) systems, including automatic speech recognition (ASR) and speech translation (ST). However, the commonly used FL approach (i.e., FEDAVG) in S2T tasks typically suffers from extensive communication overhead due to multi-round interactions based on the whole model and performance degradation caused by data heterogeneity among clients. To address these issues, we propose a personalized federated S2T framework that introduces FEDLORA, a lightweight LoRA module for client-side tuning and interaction with the server to minimize communication overhead, and FEDMEM, a global model equipped with a k-nearest-neighbor (kNN) classifier that captures client-specific distributional shifts to achieve personalization and overcome data heterogeneity. Extensive experiments based on Conformer and Whisper backbone models on CoVoST and GigaSpeech benchmarks show that our approach significantly reduces the communication overhead on all S2T tasks and effectively personalizes the global model to overcome data heterogeneity. Copyright © 2024, The Authors. All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Magnetic phase transitions in the triangular-lattice spin-1 dimer compound K2Ni2(SeO3)3

引用

Physical Review B 2024年第21期109卷 214430-214430页

作者： Lei Yue Ziyou Lu Kun Yan Le Wang Shu Guo Ruixin Guo Peng Chen Xiaobin Chen Jia-Wei Mei Department of Physics School of Science and State Key Laboratory on Tunable Laser Technology and Ministry of Industry and Information Technology Key Lab of Micro-Nano Optoelectronic Information System Shenzhen Institute for Quantum Science and Engineering International Quantum Academy Shenzhen 518048 China Dongguan Guangdong 523808 China Shenzhen Key Laboratory of Advanced Quantum Functional Materials and Devices

In our study, we conduct magnetization and heat capacity measurements to investigate field-induced magnetic phase transitions within the newly synthesized compound K2Ni2(SeO3)3, a spin-1 dimer system arranged on a triangular lattice. From our first-principles simulations, we determine that the spin system in K2Ni2(SeO3)3 can be represented as a two-dimensional triangular-lattice spin-1 dimer model, including an intra-dimer exchange of J1=0.32meV, an inter-dimer exchange of J2=0.79meV, and an easy-axis anisotropy of D=0.14meV. The presence of easy-axis magnetic anisotropy explains the distinct magnetic phase diagrams observed under c-axis directional and in-plane magnetic fields. Notably, our investigation unveils a two-step phase transition with the magnetic field aligned with the c direction. Our findings yield valuable insights into the magnetic phase transitions inherent to geometrically frustrated magnetic systems featuring dimer structures.

关键词： Frustrated magnetism Magnetic phase transitions Triangular lattice Magnetization measurements Specific heat measurements X-ray diffraction

来源：评论

学校读者我要写书评

暂无评论

Pressure-induced emission in 0D metal halide(EATMP)SbBr5 by regulating exciton-phonon coupling

引用

Chinese Journal of Structural Chemistry 2024年第7期43卷 47-53页

作者： Jiayuan Liang Xin Mi Songhao Guo Hui Luo Kejun Bu Tonghuan Fu Menglin Duan Yang Wang Qingyang Hu Rengen Xiong Peng Qin Fuqiang Huang Xujie Lü Center for High Pressure Science and Technology Advanced Research(HPSTAR) Shanghai201203China State Key Laboratory of High Performance Ceramics and Superfine Microstructure Shanghai Institute of CeramicsChinese Academy of SciencesShanghai200050China Center of Materials Science and Optoelectronics Engineering University of Chinese Academy of SciencesBeijing 100049China Center of Micro-Nano System School of Information Science and TechnologyFudan UniversityShanghai200433China Ordered Matter Science Research Center Nanchang UniversityNanchang330031China State Key Lab of Metal Matrix Composites School of Materials Science and EngineeringShanghai Jiao Tong UniversityDongchuan Road 800Shanghai200240China Shanghai Key Laboratory of Material Frontiers Research in Extreme Environments(MFree) Shanghai Advanced Research in Physical Sciences(SHARPS)PudongShanghai201203China

Zero-dimensional(0D)hybrid metal halides are considered as promising light-emitting materials due to their unique broadband emission from self-trapped excitons(STEs).Despite substantial progress in the development of these materials,the photoluminescence quantum yields(PLQY)of hybrid Sb-Br analogs have not fully realized the ca-pabilities of these materials,necessitating a better fundamental understanding of the structure-property ***,we have achieved a pressure-induced emission in 0D(EATMP)SbBr5(EATMP=(2-aminoethyl)trimethylphosphanium)and the underlying mechanisms are investigated using in situ experimental characterization and first-principles *** pressure-induced reduction in the overlap between the STE states and ground states(GSs)results in the suppression of phonon-assisted non-radiative *** photoluminescence(PL)evo-lution is systematically demonstrated to be controlled by the pressure-regulated exciton-phonon coupling,which can be quantified using Huang-Rhys *** detailed studies of the S-PLQY relation in a series of 0D hybrid antimony halides,we establish a quantitative structure-property relationship that regulating S value toward 21 leads to the optimized *** work not only sheds light on pressure-induced emission in 0D hybrid metal halides but also provides valuable insights into the design principles for enhancing the PLQY in this class of materials.

关键词： 0D hybrid metal halides Pressure-induced emission Structure-property relationship Huang-Rhys factor Exciton-phonon coupling

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：