检索结果-内蒙古大学图书馆

2024 International Meshing Roundtable, IMR 2024

作者： Zheng, Zhihao Dai, Liang Gao, Shuming State Key Lab of CAD & CG Zhejiang University China School of Data Science and Artficial Intelligence Wenzhou University of Technology China

ISBN: (纸本)9781713893462

Thanks to their superior numerical properties, conforming hex meshes have become a popular choice in the context of simulation. However, due to the global structural constraints, generating hex meshes has been a subject of extensive study, giving rise to numerous fascinating and challenging associated problems. In light of this, this paper introduces an innovative approach based on non-regular background mesh, aimed at automatically generating high-quality adaptive hex meshes for CAD models with arbitrary complexity. The algorithm initially generates a non-regular background mesh for the given solid model through several steps involving shape analysis, quad mesh sweeping and templates-based mesh refinement. Subsequently, to convert this background mesh into a conformal hex mesh, the algorithm identifies the globally optimized core hex mesh via a graph-cut algorithm. To further improve the quality of mesh, the algorithm conducts topology improvement, coupled with geometric optimization guided by quality metrics applied to boundary layers of core mesh. Experimental results showed the effectiveness of the proposed algorithm. © 2024 by SIAM.

关键词： Boundary layers

来源：评论

学校读者我要写书评

暂无评论

Quantitative relationship between components and pour point of natural esters and its molecular mechanism

引用

IEEE Access 2025年 13卷 91902-91910页

作者： Qian, Guochao Dai, Weiju Hao, Jian Feng, Dawei Xu, Jing Electric Power Research Institute Yunnan Power Grid Co. Ltd Kunming650217 China Chongqing University State Key Laboratory of Power Transmission Equipment Technology School of Electrical Engineering Chongqing400044 China Hebei University of Technology School of Electrical Engineering State Key Lab of Reliability and Intelligence of Electrical Equipment Tianjin300401 China

With increasing emphasis on environmental sustainability and fire safety in the global power transformer industry, natural esters have emerged as preferred alternatives to conventional mineral oil. However, the cold flow properties of natural esters are unsatisfactory, which limits their application in cold areas. To solve this problem, this study carried out tests on natural ester components and pour point, the relationship and its molecular mechanism between components and pour point was studied. The results indicate that unsaturated fatty acids may also increase the pour point. When the content of linolenic acid exceeds 18%, it will actually increase the pour point of natural esters. The quantitative relationship between components and pour point of natural esters was constructed, and its average relative percentage error in prediction of pour point is within 7.5%, which show its good predictive performance. Molecular dynamics further verified that C=C bonds inhibit chain bending and stacking while maintain intermolecular spacing during cooling, which helps to improve cold flow properties. This study provides a theoretical basis for the preparation of high-performance natural esters insulation oil. © 2013 IEEE.

关键词： Fireproofing

来源：评论

学校读者我要写书评

暂无评论

Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction 38

Visual Autoregressive Modeling: Scalable Image Generation vi...

引用

38th Conference on Neural Information Processing systems, NeurIPS 2024

作者： Tian, keyu Jiang, Yi Yuan, Zehuan Peng, Bingyue Wang, Liwei Center for Data Science Peking University China Bytedance Inc. China State Key Lab of General Artificial Intelligence School of Intelligence Science and Technology Peking University China

We present Visual AutoRegressive modeling (VAR), a new generation paradigm that redefines the autoregressive learning on images as coarse-to-fine "next-scale prediction" or "next-resolution prediction", diverging from the standard raster-scan "next-token prediction". This simple, intuitive methodology allows autoregressive (AR) transformers to learn visual distributions fast and can generalize well: VAR, for the first time, makes GPT-style AR models surpass diffusion transformers in image generation. On ImageNet 256×256 benchmark, VAR significantly improve AR baseline by improving Fréchet inception distance (FID) from 18.65 to 1.73, inception score (IS) from 80.4 to 350.2, with 20× faster inference speed. It is also empirically verified that VAR outperforms the Diffusion Transformer (DiT) in multiple dimensions including image quality, inference speed, data efficiency, and scalability. Scaling up VAR models exhibits clear power-law scaling laws similar to those observed in LLMs, with linear correlation coefficients near −0.998 as solid evidence. VAR further showcases zero-shot generalization ability in downstream tasks including image in-painting, out-painting, and editing. These results suggest VAR has initially emulated the two important properties of LLMs: Scaling Laws and zero-shot generalization. We have released all models and codes to promote the exploration of AR/VAR models for visual generation and unified learning. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

3D printed-electrospun PCL/hydroxyapatite/MWCNTs scaffolds for the repair of subchondral bone

引用

Regenerative Biomaterials 2023年第1期10卷 294-305页

作者： Yanyan Cao Lei Sun Zixian Liu Zhizhong Shen Wendan Jia Peiyi Hou Shengbo Sang College of Information Science and Engineering Hebei North UniversityZhangjiakou 075000China Shanxi Key Laboratory of Micro Nano Sensors&Artificial Intelligence Perception College of Information and ComputerTaiyuan University of TechnologyTaiyuan 030024China Key Lab of Advanced Transducers and Intelligent Control System of the Ministry of Education Taiyuan University of TechnologyTaiyuan 030024China Shanxi Research Institute of 6D Artificial Intelligence Biomedical Science Taiyuan 030031China

Osteochondral defect caused by trauma or osteoarthritis exhibits a major challenge in clinical treatment with limited symptomatic effects at *** regeneration and remodeling of subchondral bone play a positive effect on cartilage regeneration and further promotes the repair of osteochondral *** use of the strengths of each preparation method,the combination of 3D printing and electrospinning is a promising method for designing and constructing multi-scale scaffolds that mimic the complexity and hierarchical structure of subchondral bone at the microscale and nanoscale,*** this study,the 3D printed-electrospun poly(ɛ-caprolactone)/nano-hydroxyapatites/multi-walled carbon nanotubes(PCL/nHA/MWCNTs)scaffolds were successfully constructed by the combination of electrospinning and layer-by-layer 3D *** resulting dual-scale scaffold consisted of a dense layer of disordered nanospun fibers and a porous microscale 3D scaffold layer to support and promote the ingrowth of subchondral ***,the biomimetic PCL/nHA/MWCNTs scaffolds enhanced cell seeding efficiency and allowed for higher cell-cell interactions that supported the adhesion,proliferation,activity,morphology and subsequently improved the osteogenic differentiation of bone marrow mesenchymal stem cells in ***,this study elucidates that the construction of 3D printed-electrospun PCL/nHA/MWCNTs scaffolds provides an alternative strategy for the regeneration of subchondral bone and lays a foundation for subsequent in vivo studies.

关键词： additive manufacturing 3D printing electrospinning subchondral bone

来源：评论

学校读者我要写书评

暂无评论

Cryogenic Electrical Tree Characteristics of Epoxy Resin for HTS Power Equipment under DC/Impulse Superimposed Voltage

引用

IEEE Transactions on Dielectrics and Electrical Insulation 2024年第3期32卷 1422-1431页

作者： Xing, Yunqi Xiao, Kunran Zhao, Yuqiang Huang, Rongjin Zheng, Jingquan Hebei University of Technology State Key Laboratory of Reliability and Intelligence of Electrical Equipment Tianjin300131 China Bingtuan Xingxin Vocational and Technical College Urumqi830074 China Chinese Academy of Sciences Key Laboratory of Cryogenic Science and Technology Technical Institute of Physics and Chemistry Beijing100190 China North China Electric Power University State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources Beijing102206 China

Epoxy resin for current lead insulation in superconducting equipment offers advantages such as low costs, high chemical stability, and excellent electrical and insulation properties. However, during operation, the combined effects of complex voltage and a wide temperature range from room temperature to 77 K can easily induce partial discharge, leading to insulation faults and posing a threat to the safety and stability of the power system. In this work, we conducted electrical tree tests on bisphenol F epoxy resin to investigate the influence of environmental temperature, voltage forms, impulse frequency, and other factors on the inception and growth characteristics of electrical tree. The results indicate that low temperature can effectively inhibit the inception and growth of electrical tree in epoxy resin. Continuous DC voltage application affects traps, making superimposed voltage more likely to promote electrical tree growth than a single impulse voltage at 300 K. The impulse voltage component dominates in the superimposed voltage, and its polarity significantly affects electrical tree characteristics, though the mechanisms differ. Additionally, the form of voltage superposition influences electrical tree characteristics. The promotion effect of heteropolar superposition voltage on electrical tree is slightly lower than that of homopolar superposition voltage, but the influence is not as obvious as that of positive and negative polarity. © 1994-2012 IEEE.

关键词： Chemical equipment

来源：评论

学校读者我要写书评

暂无评论

The MINETRANS systems for IWSLT 2023 Offline Speech Translation and Speech-to-Speech Translation Tasks 20

The MINETRANS Systems for IWSLT 2023 Offline Speech Translat...

引用

20th International Conference on Spoken Language Translation, IWSLT 2023

作者： Du, Yichao Guo, Zhengsheng Tian, Jinchuan Zhang, Zhirui Wang, Xing Yu, Jianwei Tu, Zhaopeng Xu, Tong Chen, Enhong University of Science and Technology of China Tencent AI Lab China State Key Laboratory of Cognitive Intelligence China

ISBN: (纸本)9781959429845

This paper presents the MINETRANS English-to-Chinese speech translation systems developed for two challenge tracks of IWSLT 2023: Offline Speech Translation (S2T) and Speech-to-Speech Translation (S2ST). For the offline S2T track, MINETRANS employs a practical cascaded system consisting of automatic speech recognition (ASR) and machine translation (MT) modules to explore translation performance limits in both constrained and unconstrained settings. To this end, we investigate the effectiveness of multiple ASR architectures and two MT strategies, i.e., supervised in-domain fine-tuning and prompt-driven translation using ChatGPT. For the S2ST track, we propose a novel speech-to-unit translation (S2UT) framework to build an end-to-end system, which encodes the target speech as discrete units via our trained HuBERT and leverages the standard sequence-to-sequence model to learn the mapping between source speech and discrete units directly. We demonstrate that with a large-scale dataset, such as 10,000 hours of training data, this approach can well handle the mapping without any auxiliary recognition tasks (i.e., ASR and MT tasks). To the best of our knowledge, we are the first and only one to successfully train and submit the end-to-end S2ST model on this challenging track. © IWSLT *** rights reserved.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Nonlocal Huygens'meta-lens for high-qualityfactor spin-multiplexing imaging

引用

Light(Science & Applications) 2025年第3期14卷 695-702页

作者： Jin Yao Yubin Fan Yunhui Gao Rong Lin Zhihui Wang Mu Ku Chen Shumin Xiao Din Ping Tsai Department of Electrical Engineering City University of Hong KongKowloonHong Kong SARChina Centre for Biosystems Neuroscienceand NanotechnologyCity University of Hong KongKowloonHong Kong SARChina State Key Laboratory of Terahertz and Milimeter Waves City University of Hong KongKowloonHong Kong SARChina State Key Laboratory on Tunable Laser Technology Ministry of Industry and Information Technology Key Lab of Micro-Nano Optoelectronic Information SystemShenzhen Graduate SchoolHarbin Institute of TechnologyShenzhen 518055China Pengcheng Laboratory ShenzhenChina

Combining bright-feld and edge-enhanced imaging affords an effective avenue for extracting complex morphological information from objects,which is particularly beneficial for biological *** metalenses present promising candidates for achieving this ***,current multiplexing meta-lenses lack spectral modulation,and crosstalk between different wavelengths hampers the imaging quality,especilly for biological samples requiring precise wavelength ***,we experimentally demonstrate the nonlocal Huygens'meta-lens for high-quality-factor spin-multiplexing ***-bound states in the continuum(q-BlCs)are excited to provide a high quality factor of 90 and incident-angle *** generalized Kerker condition,driven by Fano-like interactions between q-BIC and in-plane Mie resonances,breaks the radiation symmetry,resulting in a transmission peak with a geometric phase for polarization-converted light,while unconverted light exhibits a transmission dip without a geometric *** polarization conversion efficiency of 65%is achieved,accompanied by a minimal unconverted value,surpassing the theoretical limit of traditional thin nonlocal *** these effects,the output polarization-converted state exhibits an efficient wavelengthselective focusing phase *** unconverted counterpart serves as an effective spatial frequency filter based on incident-angular dispersion,passing high-frequency edge ***-field imaging and edge detection are thus presented under two output spin *** work provides a versatile framework for nonlocal metasurfaces,boosting biomedical imaging and sensing applications.

关键词： nonlocal Huygensmeta lens biological imagingmultiplexing metalenses bright field imaging edge enhanced imaging high quality factor spin multiplexing imaging extracting complex morphological information biological samples spectral modulationand

来源：评论

学校读者我要写书评

暂无评论

FEEL-SNN: Robust Spiking Neural Networks with Frequency Encoding and Evolutionary Leak Factor 38

FEEL-SNN: Robust Spiking Neural Networks with Frequency Enco...

引用

38th Conference on Neural Information Processing systems, NeurIPS 2024

作者： Xu, Mengting Ma, De Tang, HuaJin Zheng, Qian Pan, Gang The State Key Lab of Brain-Machine Intelligence Zhejiang University Hangzhou China College of Computer Science and Technology Zhejiang University Hangzhou China

Currently, researchers think that the inherent robustness of spiking neural networks (SNNs) stems from their biologically plausible spiking neurons, and are dedicated to developing more bio-inspired models to defend attacks. However, most work relies solely on experimental analysis and lacks theoretical support, and the direct-encoding method and fixed membrane potential leak factor they used in spiking neurons are simplified simulations of those in the biological nervous system, which makes it difficult to ensure generalizability across all datasets and networks. Contrarily, the biological nervous system can stay reliable even in a highly complex noise environment, one of the reasons is selective visual attention and non-fixed membrane potential leaks in biological neurons. This biological finding has inspired us to design a highly robust SNN model that closely mimics the biological nervous system. In our study, we first present a unified theoretical framework for SNN robustness constraint, which suggests that improving the encoding method and evolution of the membrane potential leak factor in spiking neurons can improve SNN robustness. Subsequently, we propose a robust SNN (FEEL-SNN) with Frequency Encoding (FE) and Evolutionary Leak factor (EL) to defend against different noises, mimicking the selective visual attention mechanism and non-fixed leak observed in biological systems. Experimental results confirm the efficacy of both our FE, EL, and FEEL methods, either in isolation or in conjunction with established robust enhancement algorithms, for enhancing the robustness of SNNs. Our code is available at https://***/zju-bmi-lab/FEEL_SNN. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Vision-Language Navigation with Energy-Based Policy 38

Vision-Language Navigation with Energy-Based Policy

引用

38th Conference on Neural Information Processing systems, NeurIPS 2024

作者： Liu, Rui Wang, Wenguan Yang, Yi The State Key Lab of Brain-Machine Intelligence Zhejiang University Hangzhou China College of Computer Science and Technology Zhejiang University Hangzhou China

Vision-language navigation (VLN) requires an agent to execute actions following human instructions. Existing VLN models are optimized through expert demonstrations by supervised behavioural cloning or incorporating manual reward engineering. While straightforward, these efforts overlook the accumulation of errors in the Markov decision process, and struggle to match the distribution of the expert policy. Going beyond this, we propose an Energy-based Navigation Policy (ENP) to model the joint state-action distribution using an energy-based model. At each step, low energy values correspond to the state-action pairs that the expert is most likely to perform, and vice versa. Theoretically, the optimization objective is equivalent to minimizing the forward divergence between the occupancy measure of the expert and ours. Consequently, ENP learns to globally align with the expert policy by maximizing the likelihood of the actions and modeling the dynamics of the navigation states in a collaborative manner. With a variety of VLN architectures, ENP achieves promising performances on R2R, REVERIE, RxR, and R2R-CE, unleashing the power of existing VLN models. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MemoryFormer: Minimize Transformer Computation by Removing Fully-Connected Layers 38

MemoryFormer: Minimize Transformer Computation by Removing F...

引用

38th Conference on Neural Information Processing systems, NeurIPS 2024

作者： Ding, Ning Tang, Yehui Qin, Haochen Zhou, Zhenli Xu, Chao Li, Lin Han, Kai Liao, Heng Wang, Yunhe State Key Lab of General AI School of Intelligence Science and Technology Peking University China Huawei Noah's Ark Lab Canada Huawei HiSilicon China

In order to reduce the computational complexity of large language models, great efforts have been made to to improve the efficiency of transformer models such as linear attention and flash-attention. However, the model size and corresponding computational complexity are constantly scaled up in pursuit of higher performance. In this work, we present MemoryFormer, a novel transformer architecture which significantly reduces the computational complexity (FLOPs) from a new perspective. We eliminate nearly all the computations of the transformer model except for the necessary computation required by the multi-head attention operation. This is made possible by utilizing an alternative method for feature transformation to replace the linear projection of fully-connected layers. Specifically, we first construct a group of in-memory lookup tables that store a large amount of discrete vectors to replace the weight matrix used in linear projection. We then use a hash algorithm to retrieve a correlated subset of vectors dynamically based on the input embedding. The retrieved vectors combined together will form the output embedding, which provides an estimation of the result of matrix multiplication operation in a fully-connected layer. Compared to conducting matrix multiplication, retrieving data blocks from memory is a much cheaper operation which requires little computations. We train MemoryFormer from scratch and conduct extensive experiments on various benchmarks to demonstrate the effectiveness of the proposed model. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

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：