检索结果-内蒙古大学图书馆

38th Conference on Neural information processing Systems, NeurIPS 2024

作者： Wen, Zhuofan Gui, Shangtong Feng, Yang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences China Key Laboratory of Al Safety Chinese Academy of Sciences China University of Chinese Academy of Sciences Beijing China

Inference acceleration of large language models (LLMs) has been put forward in many application scenarios and speculative decoding has shown its advantage in addressing inference acceleration. Speculative decoding usually introduces a draft model to assist the base LLM where the draft model produces drafts and the base LLM verifies the draft for acceptance or rejection. In this framework, the final inference speed is decided by the decoding speed of the draft model and the acceptance rate of the draft provided by the draft model. Currently the widely used draft models usually generate draft tokens for the next several positions in a non-autoregressive way without considering the correlations between draft tokens. Therefore, it has a high decoding speed but an unsatisfactory acceptance rate. In this paper, we focus on how to improve the performance of the draft model and aim to accelerate inference via a high acceptance rate. To this end, we propose a CTC-based draft model which strengthens the correlations between draft tokens during the draft phase, thereby generating higher-quality draft candidate sequences. Experiment results show that compared to strong baselines, the proposed method can achieve a higher acceptance rate and hence a faster inference speed. © 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

Interference-assisted kaleidoscopic meta-plexer for arbitrary spin-wavefront manipulation

引用

Light(Science & Applications) 2019年第1期8卷 1141-1150页

作者： He-Xiu Xu Guangwei Hu Ying Li Lei Han Jianlin Zhao Yunming Sun Fang Yuan Guang-Ming Wang Zhi Hao Jiang Xiaohui Ling Tie Jun Cui Cheng-Wei Qiu Department of Electrical and Computer Engineering National University of SingaporeSingapore 117583Singapore Air and Missile Defense College Air force Engineering University710051 Xi’anChina Hunan Provincial Key Laboratory of Intelligent Information Processing and Applications College of Physics and Electronics EngineeringHengyang Normal University421008 HengyangChina School of Natural and Applied Sciences Northwestern Polytechnical University710072 Xi’anChina Advanced Technique Department Key Lab of Aeronautics Computing Technique710075 Xi’anChina State Key Laboratory of Millimeter Waves Southeast University210096 NanjingChina

Achieving simultaneous polarization and wavefront control,especially circular polarization with the auxiliary degree of freedom of light and spin angular momentum,is of fundamental importance in many optical *** are typically undesirable in highly integrated photonic circuits and ***,we propose an interference-assisted metasurface-multiplexer(meta-plexer)that counterintuitively exploits constructive and destructive interferences between hybrid meta-atoms and realizes independent spin-selective wavefront *** kaleidoscopic meta-plexers are experimentally demonstrated via two types of single-layer spinwavefront multiplexers that are composed of spatially rotated anisotropic *** type generates a spinselective Bessel-beam wavefront for spin-down light and a low scattering cross-section for stealth for spin-up *** other type demonstrates versatile control of the vortex wavefront,which is also characterized by the orbital angular momentum of light,with frequency-switchable numbers of beams under linearly polarized wave *** findings offer a distinct interference-assisted concept for realizing advanced multifunctional photonics with arbitrary and independent spin-wavefront features.A variety of applications can be readily anticipated in optical diodes,isolators,and spin-Hall meta-devices without cascading bulky optical elements.

关键词： arbitrary momentum versatile

来源：评论

学校读者我要写书评

暂无评论

A sample pre-mapping method enhancing boosting for object detection

A sample pre-mapping method enhancing boosting for object de...

引用

International Conference on Pattern Recognition

作者： Ren, Haoyu Hong, Xiaopeng Heng, Cher-Keng Liang, Luhong Chen, Xilin Key Lab. of Intelligent Information Processing of Chinese Academy of Sciences Institute of Computing Technology CAS China School of Computer Science and Technology Harbin Institute of Technology Panasonic Singapore Laboratories Pte Ltd.

ISBN: (纸本)9780769541099

We propose a novel method to improve the training efficiency and accuracy of boosted classifiers for object detection. The key step of the proposed method is a sample pre-mapping on original space by referring to the selected 'reference sample' before feeding into weak classifiers. The reference sample corresponds to an approximation of the optimal separating hyper-plane in an implicit high-dimensional space, so that the resulting classifier could achieve the performance similar to kernel method, while spending the computation cost of linear classifier in both training and detection. We employ two different non-linear mappings to verify the proposed method under boosting framework. Experimental results show that the proposed approach achieves performance comparable with the common-used methods on public datasets in both pedestrian detection and car detection. © 2010 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Boosted sigma set for pedestrian detection

Boosted sigma set for pedestrian detection

引用

International Conference on Pattern Recognition

作者： Hong, Xiaopeng Chang, Hong Chen, Xilin Gao, Wen School of Computer Science and Technology Harbin Institute of Technology China Key Lab. of Intelligent Information Processing Chinese Academy of Sciences Institute of Computing Technology China Institute of Digital Media Peking University China

ISBN: (纸本)9780769541099

This paper presents a new method to detect pedestrian in still image using Sigma sets as image region descriptors in the boosting framework. Sigma set encodes second order statistics of an image region implicitly in the form of a point set. Compared with the covariance matrix, the traditional second order statistics based region descriptor, which requires computationally demanding operations based on Riemannian manifold, Sigma set preserves similar robustness and discriminative power more efficiently because the classification on Sigma sets can be directly performed in vector space. Experimental results on the INRIA and the Daimler Chrysler pedestrian datasets show the effectiveness and efficiency of the proposed method. © 2010 IEEE.

关键词： Covariance matrix

来源：评论

学校读者我要写书评

暂无评论

A Low SAR, Small size, High gain, Circularly polarized Antenna for Wearable Application 2

A Low SAR, Small size, High gain, Circularly polarized Anten...

引用

2020 2nd International Conference on Artificial Intelligence Technologies and Application, ICAITA 2020

作者： Wang, Chao Zhang, Liang Cheng, Yi Li, XueMei Wu, Xianliang Key Lab of Ministry of Education of Intelligent Computing and Signal Processing Anhui University Hefei Anhui230601 China AnHui Province Key Laboratory of Simulation and Design for Electronic Information System Hefei Normal University Hefei Anhui230601 China

A planar, small size, high gain, low specific absorption rate (SAR) and circularly-polarized (CP) wearable antenna is proposed in this paper. The antenna is fabricated on a substrate with a dielectric constant of 3.5 with a thickness of 0.5 mm and sized at 42×42 mm only. Both the simulation results show that the overlap bandwidth of impedance and axial ratio of the proposed antenna is 13.7% (5.15-5.91 GHz). To isolate the antenna against the influence of the human body, a artificial magnetic conductor (AMC) plane is added on the reverse side of the radiator. The AMC structure effectively isolates the human body from the radiation of the antenna and reduces the specific absorption rate (SAR) of it by more than 96.1% at 5.5 GHz, which improves the antenna gain and the peak gain reaches 5.09 dBi at 5.5 GHz. The wearable performance of the antenna was analyzed, and it is observed that it can sustain good performance even under human body loading. Beside, the antenna has a small size, which makes it ideal for wearable applications. © 2020 Published under licence by IOP Publishing Ltd.

关键词： Wearable antennas

来源：评论

学校读者我要写书评

暂无评论

Automatic adaptation of annotation standards: Chinese word segmentation and POS tagging - A case study

Automatic adaptation of annotation standards: Chinese word s...

引用

Joint Conference of the 47th Annual Meeting of the Association for Computational Linguistics and 4th International Joint Conference on Natural Language processing of the AFNLP, ACL-IJCNLP 2009

作者： Jiang, Wenbin Huang, Liang Liu, Qun Key Lab. of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences P.O. Box 2704 Beijing 100190 China Google Research 1350 Charleston Rd. Mountain View CA 94043 United States

ISBN: (纸本)9781617382581

Manually annotated corpora are valuable but scarce resources, yet for many annotation tasks such as treebanking and sequence labeling there exist multiple corpora with different and incompatible annotation guidelines or standards. This seems to be a great waste of human efforts, and it would be nice to automatically adapt one annotation standard to another. We present a simple yet effective strategy that transfers knowledge from a differently annotated corpus to the corpus with desired annotation. We test the efficacy of this method in the context of Chinese word segmentation and part-of-speech tagging, where no segmentation and POS tagging standards are widely accepted due to the lack of morphology in Chinese. Experiments show that adaptation from the much larger People's Daily corpus to the smaller but more popular Penn Chinese Treebank results in significant improvements in both segmentation and tagging accuracies (with error reductions of 30.2% and 14%, respectively), which in turn helps improve Chinese parsing accuracy. © 2009 ACL and AFNLP.

关键词： Forestry

来源：评论

学校读者我要写书评

暂无评论

Pushing scientific documents by discovering interest in information flow within E-science knowledge grid

引用

4th International Conference on Grid and Cooperative computing - GCC 2005

作者： Ding, Lianhong Li, Xiang Xing, Yunpeng Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China Graduate School of Chinese Academy of Sciences 100080 Beijing China Hunan Knowledge Grid Lab. Hunan University of Science and Technology Hunan China

ISBN: (纸本)3540305106

The Knowledge Grid is an intelligent and sustainable Internet application environment that enables people and roles to effectively capture, publish, share and manage explicit knowledge resources. As an important function of the e-Science Knowledge Grid, this paper proposes an approach to effectively push scientific documents within research teams by detecting the social characteristics in self-organized network, discovering interest in information flow, and capturing dynamic changes of interests over time. The proposed approach can be used in any cooperative organizations. © Springer-Verlag Berlin Heidelberg 2005.

关键词： information analysis

来源：评论

学校读者我要写书评

暂无评论

Collaborating semantic link network with resource space model

引用

4th International Conference on Grid and Cooperative computing - GCC 2005

作者： Xing, Yunpeng Liu, Jie Sun, Xiaoping Yao, Erlin Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100080 China Graduate School Chinese Academy of Sciences Beijing China Hunan Knowledge Grid Lab. Hunan University of Science and Technology Hunan China

ISBN: (纸本)3540305106

The Semantic Link Network model SLN and Resource Space Model RSM are semantic models proposed separately for effectively specifying and managing versatile resources across the Internet. Collaborating the relational semantics of SLN with the classification semantics of the RSM can support richer semantic modeling in applications. This paper introduces the Resource Class Hierarchies into the SLN and investigates to cooperatively model with the RSM. The proposed approach can be used as a normalized semantic overlay of the Knowledge Grid environment. © Springer-Verlag Berlin Heidelberg 2005.

关键词： Mathematical models

来源：评论

学校读者我要写书评

暂无评论

How to Train Your Neural Network for Molecular Structure Generation from Mass Spectra?

How to Train Your Neural Network for Molecular Structure Gen...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Zhao, Kai Liu, Yanmin Dian, Longyang Sun, Shiwei Cui, Xuefeng Shandong University School of Computer Science and Technology Qingdao China Shandong University State Key Laboratory of Microbial Technology Qingdao China Chinese Academy of Sciences Key Lab of Intelligent Information Processing Institute of Computing Technology Beijing China

ISBN: (纸本)9798350386226

Mass spectrometry serves as a pivotal tool for the analysis of small molecules through an examination of their mass-to-charge ratios. Recent advancements in deep learning have markedly enhanced the analysis of mass spectrometric data, facilitating the prediction of novel small molecule structures without the necessity of extensive databases. Nonetheless, the paucity of annotated datasets impedes the efficacious training of molecular generation models predicated on MS2 spectra. To mitigate this limitation, we introduce ctMSNovelist, an avant-garde method that amalgamates pre-training, fine-tuning, and co-training techniques to construct a more precise model for the generation of molecular structures from tandem mass spectrometry data. This novel approach augments both the training regimen and the predictive accuracy of the MSNovelist model, thereby surmounting the obstacle of limited data. The methodology commences with the pretraining of a Variational Autoencoder (VAE) to generate molecular fingerprints derived from SMILES strings. Subsequently, it undergoes fine-tuning to emulate noisy fingerprints originating from mass spectrometry (MS) data. Concurrently, MSNovelist is co-trained utilizing these simulated fingerprints, inclusive of the highly noisy variants produced in the early stages of VAE training. The incorporation of a substantial volume of noisy data serves to enhance model accuracy and avert overfitting. We evaluated ctMSNovelist using the GNPS dataset and attained a SMILES prediction accuracy of 48.8%, representing a 4.1% enhancement over MSNovelist. It is pertinent to note that the sole distinction between ctMSNovelist and MSNovelist in this experiment was the training process. The code and models are publicly available at https://***/xfcui/ctMSNovelist. © 2024 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

A prompt-based approach to adversarial example generation and robustness enhancement

引用

Frontiers of Computer Science 2024年第4期18卷 85-96页

作者： Yuting YANG Pei HUANG Juan CAO Jintao LI Yun LIN Feifei MA Key Lab of Intelligent Information Processing of Chinese Academy of Sciences(CAS) Institute of Computing TechnologyCASBeijing 100190China School of Computer Science and Technology University of Chinese Academy of SciencesBeijing 100049China Department of Computer Science Stanford UniversityCA 94305USA School of Computing National University of SingaporeSingapore 119077Singapore Laboratory of Parallel Software and Computational Science Institute of SoftwareChinese Academy of SciencesBeijing 100190China

Recent years have seen the wide application of natural language processing(NLP)models in crucial areas such as finance,medical treatment,and news media,raising concerns about the model robustness and *** find that prompt paradigm can probe special robust defects of pre-trained language *** prompt texts are first constructed for inputs and a pre-trained language model can generate adversarial examples for victim models via *** results show that prompt paradigm can efficiently generate more diverse adversarial examples besides synonym ***,we propose a novel robust training approach based on prompt paradigm which incorporates prompt texts as the alternatives to adversarial examples and enhances robustness under a lightweight minimax-style optimization *** on three real-world tasks and two deep neural models show that our approach can significantly improve the robustness of models to resist adversarial attacks.

关键词： robustness adversarial example prompt learning pre-trained language model

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：