检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Gu, Yuxian Dong, Li Wei, Furu Huang, Minlie The CoAI Group DCST Institute for Artificial Intelligence State Key Lab of Intelligent Technology and Systems Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China Microsoft Research

In-context learning, where pre-trained language models learn to perform tasks from task examples and instructions in their contexts, has attracted much attention in the NLP community. However, the ability of in-context learning is not fully exploited because language models are not explicitly trained to learn in context. To this end, we propose PICL (Pre-training for In-Context Learning), a framework to enhance the language models' in-context learning ability by pre-training the model on a large collection of "intrinsic tasks" in the general plain-text corpus using the simple language modeling objective. PICL encourages the model to infer and perform tasks by conditioning on the contexts while maintaining task generalization of pre-trained models. We evaluate the in-context learning performance of the model trained with PICL on seven widely-used text classification datasets and the SUPERNATURALINSTRCTIONS benchmark, which contains 100+ NLP tasks formulated to text generation. Our experiments show that PICL is more effective and task-generalizable than a range of baselines, outperforming larger language models with nearly 4x parameters. The code is publicly availab.e at https://***/thu-coai/PICL. © 2023, CC BY.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

One-Shot Three-Dimensional Measurement Based on Spectral Interferometry Using a Digital Micromirror Device

One-Shot Three-Dimensional Measurement Based on Spectral Int...

引用

Pacific Rim Conference on Lasers and Electro-Optics (CLEO/Pacific Rim)

作者： Jinxu Zhang Liheng Shi Yingying Gu Donglai Zhang Lu Yin Guanhao Wu Department of Precision Instrument State Key Laboratory of Precision Measurement Technology and Instruments Tsinghua University Beijing China Space Optoelectronic Measurement and Perception Lab. Beijing Institute of Control Engineering Beijing China National Key Laboratory of Space Intelligent Control China Academy of Space Technology Beijing China

We present a one-shot 3D spectral interferometry technique using a digital micromirror device. By encoding the distribution of the spatial light field, this approach enables 3D imaging of step structures within 27 ms.

ISBN: (数字)9798350372076

ISBN: (纸本)9798350372083

关键词： Optical interferometry Three-dimensional displays Imaging Surface emitting lasers Measurement by laser beam Encoding Microcavities

来源：评论

学校读者我要写书评

暂无评论

Electromagnetic Property Sensing and Channel Reconstruction Based on Diffusion Schrödinger Bridge in ISAC

arXiv

引用

arXiv 2024年

作者： Jiang, Yuhua Gao, Feifei Jin, Shi State Key Lab of Intelligent Technologies and Systems Tsinghua University Beijing National Research Center for Information Science and Technology [BNRist Beijing China The National Mobile Communications Research Laboratory Southeast University Nanjing210096 China

Integrated sensing and communications (ISAC) has emerged as a transformative paradigm for next-generation wireless systems. In this paper, we present a novel ISAC scheme that leverages the diffusion Schrödinger bridge (DSB) to realize the sensing of electromagnetic (EM) property of a target as well as the reconstruction of the wireless channel. The DSB framework connects EM property sensing and channel reconstruction by establishing a bidirectional process: the forward process transforms the distribution of EM property into the channel distribution, while the reverse process reconstructs the EM property from the channel. To handle the difference in dimensionality between the high-dimensional sensing channel and the lower-dimensional EM property, we generate latent representations using an autoencoder network. The autoencoder compresses the sensing channel into a latent space that retains essential features, which incorporates positional embeddings to process spatial context. The simulation results demonstrate the effectiveness of the proposed DSB framework, which achieves superior reconstruction of the targets shape, relative permittivity, and conductivity. Moreover, the proposed method can also realize high-fidelity channel reconstruction given the EM property of the target. The dual capability of accurately sensing the EM property and reconstructing the channel across various positions within the sensing area underscores the versatility and potential of the proposed approach for broad application in future ISAC systems. Copyright © 2024, The Authors. All rights reserved.

关键词： Signal reconstruction

来源：评论

学校读者我要写书评

暂无评论

Guest Editorial: Ubiquitous Intelligence for Internet of Vehicles

引用

IEEE Internet of Things Magazine 2023年第3期6卷 52-54页

作者： Peng, Haixia Cheng, Nan Ye, Qiang Fang, He Yan, Shen Choo, Kim-Kwang Raymond Duong, Trung Q. California State University Long Beach Department of Computer Engineering and Computer Science Long BeachCA United States School of Telecommunications Engineering Xidian University State Key Lab. of ISN Shaanxi China Memorial University of Newfoundland Department of Computer Science NL Canada Soochow University China Intelligent Automotive Solution BU Huawei Technologies Co. Ltd Policy Standard & Patent Dept. China The University of Texas at San Antonio Cloud Technology Endowed United States Royal Academy of Engineering Queen's University Belfast United Kingdom

As one of the prominent networking paradigms in the realm of the Internet of Things (IoT), the Internet of Vehicles (IoV) facilitates seamless information dissemination and task processing among vehicles equipped with onboard sensing, communication, computing, and storage capabilities. With the advancements in artificial intelligence (AI) techniques, there is a vision to achieve pervasive intelligence within the IoV ecosystem. Various network entities, including connected vehicles, wireless base stations, edge/cloud servers, and aerial/space-assisted devices (such as drones and satellites), are expected to interact efficiently to perceive, reason, and make intelligent decisions based on contextual awareness. These advancements aim to enhance networking and computing effectiveness. The realization of an intelligent, safe, and ubiquitous IoV heavily relies on highly responsive task computing, adaptive networking, and efficient resource control to meet the increasingly diverse requirements of vehicular applications.

关键词： Special issues and sections Internet of Vehicles intelligent systems Ubiquitous computing

来源：评论

学校读者我要写书评

暂无评论

DA-Ada: Learning Domain-Aware Adapter for Domain Adaptive Object Detection

arXiv

引用

arXiv 2024年

作者： Li, Haochen Zhang, Rui Yao, Hantao Zhang, Xin Hao, Yifan Song, Xinkai Li, Xiaqing Zhao, Yongwei Li, Ling Chen, Yunji Intelligent Software Research Center Institute of Software CAS Beijing China State Key Lab of Processors Institute of Computing Technology CAS Beijing China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation CAS Beijing China University of Chinese Academy of Sciences Beijing China

Domain adaptive object detection (DAOD) aims to generalize detectors trained on an annotated source domain to an unlab.lled target domain. As the visual-language models (VLMs) can provide essential general knowledge on unseen images, freezing the visual encoder and inserting a domain-agnostic adapter can learn domain-invariant knowledge for DAOD. However, the domain-agnostic adapter is inevitably biased to the source domain. It discards some beneficial knowledge discriminative on the unlab.lled domain, ***-specific knowledge of the target domain. To solve the issue, we propose a novel Domain-Aware Adapter (DA-Ada) tailored for the DAOD task. The key point is exploiting domain-specific knowledge between the essential general knowledge and domain-invariant knowledge. DA-Ada consists of the Domain-Invariant Adapter (DIA) for learning domain-invariant knowledge and the Domain-Specific Adapter (DSA) for injecting the domain-specific knowledge from the information discarded by the visual encoder. Comprehensive experiments over multiple DAOD tasks show that DA-Ada can efficiently infer a domain-aware visual encoder for boosting domain adaptive object detection. Our code is availab.e at https://***/Therock90421/DA-Ada © 2024, CC BY-NC-SA.

关键词： Ada (programming language)

来源：评论

学校读者我要写书评

暂无评论

High responsivity and flexible deep-UV phototransistor based on Ta-doped β-Ga_(2)O_(3)

引用

npj Flexible Electronics 2022年第1期6卷 457-465页

作者： Xiao-Xi Li Guang Zeng Yu-Chun Li Hao Zhang Zhi-Gang Ji Ying-Guo Yang Man Luo Wei-Da Hu David Wei Zhang Hong-Liang Lu State Key Laboratory of ASIC and System Shanghai Institute of Intelligent Electronics&SystemsSchool of MicroelectronicsFudan University200433 ShanghaiChina National Key Laboratory of Science and Technology on Micro/Nano Fabrication Shanghai Jiao Tong University200240 ShanghaiChina Shanghai Synchrotron Radiation Facility(SSRF) Zhangjiang LabShanghai Advanced Research Institute&Shanghai Institute of Applied PhysicsChinese Academy of Sciences201204 ShanghaiChina State Key Laboratory of Infrared Physics Shanghai Institute of Technical PhysicsChinese Academy of Sciences200083 ShanghaiChina

Deep-ultraviolet(DUV)phototransistors have shown great potential applications in UV imaging,artificial intelligence,and wearable *** a large number of wide bandgap semiconductors,the quasi-two-dimensionalβ-Ga_(2)O_(3) is considered as an ideal candidate for DUV photodetector ***,we report a high responsivity(R)and fully flexible Ta-dopedβ-Ga_(2)O_(3) DUV phototransistor which exhibits outstanding optoelectrical properties with a high R of 1.32×10^(6) A/W,a large detectivity of 5.68×10^(14) Jones,a great photo-to-dark current ratio of 1.10×10^(10)%,a high external quantum efficiency of 6.60×10^(8)%,and an ultra-fast response time of~3.50 ***,the flexible Ta-dopedβ-Ga_(2)O_(3) device also displays high reliability and mechanical flexibility that can sustain well after over 1×10^(4) bending ***,high-contrast imaging of UV light was obtained on the flexible DUV detector arrays,which can be efficiently trained and recognized by an artificial neural *** findings offer a perspective to develop wearable optoelectronics and UV imaging based on high-performance flexibleβ-Ga_(2)O_(3) DUV phototransistors,providing an inspiration for the future work in artificial intelligence and bionic robot fields.

关键词： transistor responsivity artificial

来源：评论

学校读者我要写书评

暂无评论

DecompEval: Evaluating Generated Texts as Unsupervised Decomposed Question Answering

arXiv

引用

arXiv 2023年

作者： Ke, Pei Huang, Fei Mi, Fei Wang, Yasheng Liu, Qun Zhu, Xiaoyan Huang, Minlie The CoAI Group DCST Institute for Artificial Intelligence State Key Lab of Intelligent Technology and Systems Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China Huawei Noah’s Ark Lab China

Existing evaluation metrics for natural language generation (NLG) tasks face the challenges on generalization ability and interpretability. Specifically, most of the well-performed metrics are required to train on evaluation datasets of specific NLG tasks and evaluation dimensions, which may cause over-fitting to task-specific datasets. Furthermore, existing metrics only provide an evaluation score for each dimension without revealing the evidence to interpret how this score is obtained. To deal with these challenges, we propose a simple yet effective metric called DecompEval. This metric formulates NLG evaluation as an instruction-style question answering task and utilizes instruction-tuned pre-trained language models (PLMs) without training on evaluation datasets, aiming to enhance the generalization ability. To make the evaluation process more interpretable, we decompose our devised instruction-style question about the quality of generated texts into the subquestions that measure the quality of each sentence. The subquestions with their answers generated by PLMs are then recomposed as evidence to obtain the evaluation result. Experimental results show that DecompEval achieves state-of-the-art performance in untrained metrics for evaluating text summarization and dialogue generation, which also exhibits strong dimension-level / task-level generalization ability and interpretability1 Copyright © 2023, The Authors. All rights reserved.

关键词： Quality control

来源：评论

学校读者我要写书评

暂无评论

A Novel Parameter-dependent Input Normalization-based Direct MRAC with Unknown Control Direction

A Novel Parameter-dependent Input Normalization-based Direct...

引用

IEEE Conference on Decision and Control

作者： Yizhou Gong Gilberto Pin Yanjun Zhang Yang Wang School of Information Science and Technology ShanghaiTech University Shanghai China Digital Technology Org. of Electrolux Italia S.p.A. Italy School of Automation Beijing Institute of Technology Beijing China State Key Lab of Automation Intelligent Unmanned Systems Beijing Institute of Technology Beijing China

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

In this paper, we endow the model reference adaptive control (MRAC) with a novel parameter-dependent input normalization (PIN) to completely eliminate the conventional assumption of the high-frequency gain. Specifically, neither the sign nor the prior knowledge of the upper or lower bounds is required. To this end, we resort to an error augmentation together with a smart design of an adaptive law with a dead zone operation. Global stability in the mean square sense is established with the conventional proof concepts of the augmented error approach. In this way, no persistent excitation requirement is required. Although the system in question is assumed to be unity-relative-degree, the proposed technique can be easily extended to systems of arbitrary relative degrees. Finally, compared with the Nussbaum function-based methods in a numerical experiment, we show that transient behavior in our method is significantly improved.

关键词： Hands Lower bound Upper bound Simulation Stability analysis Robustness Pins Transient analysis Numerical stability Oscillators

来源：评论

学校读者我要写书评

暂无评论

Gait Planning and Motion Control Based on Vrep Simulation for Quadruped Robot

Gait Planning and Motion Control Based on Vrep Simulation fo...

引用

WRC Symposium on Advanced Robotics and Automation (WRC SARA)

作者： Linqi Zhou Zhihua Chen Jun Liu Zhi Liu Yumeng Chen Liting Zhang key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition and MOE Key Lab of Nondestructive Testing Technology Nanchang Hangkong University Nanchang China State Key Laboratory of Intelligent Control and Decision of Complex Systems School of Automation Beijing Institute of Technology Beijing China

Gait planning of quadruped robots plays an important role in achieving less walking, including dynamic and static gait. In this article, a static and dynamic gait control method based on center of gravity stability margin is proposed. Firstly, the robot model and kinematics modeling are introduced. Secondly, the robot’s foot static and dynamic gait were planned and the foot trajectory was designed. Finally, two types of gait of the robot were simulated using Vrep simulation software, and the differences in stability and speed between the coordinated gait with speed and stability in the static and dynamic gait of a 12 degree of freedom robot were analyzed, verifying the effectiveness of the gait control method proposed in this paper.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Constructing Highly Inductive Contexts for Dialogue Safety through Controllab.e Reverse Generation WARNING: This paper contains model outputs which are offensive in nature

Constructing Highly Inductive Contexts for Dialogue Safety t...

引用

2022 Findings of the Association for Computational Linguistics: EMNLP 2022

作者： Zhang, Zhexin Cheng, Jiale Sun, Hao Deng, Jiawen Mi, Fei Wang, Yasheng Shang, Lifeng Huang, Minlie The CoAI Group DCST Tsinghua University Beijing100084 China Institute for Artificial Intelligence Tsinghua University Beijing100084 China State Key Lab of Intelligent Technology and Systems Tsinghua University Beijing100084 China Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China Huawei Noah's Ark Lab

Large pretrained language models can easily produce toxic or biased content, which is prohibitive for practical use. In order to detect such toxic generations, existing methods rely on templates, real-world data extraction, crowdsourcing workers, or automatic generation to construct adversarial contexts that are likely to induce toxic generations. However, what type of context is more likely to induce unsafe responses is still under-explored. In this paper, we identify that context toxicity and context category (e.g., profanity, insult, drugs, etc.) are two important factors to cause safety issues in response generation. Hence, we propose a method called reverse generation to construct adversarial contexts conditioned on a given response, with the flexibility to control category, toxicity level, and inductivity of the generated contexts. Via reverse generation, we augment the existing BAD dataset and construct a new dataset BAD+ which contains more than 120K diverse and highly inductive contexts in 12 categories. We test three popular pretrained dialogue models (Blender, DialoGPT, and Plato2) and find that BAD+ can largely expose their safety problems. Furthermore, we show that BAD+ can greatly enhance the safety of generation and reveal the key factors of safety improvement. Our code and dataset is availab.e at https://***/thu-coai/Reverse_Generation. © 2022 Association for Computational Linguistics.

关键词： Toxicity

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：