检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Su, Bonan Zhou, Li Feng, Yuan Ying, Mingsheng Department of Computer Science and Technology Tsinghua University Beijing China Key Laboratory of System Software Chinese Academy of Sciences State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China Centre for Quantum Software and Information University of Technology Sydney Ultimo Australia

We provide well-founded semantics for a quantum programming language Qwhile-hp with heap manipulations, where allocation statements follow a dirty pattern, meaning that newly allocated qubits can nondeterministically assume arbitrary initial states. To thoroughly characterize heap manipulations in the quantum setting, we develop a quantum BI-style logic that includes interpretations for separating implication (−∗) and separating conjunction (∗). We then adopt this quantum BI-style logic as an assertion language to reason about heap-manipulated quantum programs and present a quantum separation logic which is sound and relatively complete. Finally, we apply our framework to verify the correctness of various practical quantum programs and to prove the correct usage of dirty ancilla qubits. Copyright © 2024, The Authors. All rights reserved.

关键词： Qubits

来源：评论

学校读者我要写书评

暂无评论

Joint Mobile Edge Caching and Pricing: A Mean-Field Game Approach

Joint Mobile Edge Caching and Pricing: A Mean-Field Game App...

引用

International Conference on Data Engineering

作者： Yin Xu Xichong Zhang Mingjun Xiao Jie Wu An Liu Sheng Zhang School of Computer Science and Technology University of Science and Technology of China Hefei China Suzhou Institute for Advanced Research University of Science and Technology of China Suzhou China Department of Computer and Information Sciences Temple University Philadelphia USA School of Computer Science and Technology Soochow University Suzhou China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

In this paper, we investigate the competitive content placement problem in Mobile Edge Caching (MEC) systems, where Edge Data Providers (EDPs) cache appropriate contents and trade them with requesters at a suitable price. Most of the existing works ignore the complicated strategic and economic interplay between content caching, pricing, and content sharing. Therefore, we propose a joint Mean-Field Game framework for mobile edge Caching and Pricing (MFG-CP) in large-scale dynamic MEC systems, which can facilitate distributed optimal decision-making based on the mean-field game theory. Specifi-cally, we first formulate the competitive content placement issue among EDPs as a non-cooperative stochastic differential game. To significantly reduce the communication and computation complexity, we further devise a mean-field model to approximate the collective impact of all EDPs on caching, trading, and sharing, by which each EDP can quickly estimate some unknown information without considerable interactions. Then, we develop a distributed best response scheme based on iterative learning, enabling each EDP to solely customize its optimal caching strategy and pricing policy. Besides, we theoretically prove the existence of a unique MFG equilibrium. Finally, trace-driven simulations demonstrate the effectiveness of MFG-CP compared with some baselines.

关键词： Economics Computational modeling Stochastic processes Pricing Games Differential games Data engineering

来源：评论

学校读者我要写书评

暂无评论

MOS: Model Surgery for Pre-Trained Model-Based Class-Incremental Learning

arXiv

引用

arXiv 2024年

作者： Sun, Hai-Long Zhou, Da-Wei Zhao, Hanbin Gan, Le Zhan, De-Chuan Ye, Han-Jia School of Artificial Intelligence Nanjing University China National Key Laboratory for Novel Software Technology Nanjing University China College of Computer Science and Technology Zhejiang University China

Class-Incremental Learning (CIL) requires models to continually acquire knowledge of new classes without forgetting old ones. Despite Pre-trained Models (PTMs) have shown excellent performance in CIL, catastrophic forgetting still occurs as the model learns new concepts. Existing work seeks to utilize lightweight components to adjust the PTM, while the forgetting phenomenon still comes from parameter and retrieval levels. Specifically, iterative updates of the model result in parameter drift, while mistakenly retrieving irrelevant modules leads to the mismatch during inference. To this end, we propose MOdel Surgery (MOS) to rescue the model from forgetting previous knowledge. By training task-specific adapters, we continually adjust the PTM to downstream tasks. To mitigate parameter-level forgetting, we present an adapter merging approach to learn task-specific adapters, which aims to bridge the gap between different components while reserve task-specific information. Besides, to address retrieval-level forgetting, we introduce a training-free self-refined adapter retrieval mechanism during inference, which leverages the model’s inherent ability for better adapter retrieval. By jointly rectifying the model with those steps, MOS can robustly resist catastrophic forgetting in the learning process. Extensive experiments on seven benchmark datasets validate MOS’s state-of-the-art performance. Code is available at: https://***/sun-hailong/AAAI25-MOS Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

InCLET: Large Language Model In-context Learning can Improve Embodied Instruction-following 25

InCLET: Large Language Model In-context Learning can Improve...

引用

Proceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems

作者： Peng-Yuan Wang Jing-Cheng Pang Chen-Yang Wang Xuhui Liu Tian-Shuo Liu Si-Hang Yang Hong Qian Yang Yu National Key Laboratory for Novel Software Technology School of Artificial Intelligence Nanjing University & Polixir.ai Nanjing China National Key Laboratory for Novel Software Technology School of Artificial Intelligence Nanjing University Nanjing China Shanghai Institute of AI for Education and School of Computer Science and Technology East China Normal University Shanghai China

ISBN: (纸本)9798400714269

Natural language-conditioned reinforcement learning (NLC-RL) empowers embodied agent to complete various tasks following human instruction. However, the unbounded natural language examples still introduce much complexity for the agent that solves concrete RL tasks, which can distract policy learning from completing the task. Consequently, extracting effective task representation from human instruction emerges as the critical component of NLC-RL. While previous methods have attempted to address this issue by learning task-related representation using large language models (LLMs), they highly rely on pre-collected task data and require extra training procedure. In this study, we uncover the inherent capability of LLMs to generate task representations and present a novel method, in-context learning embedding as task representation (InCLET). InCLET is grounded on a foundational finding that LLM in-context learning using trajectories can greatly help represent tasks. We thus firstly employ LLM to imagine task trajectories following the natural language instruction, then use in-context learning of LLM to generate task representations, and finally aggregate and project into a compact low-dimensional task representation. This representation is then used to train a human instruction-following agent. We conduct experiments on various embodied control environments and results show that InCLET creates effective task representations. Furthermore, this representation can significantly improve the RL training efficiency, compared to the baseline methods.

关键词： embodiment agent

来源：评论

学校读者我要写书评

暂无评论

AdvMask: A Sparse Adversarial Attack Based Data Augmentation Method for Image Classification

arXiv

引用

arXiv 2022年

作者： Yang, Suorong Li, Jinqiao Zhao, Jian Shen, Furao State Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing University Nanjing210023 China The State Key Laboratory for Novel Software Technology School of Electronic Science and Engineering Nanjing University Nanjing210023 China

Data augmentation is a widely used technique for enhancing the generalization ability of convolutional neural networks (CNNs) in image classification tasks. Occlusion is a critical factor that affects on the generalization ability of image classification models. In order to generate new samples, existing data augmentation methods based on information deletion simulate occluded samples by randomly removing some areas in the images. However, those methods cannot delete areas of the images according to their structural features of the images. To solve those problems, we propose a novel data augmentation method, AdvMask, for image classification tasks. Instead of randomly removing areas in the images, AdvMask obtains the key points that have the greatest influence on the classification results via an end-to-end sparse adversarial attack module. Therefore, we can find the most sensitive points of the classification results without considering the diversity of various image appearance and shapes of the object of interest. In addition, a data augmentation module is employed to generate structured masks based on the key points, thus forcing the CNN classification models to seek other relevant content when the most discriminative content is hidden. AdvMask can effectively improve the performance of classification models in the testing process. The experimental results on various datasets and CNN models verify that the proposed method outperforms other previous data augmentation methods in image classification tasks. Copyright © 2022, The Authors. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

A novel liquid crystal planar display structure based on fringe field effect

A novel liquid crystal planar display structure based on fri...

引用

International Conference on Display technology, 2024

作者： Li, An-Ran Yu, Xin-Yi Komitov, Lachezar Srivastava, Abhishek K. State Key Laboratory of Advanced Displays and Optoelectronics Technologies and Centre for Display Research Department of Electronics and Computer Engineering The Hong Kong University of Science and Technology Hong Kong Department of Physics University of Gothenburg Gothenburg Sweden

The liquid crystal display (LCD) continues to hold a prominent position in the display industry. These years' key research topic is the fringe field effect, which aims to improve the LCD's performance. A new LCD structure utilizing the fringe field effect has been identified as a promising solution. This structure allows for the control of the electromagnetic field of the liquid crystal cell by regulating the voltage of the Circular-Hole and Planar Electrode cell (CHPEC). This innovative structure is comprised of nematic liquid crystals (LCs) with negative dielectric anisotropy, a two-electrode system consisting of a Circular-Hole ITO structure on the top layer and a Planar structure on the bottom layer, and a SiO2 porous structure. Finite element simulation tests have verified the electric field strength, transmittance, and contrast of the cell and the matrix structure, meeting the design objectives. This breakthrough has significant potential for application in the display field. © 2024 John Wiley and Sons Inc. All rights reserved.

关键词： Electrodes

来源：评论

学校读者我要写书评

暂无评论

LT-OAQ: Learnable Threshold Based Outlier-Aware Quantization and its Energy-Efficient Accelerator for Low-Precision On-Chip Training

LT-OAQ: Learnable Threshold Based Outlier-Aware Quantization...

引用

Design, Automation and Test in Europe Conference and Exhibition

作者： Qinkai Xu Yijin Liu Yuan Meng Yang Chen Yunlong Mao Li Li Yuxiang Fu School of Electronic Science and Engineering Nanjing University School of Integrated Circuits Nanjing University State Key Laboratory for Novel Software Technology Nanjing University

ISBN: (数字)9783982674100

ISBN: (纸本)9798331534646

Low-precision training has emerged as a powerful technique for reducing computational and storage costs in Deep Neural Network (DNN) model training, enabling on-chip training or fine-tuning on edge devices. However, existing low-precision training methods often require higher bit-widths to maintain accuracy as model sizes increase. In this paper, we introduce an outlier-aware quantization strategy for low-precision training. While traditional value-aware quantization methods require costly online distribution statistics operations on computational data, impeding the efficiency gains of low-precision training, our approach addresses this challenge through a novel Learnable Threshold based Outlier-Aware Quantization (LT-OAQ) training framework. This method concurrently updates outlier thresholds and model weights through gradient descent, eliminating the need for costly data-statistics operations. To efficiently support the LT-OAQ training framework, we designed a hardware accelerator based on the systolic array architecture. This accelerator introduces a processing element (PE) fusion mechanism that dynamically fuses adjacent PEs into clusters to support outlier computations, optimizing the mapping of outlier computation tasks, enabling mixed-precision training, and implementing online quantization. Our approach maintains model accuracy while significantly reducing computational complexity and storage resource requirements. Experimental results demonstrate that our design achieves a 2.9 ×speedup in performance and a 2.17 ×reduction in energy consumption compared to state-of-the-art low-precision accelerators.

关键词： Training Technological innovation Quantization (signal) Accuracy Computational modeling computer architecture Artificial neural networks Systolic arrays System-on-chip Hardware acceleration

来源：评论

学校读者我要写书评

暂无评论

Investigating Efficacy of Perplexity in Detecting LLM-Generated Code

arXiv

引用

arXiv 2024年

作者： Xu, Jinwei Zhang, He Yang, Yanjin Cheng, Zeru Lyu, Jun Liu, Bohan Zhou, Xin Yang, Lanxin Bacchelli, Alberto Chiam, Yin Kia Chiew, Thiam Kian State Key Laboratory of Novel Software Technology Software Institute Nanjing University Nanjing210008 China Department of Informatics University of Zürich Zürich8006 Switzerland Department of Software Engineering Faculty of Computer Science and Information Technology University of Malaya Kuala Lumpur50603 Malaysia

Large language model-generated code (LLMgCode) has become increasingly prevalent in software development. Many studies report that LLMgCode has more quality and security issues than human-authored code (HaCode). It is common for LLMgCode to mix with HaCode in a code change, while the change is signed by only human developers, without being carefully checked. Many automated methods have been proposed to detect LLMgCode from HaCode, in which the perplexity-based method (PERPLEXITY for short) is the state-of-the-art method. However, the efficacy evaluation of PERPLEXITY has focused on the detection accuracy. In this article, we are interested in whether PERPLEXITY is good enough in a wider range of realistic evaluation settings. To this end, we devise a large-scale dataset that includes 11,664 HaCode snippets and 13,164 LLMgCode snippets, and based on that, we carry out a family of experiments to compare PERPLEXITY against feature-based and pre-training-based methods from three perspectives: (1) detection accuracy in terms of programming language, degree of difficulty, and scale of solution, (2) generalization capability, and (3) inference efficiency. The experimental results show that PERPLEXITY has the best generalization capability while it has low accuracy and efficiency in most cases. Based on the experimental results and detection mechanism of PERPLEXITY, we discuss implications into both the strengths and limitations of PERPLEXITY, e.g., PERPLEXITY is unsuitable for high-level programming languages while it has good interpretability. As the first large-scale investigation on detecting LLMgCode from HaCode, this article provides a wide range of evidence for future improvement. Copyright © 2024, The Authors. All rights reserved.

关键词： High level languages

来源：评论

学校读者我要写书评

暂无评论

Enhanced VR Experience with Edge Computing: The Impact of Decoding Latency

引用

IEEE Transactions on Mobile Computing 2025年第07期24卷 6275-6292页

作者： Huang, Liang Li, Yuqi Liang, Hongyuan Chi, Kaikai Wu, Yuan Zhejiang University of Technology School of Computer Science and Technology China University of Macau State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science Macau China

Virtual reality (VR) applications have revolutionized digital interaction by providing immersive experiences.360° VR video streaming has experienced significant growth and popularity as a pivotal VR application. However, the combination of limited network bandwidth and the demand for high-quality videos frequently hinders the achievement of a satisfactory quality of experience (QoE). Although prior methods have enhanced QoE, the effects of decoding latency have been poorly studied. It is technically challenging to design a quality adaptation algorithm that can balance the pursuit of high-quality videos and the limitation of limited bandwidth resources. To address this challenge, we propose an edge-end architecture for 360° VR video streaming and aim to enhance overall QoE by solving a performance optimization problem. Specifically, our experiments on commercial mobile devices in real-world situations reveal that decoding latency significantly influences QoE. First, decoding latency plays a major role in contributing to end-to-end latency, which exceeds the transmission latency. Second, decoding latency can differ considerably between devices with varying computational capabilities. Building on this insight, we propose a novel latency-aware quality adaptation (LAQA) algorithm. LAQA lies in developing a solution that can allocate video quality in real-time and enhance overall QoE. LAQA involves not only the quality of the received content, the transmission latency and the quality variance, but also the decoding latency and the fairness of the user quality. Subsequently, we formulate a combinatorial optimization problem to maximize overall QoE. Through extensive validation with experimental data from real-world situations, LAQA offers a promising approach to enhance QoE and ensure fairness performance in different devices. In particular, LAQA achieves 16.77% and 10.66% enhancement over the state-of-the-art combinatorial optimization and reinforcement learning algorithm

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

A Robust Watermarking Method for Image Processing Models 4

A Robust Watermarking Method for Image Processing Models

引用

4th International Conference on Data Intelligence and Security, ICDIS 2022

作者： Hou, Minghua Tang, Linlin Qi, Shuhan Liu, Yang Harbin Institute of Technology Shenzhen Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies Shenzhen Department of Computer Science and Engineering Guangdong China

ISBN: (数字)9781665459686

ISBN: (纸本)9781665459686

Sharing neural network models in some platforms and communities has become a popular trend, but they will inevitably suffer from malicious theft of models, If the attacker knows the structure and weights of the model, the model can be easily modified, how to protect the intellectual property rights of the deep models has become a serious problem. The appearance of model watermarking provides a technical possibility for the intellectual property protection of neural network models, and it provides us a reliable method of verifying model ownership when the model's intellectual property rights are infringed. Based on previous work, this paper proposes a new watermarking method for image processing models, which embeds the watermark information into the two chroma channels of the YCbCr color space of image processing model's output images. The proposed method can verify the model ownership in black-box case, which has strong robustness and resistance to common model compression and model fine-tuning attacks. © 2022 IEEE.

关键词： Neural network models

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：