检索结果-内蒙古大学图书馆

31st International Conference on Computational Linguistics, COLING 2025

作者： Liu, Zesheng Zhu, Qiannan Li, Cuiping Chen, Hong School of Information Renmin University of China Beijing China Key Laboratory of Data Engineering and Knowledge Engineering MOE China Engineering Research Center of Database and Business Intelligence MOE China School of Artificial Intelligence Beijing Normal University Beijing China Engineering Research Center of Intelligent Technology and Educational Application MOE China

ISBN: (纸本)9798891761964

Federated learning-based Named Entity Recognition (FNER) has attracted widespread attention through decentralized training on local clients. However, most FNER models assume that entity types are pre-fixed, so in practical applications, local clients constantly receive new entity types without enough storage to access old entity types, resulting in severe forgetting on previously learned knowledge. In addition, new clients collecting only new entity types may join the global training of FNER irregularly, further exacerbating catastrophic forgetting. To overcome the above challenges, we propose a Forgetting-Subdued Learning (FSL) model which solves the forgetting problem on old entity types from both intra-client and inter-client two aspects. Specifically, for intra-client aspect, we propose a prototype-guided adaptive pseudo labeling and a prototypical relation distillation loss to surmount catastrophic forgetting of old entity types with semantic shift. Furthermore, for inter-client aspect, we propose a task transfer detector. It can identify the arrival of new entity types that are protected by privacy and store the latest old global model for relation distillation. Qualitative experiments have shown that our model has made significant improvements compared to several baseline methods. © 2025 Association for Computational Linguistics.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Human Pose Estimation in the Internet of Things via Diffusion Generative Models

引用

IEEE Internet of Things Journal 2025年第10期12卷 13556-13567页

作者： Wu, Sifan Zhang, Hongzhe Liu, Zhenguang Chen, Haipeng Jiao, Yingying Jilin University College of Computer Science and Technology the Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Changchun130012 China School of discipline inspection and supervision China University of Political Science and Law Beijing100088 China Zhejiang University State Key Laboratory of Blockchain and Data Security Hangzhou310027 China Institute of Blockchain and Data Security Hangzhou310059 China Zhejiang University of Technology College of Computer Science and Technology Hangzhou310014 China

With the ongoing development of public video surveillance technology, accurate human pose estimation is becoming increasingly important in urban administration and law enforcement. However, existing methods rely on large-scale dense annotations, which are labor-intensive and time-consuming. To tackle this, we propose SparsePose which leverages training videos with sparse annotations (labeled every k frames) to learn to propagate temporal poses that help to estimate the poses in unlabeled frames. Technically, we engage in a novel dual-branch architecture that combines 1) pose forecasting of the consecutive neighboring frames with 2) visual clues of the current frame and the nearest labeled frames. We theoretically derive the intra-branch and inter-branch mutual information loss to supervise that maximized pose-relevant features are extracted from the current frame and different branches complement each other to approach precise pose estimation. Additionally, we propose a diffusion generative enhancement, which improves the robustness of the model to challenging scenes from the perspective of diversity. Empirical results show that our method significantly outperforms the state-of-the-art methods in sparsely labeled pose estimation on three benchmark datasets. © 2025 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis

arXiv

引用

arXiv 2025年

作者： Zhang, Bohan Zhang, Xiaokang Zhang, Jing Yu, Jifan Luo, Sijia Tang, Jie School of Information Renmin University of China China Tsinghua University China Key Laboratory of Data Engineering and Knowledge Engineering Beijing China

Current inference scaling methods, such as Self-consistency and Best-of-N, have proven effective in improving the accuracy of LLMs on complex reasoning tasks. However, these methods rely heavily on the quality of candidate responses and are unable to produce correct answers when all candidates are incorrect. In this paper, we propose a novel inference scaling strategy, CoT-based Synthesizer, which leverages CoT reasoning to synthesize superior answers by analyzing complementary information from multiple candidate responses, even when all candidate responses are flawed. To enable a lightweight and cost-effective implementation, we introduce an automated data generation pipeline that creates diverse training data. This allows smaller LLMs trained on this data to improve the inference accuracy of larger models, including API-based LLMs. Experimental results across four benchmark datasets with seven policy models demonstrate that our method significantly enhances performance, with gains of 11.8% for Llama3-8B and 10.3% for GPT-4o on the MATH dataset. The corresponding training data and code are publicly available on the repository. Copyright © 2025, The Authors. All rights reserved.

关键词： data accuracy

来源：评论

学校读者我要写书评

暂无评论

Dynamic Scaling of Unit Tests for Code Reward Modeling

arXiv

引用

arXiv 2025年

作者： Ma, Zeyao Zhang, Xiaokang Zhang, Jing Yu, Jifan Luo, Sijia Tang, Jie School of Information Renmin University of China China Tsinghua University China Key Laboratory of Data Engineering and Knowledge Engineering Beijing China

Current large language models (LLMs) often struggle to produce accurate solutions on the first attempt for code generation. Prior research tackles this challenge by generating multiple candidate solutions and validating them with LLM-generated unit tests. The execution results of unit tests serve as reward signals to identify correct solutions. As LLMs always confidently make mistakes, these unit tests are not reliable, thereby diminishing the quality of reward signals. Motivated by the observation that scaling the number of solutions improves LLM performance, we explore the impact of scaling unit tests to enhance reward signal quality. Our pioneer experiment reveals a positive correlation between the number of unit tests and reward signal quality, with greater benefits observed in more challenging problems. Based on these insights, we propose CodeRM-8B, a lightweight yet effective unit test generator that enables efficient and high-quality unit test scaling. Additionally, we implement a dynamic scaling mechanism that adapts the number of unit tests based on problem difficulty, further improving efficiency. Experimental results show that our approach significantly improves performance across various models on three benchmarks (e.g., with gains of 18.43% for Llama3-8B and 3.42% for GPT-4o-mini on HumanEval Plus). © 2025, CC BY-SA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fabrication-Tolerant High-Speed 5-Bit Silicon Optical True Time Delay Line in the O-Band

引用

Journal of Lightwave Technology 2025年第9期43卷 4358-4366页

作者： Ni, Ziheng Lu, Liangjun Wang, Yixuan Liu, Yuanbin Chen, Jianping Zhou, Linjie Shanghai Jiao Tong University State Key Laboratory of Advanced Optical Communication Systems and Networks Shanghai Institute for Advanced Communication and Data Science Department of Electronic Engineering Shanghai Key Lab of Navigation and Location Services Shanghai200240 China SJTU-Pinghu Institute of Intelligent Optoelectronics Pinghu314200 China

Fast reconfiguration time on the order of nanoseconds is crucial for microwave photonic beamformers, particularly in 5G/6G wireless communication systems. Most previously reported integrated optical true time delay lines (OTTDLs) exhibit a slow response time of tens of microseconds. In this study, we demonstrate an O-band high-speed 5-bit silicon OTTDL based on fabrication-tolerant electro-optic push-pull optical switches, which exhibit lower phase deviation and reduced insertion loss compared to conventional designs. The rising and falling times are 9 ns and 11 ns for the electro-optic switching, respectively. The insertion loss and crosstalk of our fabrication-tolerant high-speed switch element are 0.66 dB (0.74 dB) and −25.09 dB (−27.41 dB) at the bar (cross) state, respectively, at the wavelength of 1310 nm. For the 5-bit OTTDL, the initial phase variation is only ∼0.10π, which is one-sixth of that observed in the conventional design. Additionally, our proposed OTTDL features a low fiber-to-fiber insertion loss of 8.72 dB and a delay tuning range of 0-313.9 ps. The high-performance, fabrication-tolerant OTTDLs hold significant promise for future applications in fast beamforming. © 1983-2012 IEEE.

关键词： Fiber to the x

来源：评论

学校读者我要写书评

暂无评论

Accelerating the Thermal Response of a III-V/Si3N4 Hybrid External Cavity Laser with Electronic-Photonic Co-Design

引用

Journal of Lightwave Technology 2025年第10期43卷 4871-4880页

作者： Han, keyi Lu, Liangjun Guo, Yuyao Li, Xinhang Xu, Weihan Chen, Jianpin Zhou, Linjie Shanghai Jiao Tong University State Key Laboratory of Advanced Optical Communication Systems and Networks The Shanghai Institute for Advanced Communication and Data Science Shanghai Key Lab of Navigation and Location Services Department of Electronic Engineering Shanghai200240 China SJTU-Pinghu Institute of Intelligent Optoelectronics Pinghu314200 China

We propose an electronic-photonic (EP) co-designed scheme to enhance the modulation speed of thermo-optic (TO) phase shifters. We establish a small signal analysis model to optimize the TO phase shifter by compensating its thermal-response-limited low-pass behavior with an electric high-pass equalization circuit, thus expanding the modulation bandwidth. To prove its potential, we demonstrate an EP-converged frequency-modulated continuous-wave (FMCW) laser comprising an InP/Si3N4 hybrid integrated external cavity laser (ECL) driving with an electric equalization circuit. The small signal bandwidth of the TO phase shifter inside the laser cavity is enhanced from 10 kHz to 360 kHz with the equalization circuit. By driving the TO phase shifter, we generate an FMCW signal with a chirp bandwidth of 943 MHz at a repetition rate of 100 kHz. The residual nonlinearity of the frequency chirp is reduced to 0.72% thanks to the pre-distortion technique, enabling a ranging precision of 8.1 cm over a 20 m distance. © 2025 IEEE.

关键词： Pulse repetition rate

来源：评论

学校读者我要写书评

暂无评论

Security analysis and secured access design for networks of image remote sensing

引用

Digital Communications and Networks 2025年第1期11卷 136-144页

作者： Juan Zhao Haibo Dai Xiaolong Xu Hao Yan Zheng Zhang Chunguo Li School of Network Security Jinling Institute of TechnologyNanjing 211169China School of IoT Nanjing University of Posts and Telecommunications(NJUPT)Nanjing 210003China Jiangsu Key Lab.of Big Data Security and Intelligent Processing NJUPTNanJing 210003China School of Information Science and Engineering Southeast UniversityNanjing 210096China

The secured access is studied in this paper for the network of the image remote *** sensor in this network encounters the information security when uploading information of the images wirelessly from the sensor to the central collection *** order to enhance the sensing quality for the remote uploading,the passive reflection surface technique is *** one eavesdropper that exists nearby this sensor is keeping on accessing the same networks,he may receive the same image from this *** goal in this paper is to improve the SNR of legitimate collection unit while cut down the SNR of the eavesdropper as much as possible by adaptively adjust the uploading power from this sensor to enhance the security of the remote sensing *** order to achieve this goal,the secured energy efficiency performance is theoretically analyzed with respect to the number of the passive reflection elements by calculating the instantaneous performance over the channel fading *** on this theoretical result,the secured access is formulated as a mathematical optimization problem by adjusting the sensor uploading power as the unknown variables with the objective of the energy efficiency maximization while satisfying any required maximum data rate of the eavesdropper ***,the analytical expression is theoretically derived for the optimum uploading *** simulations verify the design approach.

关键词： Image remote sensing Secured access Energy efficiency Sensor transmit power Secured access design

来源：评论

学校读者我要写书评

暂无评论

KAN v.s. MLP for Offline Reinforcement Learning

KAN v.s. MLP for Offline Reinforcement Learning

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Guo, Haihong Li, Fengxin Li, Jiao Liu, Hongyan School of Information Renmin University of China China Institute of Medical Information Medical Library Chinese Academy of Medical Sciences Peking Union Medical College China Key Laboratory of Data Engineering and Knowledge Engineering Ministry of Education China School of Economics and Management Tsinghua University China

ISBN: (纸本)9798350368741

Kolmogorov-Arnold Networks (KAN) is an emerging neural network architecture in machine learning. It has greatly interested the research community about whether KAN can be a promising alternative to the commonly used Multi-Layer Perceptions (MLP). Experiments in various fields demonstrated that KAN-based machine learning can achieve comparable if not better performance than MLP-based methods, but with much smaller parameter scales and are more explainable. In this paper, we explore the incorporation of KAN into the actor and critic networks for offline reinforcement learning (RL). We evaluated the performance, parameter scales, and training efficiency of various KAN and MLP-based conservative Q-learning (CQL) on the classical D4RL benchmark for offline RL. Our study demonstrates that KAN can achieve performance close to the commonly used MLP with significantly fewer parameters. This allows us to choose the base networks according to the offline RL task requirements. © 2025 IEEE.

关键词： KAN Kolmogorov-Arnold networks MLP multilayer perceptrons offline reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Dual-Aspect Noise-Based Regularization for Multi-Modal Relation Extraction in Media Posts

IEEE Transactions on Audio, Speech and Language Processing

引用

IEEE Transactions on Audio, Speech and Language Processing 2025年 33卷 1324-1336页

作者： Kai Sun Bin Shi Samuel Mensah Wenjian Liu Bo Dong School of Computer Science and Technology and Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University Xi'an China School of Computer Science and Technology The University of Sheffield Sheffield U.K. Faculty of Data Science City University of Macau Macau China School of Continuing Education and Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University Xi'an China

Multi-Modal Relation Extraction (MMRE) plays a key role in various multimedia applications including, recommendation and information retrieval systems. MMRE aims to extract the semantic relation between entities by leveraging context from a text-image pair. By utilizing context from images, the challenge of learning from noisy images in MMRE emerges as a research problem by itself. For instance, subtle variations in similar images can act as noise and potentially impact the predictions made by MMRE models. To tackle this problem, current work utilizes attention mechanisms to fuse relevant text and image features or devise data augmentation techniques (e.g., via generative models) to improve generalization. However, the current performance still remains unsatisfactory. In an effort to improve upon the performance, we propose a Dual-Aspect Noise-based Regularization framework that encompasses two techniques: 1) noise removal through an adaptive gating mechanism, 2) fighting noise with noise to improve feature stability in the learning process. We find that combining these techniques encourages the model to focus on more relevant image features for MMRE. We carry out extensive experiments and demonstrate that our proposed model is further enhanced by exploring data augmentation techniques. This additional improvement leads the model to achieve state-of-the-art performance on the widely-used Multi-modal Neural Relation Extraction (MNRE) dataset, and show its effectiveness and generalizability on the Multi-Modal Named Entity Recognition task.

关键词： Feature extraction Noise data mining Noise measurement Social networking (online) Adaptation models Transformers Training Predictive models data models

来源：评论

学校读者我要写书评

暂无评论

LoRS: Efficient Low-Rank Adaptation for Sparse Large Language Model

arXiv

引用

arXiv 2025年

作者： Hu, Yuxuan Zhang, Jing Chen, Xiaodong Zhao, Zhe Li, Cuiping Chen, Hong School of Information Renmin University of China Beijing China Key Laboratory of Data Engineering and Knowledge Engineering Beijing China Engineering Research Center of Database and Business Intelligence Beijing China Tencent AI Lab Beijing China

Existing low-rank adaptation (LoRA) methods face challenges on sparse large language models (LLMs) due to the inability to maintain sparsity. Recent works introduced methods that maintain sparsity by augmenting LoRA techniques with additional masking mechanisms. Despite these successes, such approaches suffer from an increased memory and computation overhead, which affects efficiency of LoRA methods. In response to this limitation, we introduce LoRS, an innovative method designed to achieve both memory and computation efficiency when fine-tuning sparse LLMs. To mitigate the substantial memory and computation demands associated with preserving sparsity, our approach incorporates strategies of weight recompute and computational graph rearrangement. In addition, we also improve the effectiveness of LoRS through better adapter initialization. These innovations lead to a notable reduction in memory and computation consumption during the fine-tuning phase, all while achieving performance levels that outperform existing LoRA approaches. © 2025, CC BY.

关键词： Problem oriented languages

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：