检索结果-内蒙古大学图书馆

CoSIL: Software Issue Localization via LLM-Driven Code Repository Graph Searching

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Jiang, Zhonghao Ren, Xiaoxue Yan, Meng Jiang, Wei Li, Yong Liu, Zhongxin The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China Institute of Blockchain and Data Security Hangzhou China School of Big Data and Software Engineering Chongqing University Chongqing China Ant Group Hangzhou China

Large language models (LLMs) have significantly advanced autonomous software engineering, leading to a growing number of software engineering agents that assist developers in automatic program repair. Issue localization forms the basis for accurate patch generation. However, because of limitations caused by the context window length of LLMs, existing issue localization methods face challenges in balancing concise yet effective contexts and adequately comprehensive search spaces. In this paper, we introduce CoSIL, an LLM-driven, simple yet powerful function-level issue localization method without training or indexing. CoSIL reduces the search space through module call graphs, iteratively searches the function call graph to obtain relevant contexts, and uses context pruning to control the search direction and manage contexts effectively. Importantly, the call graph is dynamically constructed by the LLM during search, eliminating the need for pre-parsing. Experiment results demonstrate that CoSIL achieves a Top-1 localization success rate of 43% and 44.6% on SWE-bench Lite and SWE-bench Verified, using Qwen2.5-Coder-32B, respectively, outperforming existing methods by 8.6%–98.2%. When CoSIL is applied to guide the patch generation stage, the resolved rate further improves by 9.3%–31.5%. Copyright © 2025, The Authors. All rights reserved.

关键词： Automatic programming

Out-of-Distribution Generalization on Graphs via Progressive Inference

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Xu, Yiming Shi, Bin Peng, Zhen Liu, Huixiang Dong, Bo Chen, Chen School of Computer Science and Technology Xi’an Jiaotong University China Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong University China School of Distance Education Xi’an Jiaotong University China University of Virginia CharlottesvilleVA United States

The development and evaluation of graph neural networks (GNNs) generally follow the independent and identically distributed (i.i.d.) assumption. Yet this assumption is often untenable in practice due to the uncontrollable data generation mechanism. In particular, when the data distribution shows a significant shift, most GNNs would fail to produce reliable predictions and may even make decisions randomly. One of the most promising solutions to improve the model generalization is to pick out causal invariant parts in the input graph. Nonetheless, we observe a significant distribution gap between the causal parts learned by existing methods and the ground-truth, leading to undesirable performance. In response to the above issues, this paper presents GPro, a model that learns graph causal invariance with progressive inference. Specifically, the complicated graph causal invariant learning is decomposed into multiple intermediate inference steps from easy to hard, and the perception of GPro is continuously strengthened through a progressive inference process to extract causal features that are stable to distribution shifts. We also enlarge the training distribution by creating counterfactual samples to enhance the capability of the GPro in capturing the causal invariant parts. Extensive experiments demonstrate that our proposed GPro outperforms the state-of-the-art methods by 4.91% on average. For datasets with more severe distribution shifts, the performance improvement can be up to 6.86%. 1 © 2025, CC BY.

关键词： Graph neural networks

Robust fixed-time dynamic event-triggered control with disturbance observer for uncertain hybrid energy storage system in pure electric vehicles

学校读者我要写书评

暂无评论

Journal of Energy Storage 2025年 126卷

作者： Guo, Xing Li, Qing Yao, Qijia Tan, Zhao School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing100083 China Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education University of Science and Technology Beijing Beijing100083 China

The underlying control for the hybrid energy storage system (HESS) in pure electric vehicles (PEVs) is crucial. System modeling is inherently subject to uncertainties due to fluctuations in electrical parameters and unknown external disturbances, which can significantly degrade the HESS control performance. This study introduces a robust fixed-time dynamic event-triggered control scheme with a disturbance observer to enhance the robustness of the underlying tracking control in the HESS. Firstly, a fixed-time disturbance observer (FTDO) is designed by employing an integral sliding mode surface to estimate the lumped uncertainties within a fixed time. Subsequently, a hierarchical control framework, containing an upper energy management strategy based on model predictive control and an underlying tracking control based on fixed-time controller (FTC), is developed to achieve power distribution and tracking. Additionally, a dynamic event-triggered mechanism is integrated with the FTC to reduce the load on signal transmission and the frequency of controller updates, while also ensuring the tracking accuracy of the control during non-triggered periods. Finally, the superiority of the proposed method is confirmed through comparisons with another two methods under both standard and actual driving cycles. The results demonstrate its rapid convergence and strong robustness against the lumped uncertainties in the HESS. © 2025

关键词： Predictive control systems

Robustifying vision transformer for image forgery localization with multi-exit architectures

学校读者我要写书评

暂无评论

Pattern Recognition 2025年 164卷

作者： Shi, Zenan Chen, Haipeng Zhang, Dong College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology 999077 Hong Kong

The proliferation of image manipulation tools has led to an increase in the number of manipulated images being disseminated online, posing risks like the propagation of fake news and telecom fraud. Thus, there is an increasing demand for precise, generic, and robust methods for detecting and locating manipulated images. In this paper, we propose a simple and clean model, named MEAFormer, for image forgery localization that does not heavily rely on pre-trained models. MEAFormer comprises three main components: an encoder network, a neck network, and a decoder network. Specifically, the transformer-based encoder network extracts hierarchical feature representations from the input image, providing rich contextual information in each layer. The neck network, incorporating our proposed cross-layer feature aggregation (CFA), aggregates these hierarchical features. To achieve better spatial feature co-occurrence, instead of using noise or edge artifacts, we introduce a multi-scale graph reasoning (MGR) module within the decoder network via bipartite graphs over the encoder and decoder features in a multi-scale fashion. The cross-level enhancement (CLE) further performs adjacent-level feature fusion to amplify the regions of interest in aggregated manipulation features. Finally, the multi-exit architecture (MEA) guides the model to learn fine-grained features and segment out the manipulated region. Extensive experiments across diverse and challenging datasets conclusively establish the superiority of MEAFormer over existing state-of-the-art methods, excelling in accuracy, generalization, and robustness. © 2025 Elsevier Ltd

关键词： Decoding

An Image Semantic Communication System Based on GAN and Relative Position-Encoding

学校读者我要写书评

暂无评论

IEEE Communications Letters 2025年

作者： Zhang, Ziqi Tan, Weijie Li, Chunguo Guizhou University College of Big Data and Information Engineering Guiyang550025 China Guizhou University State Key Laboratory of Public Big Data College of Computer Science and Technology Guiyang550025 China Advanced Cryptography and System Security Key Laboratory of Sichuan Province Chengdu610025 China Ministry of Industry and Information Technology Laboratory of Cryptography Application Technology Innovation and Testing Verification Beijing100015 China Southeast University School of Information Science and Engineering Nanjing210096 China

In image semantic communication, the complex wireless channel environment leads to the loss of image details and performance degradation during transmission. To address this issue, we propose an image semantic communication system based on Generative Adversarial Networks (GAN) and Relative Position-Encoding (RPE), named GAN-RpeSC. Specifically, in the system design, we introduce the GAN network at the output of the semantic communication framework to enhance the image restoration. We integrate the RPE module into the Visual Transformer (ViT) module, adding the RPE module to its Multihead Self Attention (MHSA), so that the model can better capture the spatial location information of the image. Experimental results show that the proposed GAN-RpeSC has significant advantages in improving image transmission quality, with a 0.3 dB improvement in peak signal-to-noise ratio (PSNR) compared to the ViT module alone. © 1997-2012 IEEE.

关键词： Encoding (symbols)

VOILA: Complexity-Aware Universal Segmentation of CT images by Voxel Interacting with Language

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wan, Zishuo Gao, Yu Pang, Wanyuan Ding, Dawei School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing100083 China Key Laboratory of Knowledge Automation for Industrial Processes Ministry of Education Beijing100083 China

Satisfactory progress has been achieved recently in universal segmentation of CT images. Following the success of vision-language methods, there is a growing trend towards utilizing text prompts and contrastive learning to develop universal segmentation models. However, there exists a significant imbalance in information density between 3D images and text prompts. Moreover, the standard fully connected layer segmentation approach faces significant challenges in handling multiple classes and exhibits poor generalizability. To address these challenges, we propose the VOxel Interacting with LAnguage method (VOILA) for universal CT image segmentation. Initially, we align voxels and language into a shared representation space and classify voxels on the basis of cosine similarity. Subsequently, we develop the Voxel-Language Interaction framework to mitigate the impact of class imbalance caused by foreground-background discrepancies and variations in target volumes. Furthermore, a Complexity-Aware Sampling method is proposed to focus on region hard to segment, achieved by generating pseudo-heatmaps from a trainable Gaussian mixture distribution. Our results indicate the proposed VOILA is capable to achieve improved performance with reduced parameters and computational cost during training. Furthermore, it demonstrates significant generalizability across diverse datasets without additional fine-tuning. Code - https://***/ZishuoWan/VOILA. Copyright © 2025, The Authors. All rights reserved.

关键词： Computerized tomography

MSPL: Multi-modal Statistical Prompt Learning for New Energy Equipment Defect Recognition

学校读者我要写书评

暂无评论

IEEE Internet of Things Journal 2025年第11期12卷 16438-16450页

作者： Wang, Zhenwei Wang, Pengfei Han, Guangjie Zhou, Chengjie Lin, Qing Zhang, Jianxin Fan, Guangjie Zhang, Qiang Dalian University of Technology School of Computer Science and Technology Dalian116024 China Dalian116024 China Shenyang Huayan Electric Technology Co Ltd Shenyang110180 China Hohai University Key Laboratory of Maritime Intelligent Network Information Technology Ministry of Education China Deputy Director of the Yantai Big Data Center and Senior Engineer Yantai264003 China Dalian Minzu University School of Computer Science and Engineering Dalian116600 China

Monitoring renewable energy devices is crucial for the timely detection of faults and the improvement of system stability, making it a key component of the Internet of Things (IoT) ecosystem. However, existing intelligent algorithms and IoT methods rely on edge devices with limited computational capacity, which requires balancing real-time performance and accuracy. Additionally, most methods require initial training on large-scale data using cloud platforms or high-performance servers, leading to high initial costs. To address these challenges, we propose Multi-modal Statistical Prompt Learning (MSPL) for new energy equipment defect recognition on IoT edge devices. This method enables rapid learning with only a few samples, avoiding the need for large-scale centralized training. Specifically, MSPL uses the pre-trained Contrastive Language-Image Pre-training model as its backbone, leveraging text-based conceptual information to enhance the understanding of visual inputs. A Statistical Query (SQ) module is implemented at the end of the backbone to extract distinctive features from the outputs, integrating these features with soft prompts to customize them for the defect recognition task. Since the learnable parameters are limited to soft prompts added at the end of the backbone, MSPL restricts gradient backpropagation to this point. This improves parameter and memory efficiency, making it more suitable for scenarios with limited computational capacity on IoT edge devices. Experimental results of MSPL on two renewable energy equipment defect datasets and edge devices indicate that it meets real-time processing requirements while maintaining high accuracy, outperforming other methods. © 2025 IEEE.

关键词： Zero-shot learning

Causal-Inspired Multitask Learning for Video-Based Human Pose Estimation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Chen, Haipeng Wu, Sifan Wang, Zhigang Yin, Yifang Jiao, Yingying Lyu, Yingda Liu, Zhenguang College of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University China College of Computer Science and Technology Zhejiang Gongshang University China A*STAR Singapore Public Computer Education and Research Center Jilin University China The State Key Laboratory of Blockchain and Data Security Zhejiang University China Institute of Blockchain and Data Security China

Video-based human pose estimation has long been a fundamental yet challenging problem in computer vision. Previous studies focus on spatio-temporal modeling through the enhancement of architecture design and optimization strategies. However, they overlook the causal relationships in the joints, leading to models that may be overly tailored and thus estimate poorly to challenging scenes. Therefore, adequate causal reasoning capability, coupled with good interpretability of model, are both indispensable and prerequisite for achieving reliable results. In this paper, we pioneer a causal perspective on pose estimation and introduce a causal-inspired multitask learning framework, consisting of two stages. In the first stage, we try to endow the model with causal spatio-temporal modeling ability by introducing two self-supervision auxiliary tasks. Specifically, these auxiliary tasks enable the network to infer challenging keypoints based on observed keypoint information, thereby imbuing causal reasoning capabilities into the model and making it robust to challenging scenes. In the second stage, we argue that not all feature tokens contribute equally to pose estimation. Prioritizing causal (keypoint-relevant) tokens is crucial to achieve reliable results, which could improve the interpretability of the model. To this end, we propose a Token Causal Importance Selection module to identify the causal tokens and non-causal tokens (e.g., background and objects). Additionally, non-causal tokens could provide potentially beneficial cues but may be redundant. We further introduce a non-causal tokens clustering module to merge the similar non-causal tokens. Extensive experiments show that our method outperforms state-of-the-art methods on three large-scale benchmark datasets. Copyright © 2025, The Authors. All rights reserved.

关键词： Self-supervised learning

CMD: A Cache-Assisted GPU Memory Deduplication Architecture

学校读者我要写书评

暂无评论

IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 2025年

作者： Zhao, Wei Feng, Dan Tong, Wei Wei, Xueliang Wu, Bing Ministry of Education of China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan National Laboratory for Optoelectronics Key Laboratory of Information Storage System Engineering Research Center of data storage systems and Technology China

Massive off-chip accesses in GPUs are the main performance bottleneck. We find that many writes are duplicate, and the duplication can be inter-dup and intra-dup. While inter-dup means different memory blocks are identical, and intra-dup means all the 4B elements in a line are the same. In this work, we propose a cache-assisted GPU memory deduplication architecture named CMD to reduce the off-chip accesses via utilizing the data duplication in GPU applications. CMD includes three key design contributions which aim to reduce the three kinds of accesses: (1) A novel GPU memory deduplication architecture that removes the intra-dup and inter-dup lines. We design several techniques to manage duplicate blocks, reducing massive off-chip writes. (2) We propose a cache-assisted read scheme to reduce the reads to duplicate data. When an L2 cache miss wants to read the duplicate block, if the reference block has been fetched to L2 and it is clean, we can copy it to the L2 missed block without accessing off-chip DRAM. As for the reads to intra-dup data, CMD uses the on-chip metadata cache to get the data. (3) When a cache line is evicted, the clean sectors in the line are invalidated while the dirty sectors are written back. However, most read-only victims are re-referenced from DRAM more than twice. Therefore, we add a full-associate FIFO to accommodate the read-only (it is also clean) victims to reduce the re-reference counts. Experiments show that CMD can decrease the off-chip accesses by 31.01%, reduce the energy by 32.78% and improve performance by 42.53%. Besides, CMD can improve the performance of memory-intensive workloads by 57.56%. © 2025 IEEE.

关键词： Cache memory