检索结果-内蒙古大学图书馆

34th ACM Web Conference, WWW 2025

作者： Luo, Pengfei Zhou, Jingbo Xu, Tong Xia, Yuan Xu, Linli Chen, Enhong School of Computer Science and Technology University of Science and Technology of China State Key Laboratory of Cognitive Intelligence Hefei China Business Intelligence Lab Baidu Research Beijing China Baidu Inc Beijing China

ISBN: (纸本)9798400712746

With the proliferation of images in online content, language-guided image retrieval (LGIR) has emerged as a research hotspot over the past decade, encompassing a variety of subtasks with diverse input forms. While the development of large multimodal models (LMMs) has significantly facilitated these tasks, existing approaches often address them in isolation, requiring the construction of separate systems for each task. This not only increases system complexity and maintenance costs, but also exacerbates challenges stemming from language ambiguity and complex image content, making it difficult for retrieval systems to provide accurate and reliable results. To this end, we propose ImageScope, a training-free, three-stage framework that leverages collective reasoning to unify LGIR tasks. The key insight behind the unification lies in the compositional nature of language, which transforms diverse LGIR tasks into a generalized text-to-image retrieval process, along with the reasoning of LMMs serving as a universal verification to refine the results. To be specific, in the first stage, we improve the robustness of the framework by synthesizing search intents across varying levels of semantic granularity using chain-of-thought (CoT) reasoning. In the second and third stages, we then reflect on retrieval results by verifying predicate propositions locally, and performing pairwise evaluations globally. Experiments conducted on six LGIR datasets demonstrate that ImageScope outperforms competitive baselines. Comprehensive evaluations and ablation studies further confirm the effectiveness of our design. © 2025 Copyright held by the owner/author(s).

关键词： Photointerpretation

来源：评论

学校读者我要写书评

暂无评论

AdPO: Enhancing the Adversarial Robustness of Large Vision-Language Models with Preference Optimization

arXiv

引用

arXiv 2025年

作者： Liu, Chaohu Gui, Tianyi Liu, Yu Xu, Linli School of Computer Science and Technology University of Science and Technology of China China State Key Laboratory of Cognitive Intelligence China Tongyi Lab China

Large Vision-Language Models (LVLMs), such as GPT-4o and LLaVA, have recently witnessed remarkable advancements and are increasingly being deployed in real-world applications. However, inheriting the sensitivity of visual neural networks, LVLMs remain vulnerable to adversarial attacks, which can result in erroneous or malicious outputs. While existing efforts utilize adversarial fine-tuning to enhance robustness, they often suffer from performance degradation on clean inputs. In this paper, we proposes AdPO, a novel adversarial defense strategy for LVLMs based on preference optimization. For the first time, we reframe adversarial training as a preference optimization problem, aiming to enhance the model’s preference for generating normal outputs on clean inputs while rejecting the potential misleading outputs for adversarial examples. Notably, AdPO achieves this by solely modifying the image encoder, e.g., CLIP ViT, resulting in superior clean and adversarial performance in a variety of downsream tasks. Considering that training involves large language models (LLMs), the computational cost increases significantly. We validate that training on smaller LVLMs and subsequently transferring to larger models can achieve competitive performance while maintaining efficiency comparable to baseline methods. Our comprehensive experiments confirm the effectiveness of the proposed AdPO, which provides a novel perspective for future adversarial defense research. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

GTN-Cell: Efficient Standard Cell Characterization Using Graph Transformer Network

GTN-Cell: Efficient Standard Cell Characterization Using Gra...

引用

Design, Automation and Test in Europe Conference and Exhibition

作者： Lihao Liu Yunhui Li Beisi Lu Li Shang Fan Yang State Key Lab of Integrated Chips and Systems School of Microelectronics Fudan University Shanghai China State Key Lab of Integrated Chips and Systems School of Computer Science Fudan University Shanghai China

ISBN: (数字)9783982674100

ISBN: (纸本)9798331534646

Lookup table (LUT)-based libraries of standard cell characterization is crucial to accurate static timing analysis (STA). However, with the continuous scaling of technology nodes and the increasing complexity of circuit designs, the traditional nonlinear delay model (NLDM) is progressively unable to meet the required accuracy for cell modeling. The current source model (CSM) offers a more precise characterization of cells at advanced nodes and is able to handle arbitrary electrical waveforms. However, the CSM is highly time-consuming because it requires extensive transistor-level simulations, posing severe challenges to efficient standard cell library design. This work presents GTN-Cell, an efficient graph transformer network (GTN)-based method for library-compatible LUT-based CSM waveform prediction of standard cell characterization. GTN-Cell represents the transistor-level structures of standard cells as graphs, learning the local structural information of each cell. By incorporating the transformer encoder into the model and embedding path-related positional encodings, GTN -Cell captures the global relationships between distant nodes within each cell. Compared with HSPICE, the GTN-Cell achieves an average error of 2.27% on predicted voltage waveforms among different standard cells and timing arcs while reducing the number of simulations by 70%.

关键词： Training Accuracy Voltage Predictive models Transformers Libraries Encoding Integrated circuit modeling Standards Load modeling

来源：评论

学校读者我要写书评

暂无评论

An LLM-Empowered Adaptive Evolutionary Algorithm For Multi-Component Deep Learning Systems

arXiv

引用

arXiv 2025年

作者： Tian, Haoxiang Han, Xingshuo Wu, Guoquan Guo, An Zhou, Yuan Zhang, Jie Li, Shuo Wei, Jun Zhang, Tianwei Key Lab of System Software CAS State Key Lab of Computer Science ISCAS Beijing China University of CAS Beijing China Nanyang Technological University Singapore Continental-NTU Corporate Lab Singapore Nanjing Institute of Software Technology University of CAS Nanjing China Nanjing University Nanjing China Zhejiang Sci-Tech University Hangzhou China CFAR IHPC A*STAR Singapore

Multi-objective evolutionary algorithms (MOEAs) are widely used for searching optimal solutions in complex multi-component applications. Traditional MOEAs for multi-component deep learning (MCDL) systems face challenges in enhancing the search efficiency while maintaining the diversity. To combat these, this paper proposes µMOEA, the first LLM-empowered adaptive evolutionary search algorithm to detect safety violations in MCDL systems. Inspired by the context-understanding ability of Large Language Models (LLMs), µMOEA promotes the LLM to comprehend the optimization problem and generate an initial population tailed to evolutionary objectives. Subsequently, it employs adaptive selection and variation to iteratively produce offspring, balancing the evolutionary efficiency and diversity. During the evolutionary process, to navigate away from the local optima, µMOEA integrates the evolutionary experience back into the LLM. This utilization harnesses the LLM's quantitative reasoning prowess to generate differential seeds, breaking away from current optimal solutions. We evaluate µMOEA in finding safety violations of MCDL systems, and compare its performance with state-of-the-art MOEA methods. Experimental results show that µMOEA can significantly improve the efficiency and diversity of the evolutionary search. © 2025, CC BY.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

The Power of Graph Signal Processing for Chip Placement Acceleration 24

The Power of Graph Signal Processing for Chip Placement Acce...

引用

43rd International Conference on computer-Aided Design, ICCAD 2024

作者： Liu, Yiting Zhou, Hai Wang, Jia Yang, Fan Zeng, Xuan Shang, Li School of Computer Science Fudan University Shanghai China Department of ECE Northwestern University Evanston United States Department of ECE IIIinois Institute of Technology Chicago United States State Key Lab of ASIC & System Microelectronics Department Fudan University Shanghai China

ISBN: (纸本)9798400710773

Placement is a critical task with high computation complexity in VLSI physical design. Modern analytical placers formulate the placement objective as a nonlinear optimization task, which suffers a long iteration time. To accelerate and enhance the placement process, recent studies have turned to deep learning-based approaches, particularly leveraging graph convolution networks (GCNs). However, learning-based placers require time- and data-consuming model training due to the complexity of circuit placement that involves large-scale cells and design-specific graph statistics. This paper proposes GiFt, a parameter-free technique for accelerating placement, rooted in graph signal processing. GiFt excels at capturing multi-resolution smooth signals of circuit graphs to generate optimized placement solutions without the need for time-consuming model training, and meanwhile significantly reduces the number of iterations required by analytical placers. Experimental results show that GiFt significantly improving placement efficiency, while achieving competitive or superior performance compared to state-of-the-art placers. In particular, compared to DREAMPlace, the recently proposed GPU-accelerated analytical placer, GF-Placer improves total runtime over 45%. © 2024 Copyright is held by the owner/author(s).

关键词： Nonlinear programming

来源：评论

学校读者我要写书评

暂无评论

Language-Queried Target Sound Extraction Without Parallel Training Data

Language-Queried Target Sound Extraction Without Parallel Tr...

引用

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

作者： Ma, Hao Peng, Zhiyuan Li, Xu Li, Yukai Shao, Mingjie Kong, Qiuqiang Liu, Ju School of Information Science and Engineering Shandong University Qingdao China Department of Computer Science North Carolina State University NC United States ARC Lab Tencent PCG China Key Laboratory of System and Control AMSS Chinese Academy of Sciences Beijing China The Chinese University of Hong Kong Hong Kong

ISBN: (纸本)9798350368741

Language-queried target sound extraction (TSE) aims to extract specific sounds from mixtures based on language queries. Traditional fully-supervised training schemes require extensively annotated parallel audio-text data, which are labor-intensive. We introduce a parallel-data-free training scheme, requiring only unlabelled audio clips for TSE model training by utilizing the contrastive language-audio pre-trained model (CLAP). In a vanilla parallel-data-free training stage, target audio is encoded using the pre-trained CLAP audio encoder to form a condition embedding, while during testing, user language queries are encoded by CLAP text encoder as the condition embedding. This vanilla approach assumes perfect alignment between text and audio embeddings, which is unrealistic. Two major challenges arise from training-testing mismatch: the persistent modality gap between text and audio and the risk of overfitting due to the exposure of rich acoustic details in target audio embedding during training. To address this, we propose a retrieval-augmented strategy. Specifically, we create an embedding cache using audio captions generated by a large language model (LLM). During training, target audio embeddings retrieve text embeddings from this cache to use as condition embeddings, ensuring consistent modalities between training and testing and eliminating information leakage. Extensive experiment results show that our retrieval-augmented approach achieves consistent and notable performance improvements over existing state-of-the-art with better generalizability. © 2025 IEEE.

关键词： contrastive language-audio pre-training retrieval-augmented strategy target sound extraction uni-modal training for multi-modal tasks

来源：评论

学校读者我要写书评

暂无评论

Streamlining Computational Lithography With Efficient Pattern Database

引用

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

作者： Zheng, Su Zhao, Wenqian Sun, Shuyuan Yang, Fan Yu, Bei Wong, Martin D.F. The Chinese University of Hong Kong Department of Computer Science and Engineering Hong Kong Fudan University State Key Lab of Integrated Circuits and Systems China Hong Kong Baptist University Department of Computer Science Hong Kong

In the pursuit of advancing computational lithography, this paper introduces a novel pattern database framework designed to support related tasks. The proposed framework is built upon three core components: an unsupervised metric learning method for robust pattern embedding, a vector database for swift pattern retrieval, and an efficient algorithm dedicated to pattern clustering. These elements synergize to significantly enhance the efficiency and effectiveness of various computational lithography methods. In downstream tasks, our framework provides accurate lithography hotspot detection through pattern retrieval, streamlines inverse lithography technique (ILT) by leveraging solution reusing, and facilitates the exploration of ILT & source parameters based on the pattern clustering results. Collectively, these advancements culminate in a comprehensive improvement in computational lithography, offering a scalable solution for the ever-evolving demands of this field. © 2025 IEEE.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Accelerating Authenticated Block Ciphers via RISC-V Custom Cryptography Instructions

Accelerating Authenticated Block Ciphers via RISC-V Custom C...

引用

Design, Automation and Test in Europe Conference and Exhibition

作者： Yuhang Qiu Wenming Li Tianyu Liu Zhen Wang Zhiyuan Zhang Zhihua Fan Xiaochun Ye Dongrui Fan Zhimin Tang State Key Lab of Processors Institute of Computing Technology CAS Beijing China School of Computer Science and Technology UCAS Beijing China

ISBN: (数字)9783982674100

ISBN: (纸本)9798331534646

As one of the standardized encryption algorithms, authenticated block ciphers based on Galois/Counter Mode (GCM) is a widely-used method to guarantee the accuracy and reliability in data transmission. The profiling work demonstrates that across the execution process of GCM mode, the authentication operation is the main performance bottleneck because it introduces operations in high-dimensional Galois field (GF), which could not be efficiently executed via existing ISA. To overcome this problem, we propose a custom ISA extension and cooperate it with RISC-V cryptography extension to accelerate the whole process of authenticated block ciphers. Besides, we design a specific crypto core including a fully-pipelined GF(2 128 ) multiplier to support the extended instructions and integrate it into the multi-issue out-of-order core XT910 without introducing any clock frequency overhead. The proposed design significantly reduces the the number of instructions required in the main operations of authenticated block ciphers. We compare the performance of our designs to other existing acceleration scheme based on RISC-V ISA extension. Experimental result shows that our design outperforms other related work and achieves up to 17 × speedup with a lightweight hardware overhead.

关键词： Out of order Ciphers Europe Authentication Hardware Encryption Reliability Data communication Galois fields Clocks

来源：评论

学校读者我要写书评

暂无评论

Adaptive ILT via Multi-Level Lithography Simulation

引用

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

作者： Sun, Shuyuan Yang, Fan Yu, Bei Shang, Li Zeng, Xuan Fudan University State Key Lab of Integrated Circuits and Systems China Fudan University School of Microelectronics China The Chinese University of Hong Kong Department of Computer Science and Engineering Hong Kong Fudan University School of Computer Science China

Inverse lithography technology (ILT) is an advanced resolution enhancement technology (RET) approach that pushes the limits of current process conditions to achieve smaller feature sizes. This paper presents an efficient ILT framework centered on the concept of solving mask optimization problem from approximation to precision. Firstly, low-resolution lithography simulation is employed to guide ILT, generating a preliminary solution at a low cost. Subsequently, high-resolution lithography simulation is utilized for fine-tuning, and output the final correction results. Additionally, we introduce a continuous correction scheme and a hyperparameter selection strategy to enhance the adaptability and robustness of the ILT solver for full-chip scale layouts. For via layer patterns, we significantly improve the solvers performance by adopting a new high-resolution ILT approach combined with a restricted optimization region. Experimental results show that our method effectively reduces edge placement error (EPE) violations and improves efficiency for ILT on full-chip scale layouts. In the ICCAD 2013 benchmark, our method outperforms state-ofthe-art approaches, reducing L2 loss by at least 1.3%. For via layer patterns, our method achieves a 98% reduction in L2 loss and nearly triples the runtime efficiency compared to its earlier version. Furthermore, it delivers an 8% reduction in L2 loss and a 45% reduction in PVBand compared to other existing methods. © 1982-2012 IEEE.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Spk2ImgMamba: Spiking Camera Image Reconstruction with Multi-Scale state Space Models

Spk2ImgMamba: Spiking Camera Image Reconstruction with Multi...

引用

IEEE Workshop on Applications of computer Vision (WACV)

作者： Jiaoyang Yin Bin Fan Chao Xu Tiejun Huang Boxin Shi State Key Lab of Multimedia Info. Processing School of Computer Science Peking University Nat'l Eng. Research Ctr. of Visual Technology School of Computer Science Peking University Nat'l Key Lab of General AI School of Intelligence Science and Technology Peking University

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

As a bio-inspired vision sensor, the spiking camera has showcased remarkable capability in high-speed imaging with a sampling rate of 40,000 Hz. Reconstructing clear images from continuous spike streams, which is obtained by each photosensor continuously detecting photons and firing them asynchronously, has garnered significant attention. Despite promising results, existing spike-to-image reconstruction methods face challenges in balancing global receptive fields and efficient computation due to the inherent limitations of their backbones. Recently, due to powerful long-range modeling and linear complexity, the state space model (SSM) has emerged as a competitive alternative to CNNs and Transformers. In this paper, we propose a lightweight spike-to-image reconstruction network that harnesses Mamba as the backbone. Our approach sequentially executes three core modules: temporal information integration, spatial feature enhancement, and progressive image reconstruction. The former accumulates cues across diverse temporal windows to explore both long-term and short-term contexts. Subsequently, to model global dependencies while heightening local detail perception, we develop a multi-scale SSM block characterized by multi-scale multi-direction scanning, which effectively boosts spatial feature representations. Finally, intensity images are decoded progressively from the enhanced light-intensity features. Extensive experiments on both synthetic and real-captured data demonstrate that our approach achieves state-of-the-art performance, with only 10% of the network parameters and nearly two orders of magnitude less computational effort. The code will be available at https://***/interstellarH/Spk2ImgMamba.

关键词： Correlation Computational modeling Reconstruction algorithms Vision sensors Transformer cores Streaming media Cameras Transformers Image reconstruction Streams

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：