检索结果-内蒙古大学图书馆

How Deep is Love in LLMs’ Hearts? Exploring Semantic Size in Human-like Cognition

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Yao, Yao Yang, Yifei Ma, Xinbei Yang, Dongjie Zhang, Zhuosheng Li, Zuchao Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3 Shanghai China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai China School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan University Wuhan430072 China

How human cognitive abilities are formed has long captivated researchers. However, a significant challenge lies in developing meaningful methods to measure these complex processes. With the advent of large language models (LLMs), which now rival human capabilities in various domains, we are presented with a unique testbed to investigate human cognition through a new lens. Among the many facets of cognition, one particularly crucial aspect is the concept of semantic size—the perceived magnitude of both abstract and concrete words or concepts. This study seeks to investigate whether LLMs exhibit similar tendencies in understanding semantic size, thereby providing insights into the underlying mechanisms of human cognition. We begin by exploring metaphorical reasoning, comparing how LLMs and humans associate abstract words with concrete objects of varying sizes. Next, we examine LLMs’ internal representations to evaluate their alignment with human cognitive processes. Our findings reveal that multi-modal training is crucial for LLMs to achieve more human-like understanding, suggesting that real-world, multi-modal experiences are similarly vital for human cognitive development. Lastly, we examine whether LLMs are influenced by attention-grabbing headlines with larger semantic sizes in a real-world web shopping scenario. The results show that multi-modal LLMs are more emotionally engaged in decision-making, but this also introduces potential biases, such as the risk of manipulation through clickbait headlines. Ultimately, this study offers a novel perspective on how LLMs interpret and internalize language, from the smallest concrete objects to the most profound abstract concepts like ‘love’. The insights gained not only improve our understanding of LLMs but also provide new avenues for exploring the cognitive abilities that define human intelligence. Our code and dataset is publicly available at https://***/Zoeyyao27/LLM-Semantic-Size-Understanding. © 2025, CC BY.

关键词： Semantics

Joint Scheduling, Computing, and Load Balancing for Time Sensitive Traffic in SDN-Enabled Space-Air-Ground Integrated 6 G Networks: A Federated Reinforcement Learning Approach

学校读者我要写书评

暂无评论

IEEE Transactions on Mobile Computing 2025年

作者： Sun, Haitong Zhang, Haijun Ma, Hui Leung, Victor C.M Hebei Key Laboratory of Space-Air-Ground Intelligent Communication Beijing100083 China University of Science and Technology Beijing Beijing Engineering and Technology Research Center for Convergence Networks and Ubiquitous Services Beijing100083 China Shenzhen University Department of Computer Science and Software Engineering Shenzhen518061 China University of British Columbia Department of Electrical and Computer Engineering VancouverBCV6T 1Z4 Canada

Low Earth Orbit (LEO) constellations and Unmanned Aerial Vehicle (UAV) networks enable wide coverage for the sixth generation (6G) mobile communication. However, it is a challenge to achieve high scheduling success rate, ultra-low latency, and efficient load balance in the Space-Air-Ground Integrated 6G Network (SAGGIN). This paper addresses the following issue: How to effectively and orderly transmit time-sensitive traffic in SAGGIN under strict deadlines, limited computational ability, and restrained link capacity? Specifically, this paper uses software-Defined Networking (SDN) and designs a joint optimization method to enhance the traffic transmission ability of SAGGIN. Considering response time, computing cost, and link capacity in SAGGIN, the scheduling, computing, and load balance issues are modeled as a multi-objective optimization problem that minimizes the worst-case response time and computing cost of data frames while maximizing the network flow. Then, this paper leverages a Federated Reinforcement Learning (FRL) scheme to solve the problem. Results show that the FRL could achieve great scheduling, computing, and load balance performance. Specifically, our method can successfully schedule 80% of the traffic at most when the current network load is around 90%. Furthermore, the computational delay could reduce around 50%. © 2002-2012 IEEE.

关键词： Reinforcement learning

Reversible Data Hiding With Secret Encrypted Image Sharing and Adaptive Coding

学校读者我要写书评

暂无评论

IEEE Internet of Things Journal 2025年

作者： Fang, Guangtian Wang, Feng Zhao, Chenbin Qin, Chuan Chang, Ching-Chun Chang, Chin-Chen Fujian University of Technology College of Computer Science and Mathematics Fuzhou350118 China Fujian University of Technology College of Computer Science and Mathematics Key Laboratory of Big Data Mining and Applications Fuzhou350118 China Monash University Faculty of IT Department of Software Systems and Cybersecurity VIC3800 Australia Ministry of Education School of Cyber Science and Engineering Key Laboratory of Aerospace Information Security and Trusted Computing Wuhan430072 China University of Shanghai for Science and Technology School of Optical-Electrical and Computer Engineering Shanghai200093 China Feng Chia University Information and Communication Security Research Center Taichuang 40724 Taiwan Feng Chia University Department of Information Engineering and Computer Science Taichung40724 Taiwan

To ensure the security of image information and facilitate efficient management in the cloud, the utilization of reversible data hiding in encrypted images (RDHEI) has emerged as pivotal. However, most existing RDHEI schemes suffer from lower security and limited embedding capacity. To tackle these challenges, we propose a reversible data hiding with secret encrypted image sharing and adaptive coding scheme. Specifically, in the encryption phase, we introduce an improved secret sharing (SS) encryption method based on the chinese remainder theorem for polynomials (CRTP). This method not only improves the security of encrypted images but also vacates a larger room for embedding. In the embedding phase, we introduce an adaptive coding embedding approach using XOR preservation (XORP) and huffman coding, which provides high embedding capacity. Experimental results and security analysis demonstrate that our proposed encryption method achieves optimal values in security indicators for encrypted images, such as information entropy, histograms, NPCR and UACI. The proposed embedding method is superior to some state-of-the-art schemes in terms of embedding capacity. Furthermore, in datasets BOSSBase and BOWS2, the average embedding rates of the proposed embedding approach can reach 2.1745 bpp and 2.0656 bpp, respectively. © 2025 IEEE.

关键词： adaptive coding chinese remainder theorem for polynomials encrypted images Reversible data hiding secret sharing

DeepSeek: Paradigm Shifts and Technical Evolution in Large AI Models

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2025年第5期12卷 841-858页

作者： Xiong, Luolin Wang, Haofen Chen, Xi Sheng, Lu Xiong, Yun Liu, Jingping Xiao, Yanghua Chen, Huajun Han, Qing-Long Tang, Yang Ministry of Education Engineering Research Center of Process System Engineering East China University of Science and Technology Key Laboratory of Smart Manufacturing in Energy Chemical Process Shanghai 200237 China College of Design and Innovation Tongji University Shanghai 200092 China School of Computer Science Fudan University Shanghai Key Laboratory of Data Science Shanghai 200433 China School of Software Beihang University Beijing 100191 China School of Information Science and Engineering East China University of Science and Technology Shanghai 200237 China College of Computer Science and Technology Zhejiang University AZFT Joint Laboratory for Knowledge Engine Hangzhou Innovation Center Hangzhou 310058 China School of Science Computing and Engineering Technologies Swinburne University of Technology Melbourne 3122 VIC Australia

DeepSeek, a Chinese artificial intelligence (AI) startup, has released their V3 and R1 series models, which attracted global attention due to their low cost, high performance, and open-source advantages. This paper begins by reviewing the evolution of large AI models focusing on paradigm shifts, the mainstream large language model (LLM) paradigm, and the DeepSeek paradigm. Subsequently, the paper highlights novel algorithms introduced by DeepSeek, including multi-head latent attention (MLA), mixture-of-experts (MoE), multi-token prediction (MTP), and group relative policy optimization (GRPO). The paper then explores DeepSeek's engineering breakthroughs in LLM scaling, training, inference, and system-level optimization architecture. Moreover, the impact of DeepSeek models on the competitive AI landscape is analyzed, comparing them to mainstream LLMs across various fields. Finally, the paper reflects on the insights gained from DeepSeek's innovations and discusses future trends in the technical and engineering development of large AI models, particularly in data, training, and reasoning. © 2014 Chinese Association of Automation.

关键词： DeepSeek large AI models reasoning capability reinforcement learning test-time scaling

SIMAC: A Semantic-Driven Integrated Multimodal Sensing And Communication Framework

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Peng, Yubo Xiang, Luping Yang, Kun Jiang, Feibo Wang, Kezhi Wu, Dapeng Oliver State Key Laboratory of Novel Software Technology Nanjing University Nanjing China Suzhou China School of Information Science and Engineering Hunan Normal University Changsha China Department of Computer Science Brunel University London United Kingdom Department of Computer Science City University of Hong Kong Hong Kong

Traditional single-modality sensing faces limitations in accuracy and capability, and its decoupled implementation with communication systems increases latency in bandwidth-constrained environments. Additionally, single-task-oriented sensing systems fail to address users’ diverse demands. To overcome these challenges, we propose a semantic-driven integrated multimodal sensing and communication (SIMAC) framework. This framework leverages a joint source-channel coding architecture to achieve simultaneous sensing decoding and transmission of sensing results. Specifically, SIMAC first introduces a multimodal semantic fusion (MSF) network, which employs two extractors to extract semantic information from radar signals and images, respectively. MSF then applies cross-attention mechanisms to fuse these unimodal features and generate multimodal semantic representations. Secondly, we present a large language model (LLM)-based semantic encoder (LSE), where relevant communication parameters and multimodal semantics are mapped into a unified latent space and input to the LLM, enabling channel-adaptive semantic encoding. Thirdly, a task-oriented sensing semantic decoder (SSD) is proposed, in which different decoded heads are designed according to the specific needs of tasks. Simultaneously, a multi-task learning strategy is introduced to train the SIMAC framework, achieving diverse sensing services. Finally, experimental simulations demonstrate that the proposed framework achieves diverse sensing services and higher accuracy. Copyright © 2025, The Authors. All rights reserved.

关键词： Decoding

Semantic Communications with computer Vision Sensing for Edge Video Transmission

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Peng, Yubo Xiang, Luping Yang, Kun Wang, Kezhi Debbah, Mérouane State Key Laboratory of Novel Software Technology Nanjing University Nanjing China Suzhou China Department of Computer Science Brunel University London United Kingdom Department of Electrical Engineering and Computer Science The KU 6G Center Khalifa University Abu Dhabi127788 United Arab Emirates

Despite the widespread adoption of vision sensors in edge applications, such as surveillance, the transmission of video data consumes substantial spectrum resources. Semantic communication (SC) offers a solution by extracting and compressing information at the semantic level, preserving the accuracy and relevance of transmitted data while significantly reducing the volume of transmitted information. However, traditional SC methods face inefficiencies due to the repeated transmission of static frames in edge videos, exacerbated by the absence of sensing capabilities, which results in spectrum inefficiency. To address this challenge, we propose a SC with computer vision sensing (SCCVS) framework for edge video transmission. The framework first introduces a compression ratio (CR) adaptive SC (CRSC) model, capable of adjusting CR based on whether the frames are static or dynamic, effectively conserving spectrum resources. Additionally, we implement an object detection and semantic segmentation models-enabled sensing (OSMS) scheme, which intelligently senses the changes in the scene and assesses the significance of each frame through in-context analysis. Hence, The OSMS scheme provides CR prompts to the CRSC model based on real-time sensing results. Moreover, both CRSC and OSMS are designed as lightweight models, ensuring compatibility with resource-constrained sensors commonly used in practical edge applications. Experimental simulations validate the effectiveness of the proposed SCCVS framework, demonstrating its ability to enhance transmission efficiency without sacrificing critical semantic information. Copyright © 2025, The Authors. All rights reserved.

关键词： Semantic Segmentation

SAFL: Structure-Aware Personalized Federated Learning via Client-Specific Clustering and SCSI-Guided Model Pruning

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Li, Nan Wang, Xiaolu Du, Xiao Cai, Puyu Wang, Ting Engineering Research Center of Software/Hardware Co-Design Technology and Application Ministry of Education the Shangh ai Key Laboratory of Trustworthy Computing East China Normal University Shanghai200062 China Software Engineering Institute East China Normal University Shanghai200050 China Computer Science Department New York University New YorkNY10012 United States

Federated Learning (FL) enables clients to collaboratively train machine learning models without sharing local data, preserving privacy in diverse environments. While traditional FL approaches preserve privacy, they often struggle with high computational and communication overhead. To address these issues, model pruning is introduced as a strategy to streamline computations. However, existing pruning methods, when applied solely based on local data, often produce sub-models that inadequately reflect clients’ specific tasks due to data insufficiency. To overcome these challenges, this paper introduces SAFL (Structure-Aware Federated Learning), a novel framework that enhances personalized federated learning through client-specific clustering and Similar Client Structure Information (SCSI)-guided model pruning. SAFL employs a two-stage process: initially, it groups clients based on data similarities and uses aggregated pruning criteria to guide the pruning process, facilitating the identification of optimal sub-models. Subsequently, clients train these pruned models and engage in server-based aggregation, ensuring tailored and efficient models for each client. This method significantly reduces computational overhead while improving inference accuracy. Extensive experiments demonstrate that SAFL markedly diminishes model size and improves performance, making it highly effective in federated environments characterized by heterogeneous data. Copyright © 2025, The Authors. All rights reserved.

关键词： Federated learning

Sfmfold: A Multi-Modal Contrast Learning Model for Rna Secondary Structure Prediction

学校读者我要写书评

暂无评论

SSRN

SSRN 2025年

作者： Li, Ang Liu, Yuanning Zhang, Zhaoyang Li, Shuwang Dong, Hao Lv, Meng 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 College of Software Jilin University Changchun130012 China College of Information Engineering Chang’an University Xi’an710064 China

The secondary structure of RNA can regulate the interaction between RNA and protein and perform various biological tasks through specific folding shapes, which plays an important role in revealing biomolecular mechanisms and developing new vaccines and therapeutic drugs. However, existing RNA secondary structure prediction methods based on thermodynamics and traditional neural network models usually lack the ability to model long-distance dependencies of RNA molecules and cannot handle complex non-nested structures in RNA molecules. In this paper, we propose a multi-modal contrastive learning method SFMFold based on state space model, which captures long-distance interactions in RNA sequences through RNA sequence representation learning part, and models the structure of RNA molecules through RNA structure representation learning part. Finally, the features of the two modalities are aligned and deeply fused to obtain the final RNA molecule prediction map. We test SFMFold on several datasets, and the experiments show that our proposed model shows excellent performance in cross-family prediction and long sequence prediction tasks. In addition, SFMFold can also effectively predict non-nested structures such as pseudoknot with better accuracy than the SOTA methods. © 2025, The Authors. All rights reserved.

关键词： Prediction models

ATHENA: An In-vehicle CAN Intrusion Detection Framework Based on Physical Characteristics of Vehicle Systems

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wang, Kai Sun, Zhen Wang, Bailing Fan, Qilin Li, Ming Zhang, Hongke School of Computer Science and Technology Harbin Institute of Technology Weihai China Shandong Key Laboratory of Industrial Network Security China School of Big Data and Software Engineering Chongqing University Chongqing China Key Laboratory of Dependable Service Computing in Cyber Physical Society of Ministry of Education Chongqing University Chongqing China Jinan Key Laboratory of Distributed Databases Shandong Inspur Database Technology Co. Ltd Jinan China School of Electronic and Information Engineering Beijing Jiaotong University Beijing China

With the growing interconnection between In-Vehicle Networks (IVNs) and external environments, intelligent vehicles are increasingly vulnerable to sophisticated external network attacks. This paper proposes ATHENA, the first IVN intrusion detection framework that adopts a vehicle-cloud integrated architecture to achieve better security performance for the resource-constrained vehicular environment. Specifically, in the cloud with sufficient resources, ATHENA uses the clustering method of multi-distribution mixture model combined with deep data mining technology to generate the raw Payload Rule Bank of IVN CAN messages, and then improves the rule quality with the help of exploitation on the first-principled physical knowledge of the vehicle system, after which the payload rules are periodically sent to the vehicle terminal. At the vehicle terminal, a simple LSTM component is used to generate the Time Rule Bank representing the long-term time series dependencies and the periodic characteristics of CAN messages, but not for any detection tasks as in traditional usage scenarios, where only the generated time rules are the candidates for further IVN intrusion detection tasks. Based on both the payload and time rules generated from cloud and vehicle terminal, ATHENA can achieve efficient intrusion detection capability by simple rule-base matching operations, rather than using complex black-box reasoning of resource-intensive neural network models, which is in fact only used for rule logic generation phase instead of the actual intrusion detection phase in our framework. Comparative experimental results on the ROAD dataset, which is current the most outstanding real-world in-vehicle CAN dataset covering new instances of sophisticated and stealthy masquerade attacks, demonstrate ATHENA significantly outperforms the state-of-the-art IVN intrusion detection methods in detecting complex attacks. We make the code available at https://***/wangkai-tech23/ATHENA. Copyright

关键词： Network intrusion