检索结果-内蒙古大学图书馆

Unfolding the Headline: Iterative Self-Questioning for News Retrieval and Timeline Summarization

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wu, Weiqi Huang, Shen Jiang, Yong Xie, Pengjun Huang, Fei Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University China Tongyi Lab Alibaba Group China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3 China

In the fast-changing realm of information, the capacity to construct coherent timelines from extensive event-related content has become increasingly significant and challenging. The complexity arises in aggregating related documents to build a meaningful event graph around a central topic. This paper proposes CHRONOS - Causal Headline Retrieval for Open-domain News Timeline SummarizatiOn via Iterative Self-Questioning, which offers a fresh perspective on the integration of Large Language Models (LLMs) to tackle the task of Timeline Summarization (TLS). By iteratively reflecting on how events are linked and posing new questions regarding a specific news topic to gather information online or from an offline knowledge base, LLMs produce and refresh chronological summaries based on documents retrieved in each round. Furthermore, we curate Open-TLS, a novel dataset of timelines on recent news topics authored by professional journalists to evaluate open-domain TLS where information overload makes it impossible to find comprehensive relevant documents from the web. Our experiments indicate that CHRONOS is not only adept at open-domain timeline summarization, but it also rivals the performance of existing state-of-the-art systems designed for closed-domain applications, where a related news corpus is provided for summarization. Copyright © 2025, The Authors. All rights reserved.

关键词： Modeling languages

Efficient Resource Allocation in Computing Power Networks Considering Similar Task Merging: A Lyapunov Optimization-Based DRL Approach

学校读者我要写书评

暂无评论

IEEE Internet of Things Journal 2025年

作者： Jia, Zhonghai Xue, Junxiao Shi, Lei Li, Jie He, Mengyang Zhejiang Lab Research Center for Space Computing System Hangzhou310000 China Zhengzhou University School of Cyber Science and Engineering Zhengzhou450002 China SongShan Laboratory Zhengzhou450040 China Shanghai Jiao Tong University Department of Computer Science and Engineering Shanghai200240 China Shanghai Key Laboratory of Trusted Data Circulation and Governance Web3 Shanghai China

The cloud-edge-terminal architecture relies on hierarchy for resource allocation but lacks global optimization. The computing power network (CPN) introduces a new distributed computing paradigm, integrating cross-domain, heterogeneous resources for global scheduling. However, most CPN research focuses on task optimization during resource allocation, while neglecting the similarity of random tasks before the allocation stage. Additionally, fragmented CPN resources and complex task demands pose challenges to global load balancing. This paper proposes a deep reinforcement learning framework with task merging and congestion avoidance for on-demand resource allocation. Specifically, a low-complexity similar task merging algorithm reduces redundant resource consumption during task preprocessing. In task offloading, the principal neighborhood aggregated graph neural network captures CPN's intricate features. Lyapunov optimization, integrated into a multi-threaded training framework, minimizes resource backlog congestion. A carefully designed reward function balances multiple objectives, enhancing computing resource utilization efficiency and ensuring system stability. Theoretical analysis shows that with control parameter V, the trade-off between resource utilization efficiency and system stability follows the relationship O(1/V), O(V). Extensive experiments demonstrate a 33.5% improvement in resource utilization efficiency and a 62.7% increase in task offloading success rates with respect to those in state-of-the-art algorithms. The proposed algorithm exhibits robustness and effectiveness, particularly in high-load and real network topologies. © 2014 IEEE.

关键词： Computing power

LESA: Learnable LLM Layer Scaling-Up

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Yang, Yifei Cao, Zouying Ma, Xinbei Yao, Yao Qin, Libo Chen, Zhi Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3 China School of Computer Science and Engineering Central South University China ByteDance China

Training Large Language Models (LLMs) from scratch requires immense computational resources, making it prohibitively expensive. Model scaling-up offers a promising solution by leveraging the parameters of smaller models to create larger ones. However, existing depth scaling-up methods rely on empirical heuristic rules for layer duplication, which result in poorer initialization and slower convergence during continual pre-training. We propose LESA, a novel learnable method for depth scaling-up. By concatenating parameters from each layer and applying Singular Value Decomposition, we uncover latent patterns between layers, suggesting that inter-layer parameters can be learned. LESA uses a neural network to predict the parameters inserted between adjacent layers, enabling better initialization and faster training. Experiments show that LESA outperforms existing baselines, achieving superior performance with less than half the computational cost during continual pre-training. Extensive analyses demonstrate its effectiveness across different model sizes and tasks.1 Copyright © 2025, The Authors. All rights reserved.

关键词： Multilayer neural networks

Front-running Attacks in Hash-Based Transaction Sharding Blockchains

学校读者我要写书评

暂无评论

Front-running Attacks in Hash-Based Transaction Sharding Blo...

IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)

作者： Yusen Wang Jiong Lou Zihan Wang Jie Li Department of Computer Science and Engineering Shanghai Jiao Tong University China Blockchain Advanced Research Center Shanghai Jiao Tong University (Wuxi) China Shanghai Key Laboratory of Trusted Data Circulation and Governance and Web3 China

ISBN: (数字)9798331506209

ISBN: (纸本)9798331506216

Sharding is one of the prominent solutions to solve the scalability problem of traditional blockchains. By dividing the blockchain network into independent shards, transactions in different shards can be executed in parallel, improving the throughput of the blockchain. However, sharding also brings security issues. In a hash-based transaction sharding system, the output shard of a transaction is determined by the hash value of the transaction. Unfortunately, we show that this hashbased transaction assignment strategy can be easily exploited by attackers to conduct front-running attacks. Attackers can take advantage of the execution differences between different shards and the extra processing time of cross-shard transactions to make the attacker’s transaction executed and committed before the victim’s transaction, thereby obtaining the benefits that originally belonged to the victim. We also propose a flooding front-running attack, which introduces a single-shard flooding attack to enhance the front-running attack. Specifically, injecting a large number of junk transactions into the shard where the victim’s transaction is located can significantly extend the execution time of the victim’s transaction. We demonstrate the feasibility and practical effects of these two attacks through experiments on RapidChain, which show that a single-shard flooding attack can increase the success rate of a front-running attack by 12%. Finally, we discuss two possible mitigation measures and the cost of two proposed attacks.

关键词： Sharding Privacy Costs Prevention and mitigation Scalability Throughput Blockchains Floods Security

GCC: Optimizing Space Efficiency and Read Latency of SSDs with Workload-Aware Garbage Collection Aided Compression

学校读者我要写书评

暂无评论

GCC: Optimizing Space Efficiency and Read Latency of SSDs wi...

IEEE International Conference on Computer Design: VLSI in Computers and Processors, (ICCD)

作者： Linhui Liu Yunfei Gu Chenhao Zhu Chentao Wu Jie Li Minyi Guo Department of Computer Science and Engineering Shanghai Jiao Tong University China Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3 Shanghai Jiao Tong University Yancheng Blockchain Research Institute Hengyang China

ISBN: (数字)9798350380408

ISBN: (纸本)9798350380415

data compression is increasingly employed to enhance throughput and space efficiency in flash-based storage systems, which are critical for data-intensive applications. Current intra-SSD compression techniques operate transparently with respect to the file system and contribute to improving the lifetime of SSDs. These approaches typically avoid compressing read-hot data to reduce the latency penalties associated with decompression. However, the read-hot data remain uncompressed even after turning into cold data, thereby reducing overall compression effectiveness and diminishing space efficiency. Moreover, when previously compressed cold data become read-hot, it necessitates frequent decompression, which increases the read latency. To address the above problems, we propose a novel Garbage Collection aided Compression (GCC) scheme, to optimize space efficiency and mitigate read latency for compression-supported SSDs. The key idea of GCC is exploiting the valid page migration during garbage collection to enable background compression and decompression. Throughout the garbage collection process, the migrated valid pages can potentially be compressed or decompressed, which progressively improves space efficiency and minimizes the need for decompression during read operations. Performance evaluations conducted using MQSim simulator demonstrate that, compared to the typical compression schemes, GCC reduces the read and write latency by 25.27% and 9.43% on average and improves the space efficiency by 15.01% on average.

关键词： Performance evaluation File systems data compression Turning Throughput Time factors

CoCo-Agent: A Comprehensive Cognitive MLLM Agent for Smartphone GUI Automation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ma, Xinbei Zhang, Zhuosheng Zhao, Hai School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University China Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3 China

Multimodal large language models (MLLMs) have shown remarkable potential as human-like autonomous language agents to interact with real-world environments, especially for graphical user interface (GUI) automation. However, those GUI agents require comprehensive cognition ability including exhaustive perception and reliable action response. We propose a Comprehensive Cognitive LLM Agent, CoCo-Agent, with two novel approaches, comprehensive environment perception (CEP) and conditional action prediction (CAP), to systematically improve the GUI automation performance. First, CEP facilitates the GUI perception through different aspects and granularity, including screenshots and complementary detailed layouts for the visual channel and historical actions for the textual channel. Second, CAP decomposes the action prediction into sub-problems: action type prediction and action target conditioned on the action type. With our technical design, our agent achieves new state-of-the-art performance on AITW and META-GUI benchmarks, showing promising abilities in realistic scenarios. Code is available at https://***/xbmxb/CoCo-Agent. Copyright © 2024, The Authors. All rights reserved.

关键词： Graphical user interfaces

GKT: A Novel Guidance-Based Knowledge Transfer Framework For Efficient Cloud-edge Collaboration LLM Deployment

学校读者我要写书评

暂无评论

arXiv 2024年

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

The burgeoning size of Large Language Models (LLMs) has led to enhanced capabilities in generating responses, albeit at the expense of increased inference times and elevated resource demands. Existing methods of acceleration, predominantly hinged on knowledge distillation, generally necessitate fine-tuning of considerably large models, posing a challenge for average users. Furthermore, present techniques for expediting inference and reducing costs operate independently. To address these issues, we introduce a novel and intuitive Guidance-based Knowledge Transfer (GKT) framework. This approach leverages a larger LLM as a "teacher" to create guidance prompts, paired with a smaller "student" model to finalize responses. Remarkably, GKT requires no fine-tuning and doesn’t necessitate the teacher and student models to have the same vocabulary, allowing for extensive batch generation to accelerate the process while ensuring user customization. GKT can be seamlessly integrated into cloud-edge collaboration architectures, and is versatile enough for plug-and-play application across various models. When utilizing ChatGPT as teacher model and Llama2-70B as the student model, we can achieve 95.00% of ChatGPT’s performance at 52% of the cost. The results highlight substantial enhancements in accuracy and processing speed on the GSM8K and CSQA datasets, surpassing the performance of using either the student or teacher models in isolation. Our code is publicly available at https://***/Zoeyyao27/GKT © 2024, CC BY.

关键词： Distillation

On the Robustness of Editing Large Language Models

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ma, Xinbei Ju, Tianjie Qiu, Jiyang Zhang, Zhuosheng Zhao, Hai Liu, Lifeng Wang, Yulong School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University China Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3 China Baichuan Intelligent Technology China

Large language models (LLMs) have played a pivotal role in building communicative AI, yet they encounter the challenge of efficient updates. Model editing enables the manipulation of specific knowledge memories and the behavior of language generation without retraining. However, the robustness of model editing remains an open question. This work seeks to understand the strengths and limitations of editing methods, facilitating practical applications of communicative AI. We focus on three key research questions. RQ1: Can edited LLMs behave consistently resembling communicative AI in realistic situations? RQ2: To what extent does the rephrasing of prompts lead LLMs to deviate from the edited knowledge memory? RQ3: Which knowledge features are correlated with the performance and robustness of editing? Our empirical studies uncover a substantial disparity between existing editing methods and the practical application of LLMs. On rephrased prompts that are flexible but common in realistic applications, the performance of editing experiences a significant decline. Further analysis shows that more popular knowledge is memorized better, easier to recall, and more challenging to edit effectively. Copyright © 2024, The Authors. All rights reserved.

关键词： Computational linguistics

PyramidInfer: Pyramid KV Cache Compression for High-throughput LLM Inference

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yang, Dongjie Han, Xiaodong Gao, Yan Hu, Yao Zhang, Shilin Zhao, Hai Shanghai Jiao Tong University China Xiaohongshu Inc. China South China University of Technology China The Department of Computer Science and Engineering Shanghai Jiao Tong University Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3 China

Large Language Models (LLMs) have shown remarkable comprehension abilities but face challenges in GPU memory usage during inference, hindering their scalability for real-time applications like chatbots. To accelerate inference, we store computed keys and values (KV cache) in the GPU memory. Existing methods study the KV cache compression to reduce memory by pruning the pre-computed KV cache. However, they neglect the inter-layer dependency between layers and huge memory consumption in pre-computation. To explore these deficiencies, we find that the number of crucial keys and values that influence future generations decreases layer by layer and we can extract them by the consistency in attention weights. Based on the findings, we propose PyramidInfer, a method that compresses the KV cache by layer-wise retaining crucial context. PyramidInfer saves significant memory by computing fewer keys and values without sacrificing performance. Experimental results show PyramidInfer improves 2.2x throughput compared to Accelerate with over 54% GPU memory reduction in KV cache. Our code is available in https://***/mutonix/ pyramidinfer. © 2024, CC BY.

关键词： Cache memory