语言大模型 / LLM - arXivDaily 专题

2407.16893 2026-03-04 cs.CY cs.AI cs.CL 92%

The Price of Prompting: Profiling Energy Use in Large Language Models Inference

提示的成本：大型语言模型推理中能源使用的 profiling

Erik Johannes Husom, Arda Goknil, Lwin Khin Shar, Sagar Sen

机构 * SINTEF ； Singapore Management University（新加坡管理大学）

专题命中效率与部署：large language model(title,abstract)；language model(title,abstract)；prompting(title)；LLM(abstract)

AI总结本文提出MELODI框架，用于分析大型语言模型推理过程中的能源消耗，通过构建数据集研究提示属性与能源支出的关系，为可持续LLM部署提供基础工具。

Comments 11 pages, 5 figures. Submitted to NeurIPS 2024. The released code and dataset are available at https://github.com/ejhusom/MELODI

2602.21652 2026-02-26 cs.CL cs.AI 92%

Sparsity Induction for Accurate Post-Training Pruning of Large Language Models

稀疏性诱导用于大语言模型的准确后训练剪枝

Minhao Jiang, Zhikai Li, Xuewen Liu, Jing Zhang, Mengjuan Chen, Qingyi Gu

机构 * Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）； School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）

专题命中效率与部署：large language model(title,abstract)；language model(title,abstract)；post-training(title,abstract)；分类 cs.CL、cs.AI

AI总结本文提出稀疏性诱导方法，通过增强分布和特征层面的稀疏性，提升大语言模型后训练剪枝的性能。

Comments 5 pages, 1 figure, 4 tables

2602.04913 2026-02-06 cs.LG cs.AI cs.SD 92%

A$^2$-LLM: An End-to-end Conversational Audio Avatar Large Language Model

A$^2$-LLM：一种端到端的对话音频虚拟形象大语言模型

Xiaolin Hu, Hang Yuan, Xinzhu Sang, Binbin Yan, Zhou Yu, Cong Huang, Kai Chen

机构 * State Key Laboratory of Information Photonics（信息光子学国家重点实验室）； Optical Communications, Beijing University of Posts（邮电大学光学通信学院）； Zhongguancun Institute of Artificial Intelligence, Beijing, China（中关村人工智能研究院）； School of Finance and Statistics, East China Normal University, Shanghai, China（东华大学金融与统计学院）

专题命中效率与部署：LLM(title,abstract)；large language model(title,abstract)；language model(title,abstract)；分类 cs.AI、cs.LG

AI总结 A$^2$-LLM通过统一框架联合推理语言、音频语调和3D面部运动，实现端到端的情感表达对话虚拟形象，提升实时效率与情感表现力。

Comments 13 pages, 3 figures

2512.01672 2025-12-02 cs.LG cs.AI 92%

ICAD-LLM: One-for-All Anomaly Detection via In-Context Learning with Large Language Models

ICAD-LLM: 一种通过大语言模型上下文学习实现的通用异常检测方法

Zhongyuan Wu, Jingyuan Wang, Zexuan Cheng, Yilong Zhou, Weizhi Wang, Juhua Pu, Chao Li, Changqing Ma

专题命中效率与部署：LLM(title,abstract)；large language model(title,abstract)；language model(title,abstract)；分类 cs.AI、cs.LG

AI总结 ICAD-LLM通过大语言模型的上下文学习能力，实现跨领域和模态的通用异常检测。

2509.18101 2025-11-12 cs.AI cs.LG 92%

A Cost-Benefit Analysis of On-Premise Large Language Model Deployment: Breaking Even with Commercial LLM Services

Guanzhong Pan, Vishal Chodnekar, Abinas Roy, Haibo Wang

机构 * Carnegie Mellon University（卡内基梅隆大学）

专题命中效率与部署：LLM(title,abstract)；large language model(title,abstract)；language model(title,abstract)；分类 cs.AI、cs.LG

2510.01225 2025-10-30 cs.CE cs.AI cs.CL cs.SE 92%

Utilizing Modern Large Language Models (LLM) for Financial Trend Analysis and Digest Creation

Andrei Lazarev, Dmitrii Sedov

专题命中效率与部署：LLM(title,abstract)；large language model(title,abstract)；language model(title,abstract)；分类 cs.CL、cs.AI

Comments This is the version of the article accepted for publication in SUMMA 2024 after peer review. The final, published version is available at IEEE Xplore: 10.1109/SUMMA64428.2024.10803746

Journal ref 2024 6th International Conference on Control Systems, Mathematical Modeling, Automation and Energy Efficiency (SUMMA), Lipetsk, Russian Federation, 2024, pp. 317-321

2510.03274 2025-10-07 cs.LG cs.AI 92%

Quant-dLLM: Post-Training Extreme Low-Bit Quantization for Diffusion Large Language Models

Tianao Zhang, Zhiteng Li, Xianglong Yan, Haotong Qin, Yong Guo, Yulun Zhang

机构 * Shanghai Jiao Tong University（上海交通大学）； ETH Zürich（苏黎世联邦理工学院）； South China University of Technology（华南理工大学）

专题命中效率与部署：large language model(title,abstract)；language model(title,abstract)；post-training(title,abstract)；分类 cs.AI、cs.LG

2406.15477 2025-08-08 cs.CL cs.AI 92%

CrisisSense-LLM: Instruction Fine-Tuned Large Language Model for Multi-label Social Media Text Classification in Disaster Informatics

Kai Yin, Bo Li, Chengkai Liu, Ali Mostafavi, Xia Hu

专题命中效率与部署：LLM(title,abstract)；large language model(title,abstract)；language model(title,abstract)；分类 cs.CL、cs.AI

Comments Relevant source code and data is available: https://github.com/KaiYin97/CrsisLLM

2502.13179 2025-08-07 cs.LG cs.AI 92%

PTQ1.61: Push the Real Limit of Extremely Low-Bit Post-Training Quantization Methods for Large Language Models

Jiaqi Zhao, Miao Zhang, Ming Wang, Yuzhang Shang, Kaihao Zhang, Weili Guan, Yaowei Wang, Min Zhang

机构 * Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））； Illinois Institute of Technology（伊利诺伊大学香槟分校）

专题命中效率与部署：large language model(title,abstract)；language model(title,abstract)；post-training(title,abstract)；分类 cs.AI、cs.LG

Comments 20 pages, 11 figures

2501.00055 2025-01-03 cs.CR cs.AI cs.CL 92%

LLM-Virus: Evolutionary Jailbreak Attack on Large Language Models

Miao Yu, Junfeng Fang, Yingjie Zhou, Xing Fan, Kun Wang, Shirui Pan, Qingsong Wen

专题命中效率与部署：LLM(title,abstract)；large language model(title,abstract)；language model(title,abstract)；分类 cs.CL、cs.AI

2412.06419 2024-12-10 cs.CL cs.AI 92%

LLM-BIP: Structured Pruning for Large Language Models with Block-Wise Forward Importance Propagation

Haihang Wu

专题命中效率与部署：LLM(title,abstract)；large language model(title,abstract)；language model(title,abstract)；分类 cs.CL、cs.AI

2410.13299 2024-12-02 cs.LG cs.AI 92%

LLM-Rank: A Graph Theoretical Approach to Pruning Large Language Models

David Hoffmann, Kailash Budhathoki, Matthaeus Kleindessner

专题命中效率与部署：LLM(title,abstract)；large language model(title,abstract)；language model(title,abstract)；分类 cs.AI、cs.LG

2410.10846 2024-10-16 cs.LG cs.CL 92%

Duo-LLM: A Framework for Studying Adaptive Computation in Large Language Models

Keivan Alizadeh, Iman Mirzadeh, Hooman Shahrokhi, Dmitry Belenko, Frank Sun, Minsik Cho, Mohammad Hossein Sekhavat, Moin Nabi, Mehrdad Farajtabar

专题命中效率与部署：LLM(title,abstract)；large language model(title,abstract)；language model(title,abstract)；分类 cs.CL、cs.LG

2408.03354 2024-10-02 cs.CR cs.AI cs.CL 92%

The Use of Large Language Models (LLM) for Cyber Threat Intelligence (CTI) in Cybercrime Forums

Vanessa Clairoux-Trepanier, Isa-May Beauchamp, Estelle Ruellan, Masarah Paquet-Clouston, Serge-Olivier Paquette, Eric Clay

专题命中效率与部署：LLM(title,abstract)；large language model(title,abstract)；language model(title,abstract)；分类 cs.CL、cs.AI

2409.20094 2024-10-01 cs.CL cs.AI 92%

Aggressive Post-Training Compression on Extremely Large Language Models

Zining Zhang, Yao Chen, Bingsheng He, Zhenjie Zhang

专题命中效率与部署：large language model(title,abstract)；language model(title,abstract)；post-training(title,abstract)；分类 cs.CL、cs.AI

2408.08682 2024-08-19 cs.AI cs.CL cs.CV 92%

LLM-PCGC: Large Language Model-based Point Cloud Geometry Compression

Yuqi Ye, Wei Gao

专题命中效率与部署：LLM(title,abstract)；large language model(title,abstract)；language model(title,abstract)；分类 cs.CL、cs.AI

2407.16667 2024-07-24 cs.CR cs.AI cs.CL 92%

RedAgent: Red Teaming Large Language Models with Context-aware Autonomous Language Agent

Huiyu Xu, Wenhui Zhang, Zhibo Wang, Feng Xiao, Rui Zheng, Yunhe Feng, Zhongjie Ba, Kui Ren

专题命中效率与部署：large language model(title,abstract)；language model(title,abstract)；language agent(title)；LLM(abstract)

2403.00863 2024-06-21 cs.IR cs.AI cs.CL 92%

LLM-Ensemble: Optimal Large Language Model Ensemble Method for E-commerce Product Attribute Value Extraction

Chenhao Fang, Xiaohan Li, Zezhong Fan, Jianpeng Xu, Kaushiki Nag, Evren Korpeoglu, Sushant Kumar, Kannan Achan

专题命中效率与部署：LLM(title,abstract)；large language model(title,abstract)；language model(title,abstract)；分类 cs.CL、cs.AI

Comments SIGIR 2024 industry track

2312.04916 2024-06-18 cs.LG cs.AI cs.DC 92%

EE-LLM: Large-Scale Training and Inference of Early-Exit Large Language Models with 3D Parallelism

Yanxi Chen, Xuchen Pan, Yaliang Li, Bolin Ding, Jingren Zhou

专题命中效率与部署：LLM(title,abstract)；large language model(title,abstract)；language model(title,abstract)；分类 cs.AI、cs.LG

Comments ICML 2024 camera-ready version

2401.14112 2024-03-05 cs.LG cs.AI cs.AR 92%

FP6-LLM: Efficiently Serving Large Language Models Through FP6-Centric Algorithm-System Co-Design

Haojun Xia, Zhen Zheng, Xiaoxia Wu, Shiyang Chen, Zhewei Yao, Stephen Youn, Arash Bakhtiari, Michael Wyatt, Donglin Zhuang, Zhongzhu Zhou, Olatunji Ruwase, Yuxiong He, Shuaiwen Leon Song

专题命中效率与部署：LLM(title,abstract)；large language model(title,abstract)；language model(title,abstract)；分类 cs.AI、cs.LG

Comments Adding URL link of the source code

2401.06951 2024-02-23 cs.CL cs.AI 92%

E^2-LLM: Efficient and Extreme Length Extension of Large Language Models

Jiaheng Liu, Zhiqi Bai, Yuanxing Zhang, Chenchen Zhang, Yu Zhang, Ge Zhang, Jiakai Wang, Haoran Que, Yukang Chen, Wenbo Su, Tiezheng Ge, Jie Fu, Wenhu Chen, Bo Zheng

专题命中效率与部署：LLM(title,abstract)；large language model(title,abstract)；language model(title,abstract)；分类 cs.CL、cs.AI

2212.06094 2023-05-31 cs.CL cs.AI 92%

Prompting Is Programming: A Query Language for Large Language Models

Luca Beurer-Kellner, Marc Fischer, Martin Vechev

专题命中效率与部署：large language model(title,abstract)；language model(title,abstract)；prompting(title,abstract)；分类 cs.CL、cs.AI

Comments To be published at PLDI'23: 44th ACM SIGPLAN International Conference on Programming Language Design and Implementation

2608.13767 2026-08-17 cs.AI cs.RO 新提交 92%

Simulation-Aware In-Context Policy Improvement for LLM-Aided Analog Layout Refinement

面向LLM辅助的模拟电路版图优化的感知仿真上下文内策略改进

Bingyang Liu, Ziming Wei, Xiaohan Gao, David Z. Pan

机构 * The University of Texas at Austin（德克萨斯大学奥斯汀分校）

专题命中效率与部署：LLM(title,title_cn)；large language model(abstract)；language model(abstract)；分类 cs.AI

AI总结针对LLM辅助模拟版图优化的样本效率问题，提出感知仿真的LLM多智能体框架，通过上下文内策略改进，仅需数十次仿真即可提升后版图性能，优于生成器启发式规则与贝叶斯优化方法。

Comments 7 pages, 3 figures. To appear in the Proceedings of the 2026 International Conference on LLM-Aided Design (ICLAD 2026)

2306.00978 2026-04-28 cs.CL 92%

AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

AWQ：基于激活的权重量化用于LLM压缩与加速

Ji Lin, Jiaming Tang, Haotian Tang, Shang Yang, Wei-Ming Chen, Wei-Chen Wang, Guangxuan Xiao, Xingyu Dang, Chuang Gan, Song Han

机构 * MIT（麻省理工学院）； Shanghai Jiao Tong University（上海交通大学）； NVIDIA（英伟达）； Tsinghua University（清华大学）； UMass Amherst（马萨诸塞大学阿姆赫斯特分校）

专题命中效率与部署：LLM(title,title_cn)；large language model(abstract)；language model(abstract)；分类 cs.CL

AI总结本文提出AWQ方法，通过识别重要权重通道减少量化误差，实现低比特权重量化，提升LLM的压缩与加速性能，并在多个基准测试中表现优异。

Comments MLSys 2024 Best Paper Award. Code available at: https://github.com/mit-han-lab/llm-awq

2503.12340 2025-03-18 cs.CL 92%

SVD-LLM V2: Optimizing Singular Value Truncation for Large Language Model Compression

Xin Wang, Samiul Alam, Zhongwei Wan, Hui Shen, Mi Zhang

专题命中效率与部署：LLM(title,abstract)；large language model(title,abstract)；language model(title,abstract)；分类 cs.CL

Comments NAACL 2025; Code available at AIoT-MLSys-Lab/SVD-LLM" target="_blank" rel="noopener">https://github.com/AIoT-MLSys-Lab/SVD-LLM

2608.03812 2026-08-05 cs.CV 新提交 92%

OmniPack: Unified Token Compression for Efficient Omni-modal Large Language Models

OmniPack：面向高效全模态大语言模型的统一令牌压缩方法

Wanshun Su, Yang Shi, Feihu Liu, Ziwen Yu, Yan Min, Zhuoran Zhang, Qixun Wang, Haotian Wang, Shixuan Liu, Yuanxing Zhang, Peng Wu, Chengfu Huo, Liang Ding

专题命中效率与部署：LLM(summary_cn,abstract)；large language model(title,abstract)；language model(title,abstract)

AI总结本文针对全模态大语言模型的高计算开销问题，提出无需训练的OmniPack框架，通过LLM前结构压缩与LLM内语义优化的协作，在5个基准上实现最优性能-效率权衡，在Qwen2.5-Omni-7B上大幅降低计算量且保持高性能。

Comments 16 pages, 5 figures, 15 tables

2608.01655 2026-08-04 cs.DC 新提交 92%

PrefixPlace: Provable Prefix Key-Value Placement for Large Language Model Serving under Heterogeneous Compute and Transfer Costs

PrefixPlace：异构计算与传输成本下大语言模型服务的可证明前缀键值放置方案

Zhiyu Wang, Rajkumar Buyya

专题命中效率与部署：LLM(summary_cn,abstract)；large language model(title,abstract)；language model(title,abstract)

AI总结针对异构计算与传输成本下LLM前缀KV放置的次优问题，提出PrefixPlace规划器，其性能接近最优且效率高，可提升RAG等场景的成本节省效果。

2607.29136 2026-08-03 cs.CV 新提交 92%

On the Efficacy of Self-Supervised Point Cloud Encoders for Efficient 3D Large Language Models

自监督点云编码器在高效3D大语言模型中的效能研究

Yao Zheng, Tian Zhang

机构 * Beijing University of Posts and Telecommunications（北京邮电大学）

专题命中效率与部署：LLM(summary_cn,abstract)；large language model(title,abstract)；language model(title,abstract)

AI总结该研究探究低成本自监督点云编码器能否替代昂贵多模态编码器用于3D-LLM，经实验发现其与架构存在强交互，为高性价比3D-LLM设计提供指南。

Comments 14 pages, 3 figures. This work has been previously released as a preprint on ChinaXiv (No. ChinaXiv:202607.00167, DOI: 10.12074/202607.00167)

2607.27918 2026-07-31 math.OC 新提交 92%

OptGraph: Large Language Models Enhanced Evolutionary Optimization Via Graph Retrieval-Augmented Generation

OptGraph：基于图检索增强生成的大语言模型增强进化优化

Xianchao Xiu, Jianhao Li, Huangyue Chen, Wanquan Liu

专题命中效率与部署：LLM(summary_cn,abstract)；large language model(title,abstract)；language model(title,abstract)

AI总结针对现有LLM自动化进化优化的局限，提出引入GraphRAG的OptGraph工作流，通过类型化图复用经验等方法，在基准数据集上较现有框架平均精确准确率提升8.9%。

2607.15297 2026-07-20 eess.IV cs.MM 新提交 92%

Large Language Model-Enhanced Multi-hop Parallel Image Semantic Communication

大语言模型增强的多跳并行图像语义通信

Bingyan Xie, Jihong Park, Rui Mao, Longyu Zhou, Tianhao Liang, Yongpeng Wu, Wenjun Zhang

专题命中效率与部署：LLM(summary_cn,abstract)；large language model(title,abstract)；language model(title,abstract)

AI总结研究提出LLM-MHPSC框架减轻多跳无线图像传输失真累积，设计粗到细残余压缩方案，开发LLM-RTO并提出自适应跳选择策略，实验表明其优于现有方案，为多跳语义通信应用提供灵活有效解决方案。

1. 效率与部署 22116 篇

The Price of Prompting: Profiling Energy Use in Large Language Models Inference

Sparsity Induction for Accurate Post-Training Pruning of Large Language Models

A$^2$-LLM: An End-to-end Conversational Audio Avatar Large Language Model

ICAD-LLM: One-for-All Anomaly Detection via In-Context Learning with Large Language Models

A Cost-Benefit Analysis of On-Premise Large Language Model Deployment: Breaking Even with Commercial LLM Services

Utilizing Modern Large Language Models (LLM) for Financial Trend Analysis and Digest Creation

Quant-dLLM: Post-Training Extreme Low-Bit Quantization for Diffusion Large Language Models

CrisisSense-LLM: Instruction Fine-Tuned Large Language Model for Multi-label Social Media Text Classification in Disaster Informatics

PTQ1.61: Push the Real Limit of Extremely Low-Bit Post-Training Quantization Methods for Large Language Models

LLM-Virus: Evolutionary Jailbreak Attack on Large Language Models

LLM-BIP: Structured Pruning for Large Language Models with Block-Wise Forward Importance Propagation

LLM-Rank: A Graph Theoretical Approach to Pruning Large Language Models

Duo-LLM: A Framework for Studying Adaptive Computation in Large Language Models

The Use of Large Language Models (LLM) for Cyber Threat Intelligence (CTI) in Cybercrime Forums

Aggressive Post-Training Compression on Extremely Large Language Models

LLM-PCGC: Large Language Model-based Point Cloud Geometry Compression

RedAgent: Red Teaming Large Language Models with Context-aware Autonomous Language Agent

LLM-Ensemble: Optimal Large Language Model Ensemble Method for E-commerce Product Attribute Value Extraction

EE-LLM: Large-Scale Training and Inference of Early-Exit Large Language Models with 3D Parallelism

FP6-LLM: Efficiently Serving Large Language Models Through FP6-Centric Algorithm-System Co-Design

E^2-LLM: Efficient and Extreme Length Extension of Large Language Models

Prompting Is Programming: A Query Language for Large Language Models

Simulation-Aware In-Context Policy Improvement for LLM-Aided Analog Layout Refinement

AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

SVD-LLM V2: Optimizing Singular Value Truncation for Large Language Model Compression

OmniPack: Unified Token Compression for Efficient Omni-modal Large Language Models

PrefixPlace: Provable Prefix Key-Value Placement for Large Language Model Serving under Heterogeneous Compute and Transfer Costs

On the Efficacy of Self-Supervised Point Cloud Encoders for Efficient 3D Large Language Models

OptGraph: Large Language Models Enhanced Evolutionary Optimization Via Graph Retrieval-Augmented Generation

Large Language Model-Enhanced Multi-hop Parallel Image Semantic Communication