语言大模型 / LLM - arXivDaily 专题

2507.02456 2025-07-04 cs.AR 89%

System-performance and cost modeling of Large Language Model training and inference

Wenzhe Guo, Joyjit Kundu, Uras Tos, Weijiang Kong, Giuliano Sisto, Timon Evenblij, Manu Perumkunnil

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

2402.10787 2025-07-03 cs.LG cs.AI cs.CL 89%

Squat: Quant Small Language Models on the Edge

Xuan Shen, Peiyan Dong, Zhenglun Kong, Yifan Gong, Changdi Yang, Zhaoyang Han, Yanyue Xie, Lei Lu, Cheng Lyu, Chao Wu, Yanzhi Wang, Pu Zhao

机构 * Northeastern University（东北大学）； MIT（麻省理工学院）； Harvard University（哈佛大学）

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

Comments Accepeted by ICCAD 2025

2401.12522 2025-07-02 cs.CL cs.AI cs.LG 89%

BiTA: Bi-Directional Tuning for Lossless Acceleration in Large Language Models

Feng Lin, Hanling Yi, Hongbin Li, Yifan Yang, Xiaotian Yu, Guangming Lu, Rong Xiao

机构 * Intellifusion Inc.（Intellifusion公司）； Harbin Institute of Technology（哈尔滨工业大学）

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

Comments An appendix has been included. Source code at https://github.com/linfeng93/BiTA

Journal ref Expert Systems with Applications 2025

2501.17905 2025-07-01 cs.LG cs.AI cs.CL 89%

DReSS: Data-driven Regularized Structured Streamlining for Large Language Models

Mingkuan Feng, Jinyang Wu, Shuai Zhang, Pengpeng Shao, Ruihan Jin, Zhengqi Wen, Jianhua Tao, Feihu Che

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

2505.06738 2025-06-17 cs.CR 89%

I Know What You Said: Unveiling Hardware Cache Side-Channels in Local Large Language Model Inference

Zibo Gao, Junjie Hu, Feng Guo, Yixin Zhang, Yinglong Han, Siyuan Liu, Haiyang Li, Zhiqiang Lv

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

Comments Submitted for review in January 22, 2025, revised under shepherding

2506.11135 2025-06-16 cs.CL cs.AI cs.LG cs.NE 89%

Large Language Models and Emergence: A Complex Systems Perspective

David C. Krakauer, John W. Krakauer, Melanie Mitchell

机构 * Santa Fe Institute（圣菲研究所）； Department of Neuroscience, Johns Hopkins School of Medicine（约翰霍普金斯医学院神经科学系）

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

2506.11120 2025-06-16 cs.CL cs.AI cs.LG 89%

SDMPrune: Self-Distillation MLP Pruning for Efficient Large Language Models

Hourun Zhu, Chengchao Shen

机构 * Department of Computer Science Central South University（计算机科学系中南大学）

专题命中效率与部署：large language model(title)；language model(title)；LLM(abstract)；post-training(abstract)

2506.10762 2025-06-13 cs.HC 89%

Integrating Large Language Models into Text Animation: An Intelligent Editing System with Inline and Chat Interaction

Bao Zhang, Zihan Li, Zhenglei Liu, Huanchen Wang, Yuxin Ma

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

2506.10426 2025-06-13 cs.SE 89%

Towards Understanding Bugs in Distributed Training and Inference Frameworks for Large Language Models

Xiao Yu, Haoxuan Chen, Feifei Niu, Xing Hu, Jacky Wai Keung, Xin Xia

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

2506.10268 2025-06-13 cs.CL cs.AI cs.LG 89%

Do Language Models Have Bayesian Brains? Distinguishing Stochastic and Deterministic Decision Patterns within Large Language Models

Andrea Yaoyun Cui, Pengfei Yu

机构 * University of Illinois Urbana Champaign（伊利诺伊大学厄巴纳-香槟分校）； Boson AI

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

2502.15010 2025-06-13 cs.CL cs.AI cs.CR cs.LG 89%

Obliviate: Efficient Unmemorization for Protecting Intellectual Property in Large Language Models

Mark Russinovich, Ahmed Salem

机构 * Microsoft Azure（微软Azure）； Microsoft（微软）

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

2506.05695 2025-06-11 cs.CL cs.AI cs.LG 89%

Being Strong Progressively! Enhancing Knowledge Distillation of Large Language Models through a Curriculum Learning Framework

Lingyuan Liu, Mengxiang Zhang

机构 * City University of Hong Kong（香港城市大学）； The University of Hong Kong（香港大学）

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

2501.14417 2025-06-10 cs.DC 89%

DeepServe: Serverless Large Language Model Serving at Scale

Junhao Hu, Jiang Xu, Zhixia Liu, Yulong He, Yuetao Chen, Hao Xu, Jiang Liu, Jie Meng, Baoquan Zhang, Shining Wan, Gengyuan Dan, Zhiyu Dong, Zhihao Ren, Changhong Liu, Tao Xie, Dayun Lin, Qin Zhang, Yue Yu, Hao Feng, Xusheng Chen, Yizhou Shan

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

2504.11199 2025-06-06 cs.CV 89%

Video Summarization with Large Language Models

Min Jung Lee, Dayoung Gong, Minsu Cho

机构 * Pohang University of Science and Technology (POSTECH)（釜山科学技术大学）； GenGenAI

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

Comments Accepted to CVPR 2025

2502.18504 2025-06-06 cs.CR cs.AI cs.CL cs.LG 89%

TurboFuzzLLM: Turbocharging Mutation-based Fuzzing for Effectively Jailbreaking Large Language Models in Practice

Aman Goel, Xian Carrie Wu, Zhe Wang, Dmitriy Bespalov, Yanjun Qi

机构 * Amazon Web Services, USA（亚马逊网络服务（美国））

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

Comments Oral presentation at NAACL 2025 industry track

2502.18845 2025-06-05 cs.CL cs.AI cs.LG 89%

Sliding Window Attention Training for Efficient Large Language Models

Zichuan Fu, Wentao Song, Yejing Wang, Xian Wu, Yefeng Zheng, Yingying Zhang, Derong Xu, Xuetao Wei, Tong Xu, Xiangyu Zhao

机构 * City University of Hong Kong（香港城市大学）； Xi’an Jiaotong University（西安交通大学）； Jarvis Research Center, Tencent YouTu Lab（腾讯优图实验室研究部）； Westlake University（西湖大学）； University of Science and Technology of China（中国科学技术大学）； Southern University of Science and Technology（南方科技大学）

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

Comments 14 pages, 5 figures

2502.16540 2025-06-05 cs.CL cs.AI cs.AR cs.IR cs.LG 89%

D2S-FLOW: Automated Parameter Extraction from Datasheets for SPICE Model Generation Using Large Language Models

Hong Cai Chen, Yi Pin Xu, Yang Zhang

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

Comments 14 pages, 18 figures

2506.02509 2025-06-04 cs.DB 89%

In-context Clustering-based Entity Resolution with Large Language Models: A Design Space Exploration

Jiajie Fu, Haitong Tang, Arijit Khan, Sharad Mehrotra, Xiangyu Ke, Yunjun Gao

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

Comments Accept by SIGMOD26

2506.01097 2025-06-03 cs.CV 89%

Generic Token Compression in Multimodal Large Language Models from an Explainability Perspective

Lei Lei, Jie Gu, Xiaokang Ma, Chu Tang, Jingmin Chen, Tong Xu

机构 * University of Science and Technology of China（中国科学技术大学）； Rightly Robotics（Rightly机器人公司）； Shanghai Innovation Institute（上海创新研究院）

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

2503.04992 2025-06-03 cs.LG cs.AI cs.CL 89%

Wanda++: Pruning Large Language Models via Regional Gradients

Yifan Yang, Kai Zhen, Bhavana Ganesh, Aram Galstyan, Goeric Huybrechts, Markus Müller, Jonas M. Kübler, Rupak Vignesh Swaminathan, Athanasios Mouchtaris, Sravan Babu Bodapati, Nathan Susanj, Zheng Zhang, Jack FitzGerald, Abhishek Kumar

机构 * University of California, Santa Barbara（加州大学圣芭芭拉分校）； Amazon AGI（亚马逊人工智能研究院）

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

Comments Paper accepted at ACL 2025 Findings

2411.00850 2025-05-30 cs.LG cs.AI cs.CL 89%

GWQ: Gradient-Aware Weight Quantization for Large Language Models

Yihua Shao, Yan Gu, Siyu Chen, Haiyang Liu, Zixian Zhu, Zijian Ling, Minxi Yan, Ziyang Yan, Chenyu Zhang, Michele Magno, Haotong Qin, Yan Wang, Jingcai Guo, Ling Shao, Hao Tang

机构 * PKU（北京大学）； CASIA（中国科学院自动化研究所）； THU（清华大学）； USTB（中国矿业大学）； UNITN（意大利那不勒斯）； ETHz（苏黎世联邦理工学院）； PolyU（香港理工大学）； UCAS（中国科学院大学）

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

2408.12757 2025-05-27 cs.DC 89%

NanoFlow: Towards Optimal Large Language Model Serving Throughput

Kan Zhu, Yufei Gao, Yilong Zhao, Liangyu Zhao, Gefei Zuo, Yile Gu, Dedong Xie, Tian Tang, Qinyu Xu, Zihao Ye, Keisuke Kamahori, Chien-Yu Lin, Ziren Wang, Stephanie Wang, Arvind Krishnamurthy, Baris Kasikci

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

2503.09291 2025-05-26 cs.CR 89%

Prompt Inference Attack on Distributed Large Language Model Inference Frameworks

Xinjian Luo, Ting Yu, Xiaokui Xiao

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

Comments Accepted for publication at CCS 2025

2505.14085 2025-05-21 cs.NI 89%

CE-LSLM: Efficient Large-Small Language Model Inference and Communication via Cloud-Edge Collaboration

Pengyan Zhu, Tingting Yang

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

Comments 14 pages, 7 figures including subplots

2407.11062 2025-05-20 cs.LG cs.AI cs.CL 89%

EfficientQAT: Efficient Quantization-Aware Training for Large Language Models

Mengzhao Chen, Wenqi Shao, Peng Xu, Jiahao Wang, Peng Gao, Kaipeng Zhang, Ping Luo

机构 * The University of Hong Kong（香港大学）； Shanghai AI Laboratory（上海人工智能实验室）

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

Comments ACL 2025 Main, camera ready version

2504.09897 2025-05-20 cs.CV 89%

TAMP: Token-Adaptive Layerwise Pruning in Multimodal Large Language Models

Jaewoo Lee, Keyang Xuan, Chanakya Ekbote, Sandeep Polisetty, Yi R. Fung, Paul Pu Liang

机构 * University of North Carolina Chapel Hill（北卡罗来纳大学教堂山分校）； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）； Massachusetts Institute of Technology（麻省理工学院）； University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）； Hong Kong University of Science and Technology（香港科学与技术大学）

专题命中效率与部署：large language model(title,abstract)；language model(title,abstract)；post-training(abstract)

Comments ACL Findings 2025

2405.09965 2025-05-20 cs.SE 89%

Large Language Models for Automated Web-Form-Test Generation: An Empirical Study

Tao Li, Chenhui Cui, Rubing Huang, Dave Towey, Lei Ma

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

Comments To be published in ACM Transactions on Software Engineering and Methodology

2505.10581 2025-05-19 econ.GN q-fin.EC 89%

The Impact of Large Language Models on Task Automation in Manufacturing Services

Jochen Wulf, Juerg Meierhofer

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

Comments arXiv admin note: text overlap with arXiv:2406.01407

2502.04405 2025-05-15 cs.LG cs.AI cs.CL 89%

FAS: Fast ANN-SNN Conversion for Spiking Large Language Models

Long Chen, Xiaotian Song, Andy Song, BaDong Chen, Jiancheng Lv, Yanan Sun

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

2505.06875 2025-05-13 cs.RO 89%

Towards Human-Centric Autonomous Driving: A Fast-Slow Architecture Integrating Large Language Model Guidance with Reinforcement Learning

Chengkai Xu, Jiaqi Liu, Yicheng Guo, Yuhang Zhang, Peng Hang, Jian Sun

机构 * College of Transportation, Tongji University（同济大学交通学院）

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

1. 效率与部署 22405 篇

System-performance and cost modeling of Large Language Model training and inference

Squat: Quant Small Language Models on the Edge

BiTA: Bi-Directional Tuning for Lossless Acceleration in Large Language Models

DReSS: Data-driven Regularized Structured Streamlining for Large Language Models

I Know What You Said: Unveiling Hardware Cache Side-Channels in Local Large Language Model Inference

Large Language Models and Emergence: A Complex Systems Perspective

SDMPrune: Self-Distillation MLP Pruning for Efficient Large Language Models

Integrating Large Language Models into Text Animation: An Intelligent Editing System with Inline and Chat Interaction

Towards Understanding Bugs in Distributed Training and Inference Frameworks for Large Language Models

Do Language Models Have Bayesian Brains? Distinguishing Stochastic and Deterministic Decision Patterns within Large Language Models

Obliviate: Efficient Unmemorization for Protecting Intellectual Property in Large Language Models

Being Strong Progressively! Enhancing Knowledge Distillation of Large Language Models through a Curriculum Learning Framework

DeepServe: Serverless Large Language Model Serving at Scale

Video Summarization with Large Language Models

TurboFuzzLLM: Turbocharging Mutation-based Fuzzing for Effectively Jailbreaking Large Language Models in Practice

Sliding Window Attention Training for Efficient Large Language Models

D2S-FLOW: Automated Parameter Extraction from Datasheets for SPICE Model Generation Using Large Language Models

In-context Clustering-based Entity Resolution with Large Language Models: A Design Space Exploration

Generic Token Compression in Multimodal Large Language Models from an Explainability Perspective

Wanda++: Pruning Large Language Models via Regional Gradients

GWQ: Gradient-Aware Weight Quantization for Large Language Models

NanoFlow: Towards Optimal Large Language Model Serving Throughput

Prompt Inference Attack on Distributed Large Language Model Inference Frameworks

CE-LSLM: Efficient Large-Small Language Model Inference and Communication via Cloud-Edge Collaboration

EfficientQAT: Efficient Quantization-Aware Training for Large Language Models

TAMP: Token-Adaptive Layerwise Pruning in Multimodal Large Language Models

Large Language Models for Automated Web-Form-Test Generation: An Empirical Study

The Impact of Large Language Models on Task Automation in Manufacturing Services

FAS: Fast ANN-SNN Conversion for Spiking Large Language Models

Towards Human-Centric Autonomous Driving: A Fast-Slow Architecture Integrating Large Language Model Guidance with Reinforcement Learning