语言大模型 / LLM - arXivDaily 专题

2411.17116 2025-06-02 cs.CL cs.AI cs.LG 85%

Star Attention: Efficient LLM Inference over Long Sequences

Shantanu Acharya, Fei Jia, Boris Ginsburg

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

Comments Accepted at ICML 2025

2505.22063 2025-05-29 cs.SD eess.AS 85%

Weakly Supervised Data Refinement and Flexible Sequence Compression for Efficient Thai LLM-based ASR

Mingchen Shao, Xinfa Zhu, Chengyou Wang, Bingshen Mu, Hai Li, Ying Yan, Junhui Liu, Danming Xie, Lei Xie

机构 * Northwestern Polytechnical University（西北工业大学）； iQIYI

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

Comments Accepted by INTERSPEECH 2025

2505.21518 2025-05-29 cs.NI 85%

Resilient LLM-Empowered Semantic MAC Protocols via Zero-Shot Adaptation and Knowledge Distillation

Yongjun Kim, Jihong Park, Mehdi Bennis, Junil Choi

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

2401.17644 2025-05-27 cs.DC cs.PF 85%

BurstGPT: A Real-world Workload Dataset to Optimize LLM Serving Systems

Yuxin Wang, Yuhan Chen, Zeyu Li, Xueze Kang, Yuchu Fang, Yeju Zhou, Yang Zheng, Zhenheng Tang, Xin He, Rui Guo, Xin Wang, Qiang Wang, Amelie Chi Zhou, Xiaowen Chu

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

2505.12392 2025-05-27 cs.CL cs.AI cs.LG 85%

SLOT: Sample-specific Language Model Optimization at Test-time

Yang Hu, Xingyu Zhang, Xueji Fang, Zhiyang Chen, Xiao Wang, Huatian Zhang, Guojun Qi

机构 * Westlake University（西湖大学）； University of Washington（华盛顿大学）； USTC（中国科学技术大学）

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

2501.04285 2025-05-27 cs.IT eess.SP math.IT 85%

Separate Source Channel Coding Is Still What You Need: An LLM-based Rethinking

Tianqi Ren, Rongpeng Li, Ming-min Zhao, Xianfu Chen, Guangyi Liu, Yang Yang, Zhifeng Zhao, Honggang Zhang

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

Journal ref ZTE Communications, vol. 23, no. 1, pp. 30-44, Mar. 2025

2408.14293 2025-05-27 cs.CR 85%

Investigating the Effectiveness of Bayesian Spam Filters in Detecting LLM-modified Spam Mails

Malte Josten, Torben Weis

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

Comments EAI International Conference on Digital Forensics & Cyber Crime 2024

2505.16502 2025-05-27 cs.DC cs.NI 85%

Recursive Offloading for LLM Serving in Multi-tier Networks

Zhiyuan Wu, Sheng Sun, Yuwei Wang, Min Liu, Bo Gao, Jinda Lu, Zheming Yang, Tian Wen

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

Comments 7 figures, 3 tables

2505.17787 2025-05-26 cs.AR 85%

Titanus: Enabling KV Cache Pruning and Quantization On-the-Fly for LLM Acceleration

Peilin Chen, Xiaoxuan Yang

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

Comments Accepted to GLSVLSI 2025

2505.11945 2025-05-23 cs.CV 85%

Top-Down Compression: Revisit Efficient Vision Token Projection for Visual Instruction Tuning

Bonan li, Zicheng Zhang, Songhua Liu, Weihao Yu, Xinchao Wang

机构 * UCAS（中国科学技术大学）； NUS（新加坡国立大学）

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

Comments Under Review

2505.14336 2025-05-22 eess.AS cs.CV cs.MM cs.SD 85%

Scaling and Enhancing LLM-based AVSR: A Sparse Mixture of Projectors Approach

Umberto Cappellazzo, Minsu Kim, Stavros Petridis, Daniele Falavigna, Alessio Brutti

机构 * Imperial College London（伦敦帝国学院）； Meta AI ； Fondazione Bruno Kessler（布鲁诺·克塞尔基金会）

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

Comments Interspeech 2025

2505.11890 2025-05-20 cs.CE 85%

LLM-Enhanced Feature Engineering for Multi-Factor Electricity Price Predictions

Haochen Xue, Chenghao Liu, Chong Zhang, Yuxuan Chen, Angxiao Zong, Zhaodong Wu, Yulong Li, Jiayi Liu, Kaiyu Liang, Zhixiang Lu, Ruobing Li, Jionglong Su

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

2501.15087 2025-05-20 cs.IR 85%

Multi-Grained Patch Training for Efficient LLM-based Recommendation

Jiayi Liao, Ruobing Xie, Sihang Li, Xiang Wang, Xingwu Sun, Zhanhui Kang, Xiangnan He

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

2505.09319 2025-05-15 cs.PF 85%

Statistical Modeling and Uncertainty Estimation of LLM Inference Systems

Kaustabha Ray, Nelson Mimura Gonzalez, Bruno Wassermann, Rachel Tzoref-Brill, Dean H. Lorenz

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

2505.04521 2025-05-08 cs.SE 85%

Comparative Analysis of Carbon Footprint in Manual vs. LLM-Assisted Code Development

Kuen Sum Cheung, Mayuri Kaul, Gunel Jahangirova, Mohammad Reza Mousavi, Eric Zie

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

2505.00342 2025-05-02 cs.SE 85%

LLMPrism: Black-box Performance Diagnosis for Production LLM Training Platforms

Zhihan Jiang, Rui Ren, Guangba Yu, Yulun Wu, Wenwei Gu, Yichen Li, Yujie Huang, Cong Feng, Zengyin Yang, Yongqiang Yang, Michael R. Lyu

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

2502.16473 2025-05-02 cs.AR 85%

TerEffic: Highly Efficient Ternary LLM Inference on FPGA

Chenyang Yin, Zhenyu Bai, Pranav Venkatram, Shivam Aggarwal, Zhaoying Li, Tulika Mitra

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

2411.17651 2025-05-01 cs.DC 85%

APEX: An Extensible and Dynamism-Aware Simulator for Automated Parallel Execution in LLM Serving

Yi-Chien Lin, Woosuk Kwon, Ronald Pineda, Fanny Nina Paravecino

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

2504.19333 2025-04-30 cs.CL cs.AI cs.LG 85%

Unified Multi-Task Learning & Model Fusion for Efficient Language Model Guardrailing

James O' Neill, Santhosh Subramanian, Eric Lin, Vaikkunth Mugunthan

机构 * DynamoAI San Francisco, California, USA（DynamoAI旧金山加州）

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

2503.18869 2025-04-23 cs.AR 85%

Reimagining Memory Access for LLM Inference: Compression-Aware Memory Controller Design

Rui Xie, Asad Ul Haq, Linsen Ma, Yunhua Fang, Zirak Burzin Engineer, Liu Liu, Tong Zhang

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

Comments 9 pages, 11 figures

2402.15390 2025-04-15 cs.LG cs.AI cs.CL 85%

Explorations of Self-Repair in Language Models

Cody Rushing, Neel Nanda

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

Comments ICML 2024

Journal ref Proceedings of the 41st International Conference on Machine Learning, PMLR 235:42836-42855, 2024

2504.07431 2025-04-15 cs.NI 85%

LLM-Enabled Data Transmission in End-to-End Semantic Communication

Shavbo Salehi, Melike Erol-Kantarci, Dusit Niyato

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

2504.07479 2025-04-11 cs.AR 85%

UniCAIM: A Unified CAM/CIM Architecture with Static-Dynamic KV Cache Pruning for Efficient Long-Context LLM Inference

Weikai Xu, Wenxuan Zeng, Qianqian Huang, Meng Li, Ru Huang

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

2504.03661 2025-04-09 cs.DC 85%

MILLION: Mastering Long-Context LLM Inference Via Outlier-Immunized KV Product Quantization

Zongwu Wang, Peng Xu, Fangxin Liu, Yiwei Hu, Qingxiao Sun, Gezi Li, Cheng Li, Xuan Wang, Li Jiang, Haibing Guan

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

Comments 7 pages, 7 figures and 4 tables

2504.02165 2025-04-04 cs.CE 85%

Responsible Innovation: A Strategic Framework for Financial LLM Integration

Ahmadreza Tavasoli, Maedeh Sharbaf, Seyed Mohamad Madani

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

Comments 27 pages, 3 figures

2410.02757 2025-04-03 cs.CV 85%

Loong: Generating Minute-level Long Videos with Autoregressive Language Models

Yuqing Wang, Tianwei Xiong, Daquan Zhou, Zhijie Lin, Yang Zhao, Bingyi Kang, Jiashi Feng, Xihui Liu

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

Comments Project page: https://yuqingwang1029.github.io/Loong-video

2503.06930 2025-04-01 cs.CV 85%

Post-Training Quantization for Diffusion Transformer via Hierarchical Timestep Grouping

Ning Ding, Jing Han, Yuchuan Tian, Chao Xu, Kai Han, Yehui Tang

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

2411.06364 2025-03-26 cs.DC 85%

EconoServe: Maximizing Multi-Resource Utilization with SLO Guarantees in LLM Serving

Haiying Shen, Tanmoy Sen

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

Comments 14 pages

2503.18292 2025-03-25 cs.DC 85%

Jenga: Effective Memory Management for Serving LLM with Heterogeneity

Chen Zhang, Kuntai Du, Shu Liu, Woosuk Kwon, Xiangxi Mo, Yufeng Wang, Xiaoxuan Liu, Kaichao You, Zhuohan Li, Mingsheng Long, Jidong Zhai, Joseph Gonzalez, Ion Stoica

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

Comments 16 pages, 19 figures

2404.13558 2025-03-25 cs.CV 85%

LASER: Tuning-Free LLM-Driven Attention Control for Efficient Text-conditioned Image-to-Animation

Haoyu Zheng, Wenqiao Zhang, Yaoke Wang, Juncheng Li, Zheqi Lv, Xin Min, Mengze Li, Dongping Zhang, Siliang Tang, Yueting Zhuang

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

1. 效率与部署 22368 篇

Star Attention: Efficient LLM Inference over Long Sequences

Weakly Supervised Data Refinement and Flexible Sequence Compression for Efficient Thai LLM-based ASR

Resilient LLM-Empowered Semantic MAC Protocols via Zero-Shot Adaptation and Knowledge Distillation

BurstGPT: A Real-world Workload Dataset to Optimize LLM Serving Systems

SLOT: Sample-specific Language Model Optimization at Test-time

Separate Source Channel Coding Is Still What You Need: An LLM-based Rethinking

Investigating the Effectiveness of Bayesian Spam Filters in Detecting LLM-modified Spam Mails

Recursive Offloading for LLM Serving in Multi-tier Networks

Titanus: Enabling KV Cache Pruning and Quantization On-the-Fly for LLM Acceleration

Top-Down Compression: Revisit Efficient Vision Token Projection for Visual Instruction Tuning

Scaling and Enhancing LLM-based AVSR: A Sparse Mixture of Projectors Approach

LLM-Enhanced Feature Engineering for Multi-Factor Electricity Price Predictions

Multi-Grained Patch Training for Efficient LLM-based Recommendation

Statistical Modeling and Uncertainty Estimation of LLM Inference Systems

Comparative Analysis of Carbon Footprint in Manual vs. LLM-Assisted Code Development

LLMPrism: Black-box Performance Diagnosis for Production LLM Training Platforms

TerEffic: Highly Efficient Ternary LLM Inference on FPGA

APEX: An Extensible and Dynamism-Aware Simulator for Automated Parallel Execution in LLM Serving

Unified Multi-Task Learning & Model Fusion for Efficient Language Model Guardrailing

Reimagining Memory Access for LLM Inference: Compression-Aware Memory Controller Design

Explorations of Self-Repair in Language Models

LLM-Enabled Data Transmission in End-to-End Semantic Communication

UniCAIM: A Unified CAM/CIM Architecture with Static-Dynamic KV Cache Pruning for Efficient Long-Context LLM Inference

MILLION: Mastering Long-Context LLM Inference Via Outlier-Immunized KV Product Quantization

Responsible Innovation: A Strategic Framework for Financial LLM Integration

Loong: Generating Minute-level Long Videos with Autoregressive Language Models

Post-Training Quantization for Diffusion Transformer via Hierarchical Timestep Grouping

EconoServe: Maximizing Multi-Resource Utilization with SLO Guarantees in LLM Serving

Jenga: Effective Memory Management for Serving LLM with Heterogeneity

LASER: Tuning-Free LLM-Driven Attention Control for Efficient Text-conditioned Image-to-Animation