语言大模型 / LLM - arXivDaily 专题

2503.14882 2025-03-20 cs.DC eess.SP 85%

Communication-Efficient Distributed On-Device LLM Inference Over Wireless Networks

Kai Zhang, Hengtao He, Shenghui Song, Jun Zhang, Khaled B. Letaief

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

Comments arXiv admin note: text overlap with arXiv:2502.12559

2407.16970 2025-03-19 cs.CL cs.AI cs.LG 85%

Towards Aligning Language Models with Textual Feedback

Saüc Abadal Lloret, Shehzaad Dhuliawala, Keerthiram Murugesan, Mrinmaya Sachan

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

Comments Accepted to EMNLP 2024

2503.12062 2025-03-18 cs.IR 85%

Genicious: Contextual Few-shot Prompting for Insights Discovery

Vineet Kumar, Ronald Tony, Darshita Rathore, Vipasha Rana, Bhuvanesh Mandora, Kanishka, Chetna Bansal, Anindya Moitra

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

Comments 5 pages, 3 figures, CODS-COMAD Dec 24, Jodhpur, India

2503.10377 2025-03-14 cs.DC 85%

SPPO:Efficient Long-sequence LLM Training via Adaptive Sequence Pipeline Parallel Offloading

Qiaoling Chen, Shenggui Li, Wei Gao, Peng Sun, Yonggang Wen, Tianwei Zhang

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

2503.10041 2025-03-14 cs.SE 85%

NumScout: Unveiling Numerical Defects in Smart Contracts using LLM-Pruning Symbolic Execution

Jiachi Chen, Zhenzhe Shao, Shuo Yang, Yiming Shen, Yanlin Wang, Ting Chen, Zhenyu Shan, Zibin Zheng

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

2503.09758 2025-03-14 cs.RO cs.MA 85%

Multi-Agent LLM Actor-Critic Framework for Social Robot Navigation

Weizheng Wang, Ike Obi, Byung-Cheol Min

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

2503.08619 2025-03-12 cs.CV 85%

LightGen: Efficient Image Generation through Knowledge Distillation and Direct Preference Optimization

Xianfeng Wu, Yajing Bai, Haoze Zheng, Harold Haodong Chen, Yexin Liu, Zihao Wang, Xuran Ma, Wen-Jie Shu, Xianzu Wu, Harry Yang, Ser-Nam Lim

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

Comments Code: https://github.com/XianfengWu01/LightGen

2503.08461 2025-03-12 cs.MM cs.DC 85%

FastCache: Optimizing Multimodal LLM Serving through Lightweight KV-Cache Compression Framework

Jianian Zhu, Hang Wu, Haojie Wang, Yinghui Li, Biao Hou, Ruixuan Li, Jidong Zhai

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

Comments 14 pages, 14 figures

2503.08123 2025-03-12 cs.NI 85%

LLM4MAC: An LLM-Driven Reinforcement Learning Framework for MAC Protocol Emergence

Renxuan Tan, Rongpeng Li, Zhifeng Zhao

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

Comments 5 pages, 5 figures

2503.07670 2025-03-12 cs.NI eess.IV 85%

Retrieval Augmented Generation with Multi-Modal LLM Framework for Wireless Environments

Muhammad Ahmed Mohsin, Ahsan Bilal, Sagnik Bhattacharya, John M. Cioffi

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

Comments Accepted @ ICC 2025

2502.14856 2025-03-12 cs.CL cs.AI cs.LG 85%

FR-Spec: Accelerating Large-Vocabulary Language Models via Frequency-Ranked Speculative Sampling

Weilin Zhao, Tengyu Pan, Xu Han, Yudi Zhang, Ao Sun, Yuxiang Huang, Kaihuo Zhang, Weilun Zhao, Yuxuan Li, Jianyong Wang, Zhiyuan Liu, Maosong Sun

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

2503.06216 2025-03-11 eess.SP 85%

A Novel Distributed PV Power Forecasting Approach Based on Time-LLM

Huapeng Lin, Miao Yu

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

Comments 23 pages, 8 figures

2406.13511 2025-03-11 cs.DC 85%

Slice-Level Scheduling for High Throughput and Load Balanced LLM Serving

Ke Cheng, Wen Hu, Zhi Wang, Hongen Peng, Jianguo Li, Sheng Zhang

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

Comments This work has been submitted to the IEEE for possible publication

2503.05248 2025-03-10 cs.DC 85%

Optimizing LLM Inference Throughput via Memory-aware and SLA-constrained Dynamic Batching

Bowen Pang, Kai Li, Feifan Wang

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

2407.01161 2025-03-10 cs.HC 85%

GazeNoter: Co-Piloted AR Note-Taking via Gaze Selection of LLM Suggestions to Match Users' Intentions

Hsin-Ruey Tsai, Shih-Kang Chiu, Bryan Wang

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

Comments 22 pages, 19 figures

2503.04253 2025-03-07 cs.AR 85%

ADOR: A Design Exploration Framework for LLM Serving with Enhanced Latency and Throughput

Junsoo Kim, Hunjong Lee, Geonwoo Ko, Gyubin Choi, Seri Ham, Seongmin Hong, Joo-Young Kim

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

Comments 11pages, 17 figures

2502.09766 2025-03-05 cs.SE 85%

LLM-Generated Microservice Implementations from RESTful API Definitions

Saurabh Chauhan, Zeeshan Rasheed, Abdul Malik Sami, Zheying Zhang, Jussi Rasku, Kai-Kristian Kemell, Pekka Abrahamsson

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

2503.01319 2025-03-04 cs.SE 85%

ABFS: Natural Robustness Testing for LLM-based NLP Software

Mingxuan Xiao, Yan Xiao, Shunhui Ji, Yunhe Li, Lei Xue, Pengcheng Zhang

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

2503.00813 2025-03-04 cs.DC 85%

HLoRA: Efficient Federated Learning System for LLM Heterogeneous Fine-Tuning

Qianli Liu, Zhaorui Zhang, Xin Yao, Benben Liu

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

2503.00502 2025-03-04 cs.RO 85%

Interact, Instruct to Improve: A LLM-Driven Parallel Actor-Reasoner Framework for Enhancing Autonomous Vehicle Interactions

Shiyu Fang, Jiaqi Liu, Chengkai Xu, Chen Lv, Peng Hang, Jian Sun

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

2502.16963 2025-02-25 cs.AR 85%

Make LLM Inference Affordable to Everyone: Augmenting GPU Memory with NDP-DIMM

Lian Liu, Shixin Zhao, Bing Li, Haimeng Ren, Zhaohui Xu, Mengdi Wang, Xiaowei Li, Yinhe Han, Ying Wang

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

Comments 15 pages, 17 figures, accepted by HPCA 2025

2502.16924 2025-02-25 cs.IR 85%

FilterLLM: Text-To-Distribution LLM for Billion-Scale Cold-Start Recommendation

Ruochen Liu, Hao Chen, Yuanchen Bei, Zheyu Zhou, Lijia Chen, Qijie Shen, Feiran Huang, Fakhri Karray, Senzhang Wang

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

Comments 12 pages

2502.16199 2025-02-25 cs.NI 85%

LLMKey: LLM-Powered Wireless Key Generation Scheme for Next-Gen IoV Systems

Huanqi Yang, Weitao Xu

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

2502.15304 2025-02-24 cs.LG cs.AI cs.CL 85%

SVDq: 1.25-bit and 410x Key Cache Compression for LLM Attention

Hong Yankun, Li Xing, Zhen Hui-Ling, Yu Xianzhi, Liu Wulong, Yuan Mingxuan

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

2502.14553 2025-02-21 cs.CL cs.AI cs.LG 85%

Multiscale Byte Language Models -- A Hierarchical Architecture for Causal Million-Length Sequence Modeling

Eric Egli, Matteo Manica, Jannis Born

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

Comments Under Review

2502.14328 2025-02-21 cs.SE 85%

SolSearch: An LLM-Driven Framework for Efficient SAT-Solving Code Generation

Junjie Sheng, Yanqiu Lin, Jiehao Wu, Yanhong Huang, Jianqi Shi, Min Zhang, Xiangfeng Wang

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

2502.14008 2025-02-21 cs.CL cs.AI cs.LG 85%

MaskPrune: Mask-based LLM Pruning for Layer-wise Uniform Structures

Jiayu Qin, Jianchao Tan, Kefeng Zhang, Xunliang Cai, Wei Wang

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

2408.04323 2025-02-21 cs.DC 85%

SCOOT: SLO-Oriented Performance Tuning for LLM Inference Engines

Ke Cheng, Zhi Wang, Wen Hu, Tiannuo Yang, Jianguo Li, Sheng Zhang

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

Comments Accepted by The ACM Web Conference 2025 (WWW'25)

2502.12947 2025-02-19 cs.CL cs.AI cs.LG 85%

Every Expert Matters: Towards Effective Knowledge Distillation for Mixture-of-Experts Language Models

Gyeongman Kim, Gyouk Chu, Eunho Yang

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

2502.12559 2025-02-19 cs.DC 85%

Distributed On-Device LLM Inference With Over-the-Air Computation

Kai Zhang, Hengtao He, Shenghui Song, Jun Zhang, Khaled B. Letaief

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

Communication-Efficient Distributed On-Device LLM Inference Over Wireless Networks

Towards Aligning Language Models with Textual Feedback

Genicious: Contextual Few-shot Prompting for Insights Discovery

SPPO:Efficient Long-sequence LLM Training via Adaptive Sequence Pipeline Parallel Offloading

NumScout: Unveiling Numerical Defects in Smart Contracts using LLM-Pruning Symbolic Execution

Multi-Agent LLM Actor-Critic Framework for Social Robot Navigation

LightGen: Efficient Image Generation through Knowledge Distillation and Direct Preference Optimization

FastCache: Optimizing Multimodal LLM Serving through Lightweight KV-Cache Compression Framework

LLM4MAC: An LLM-Driven Reinforcement Learning Framework for MAC Protocol Emergence

Retrieval Augmented Generation with Multi-Modal LLM Framework for Wireless Environments

FR-Spec: Accelerating Large-Vocabulary Language Models via Frequency-Ranked Speculative Sampling

A Novel Distributed PV Power Forecasting Approach Based on Time-LLM

Slice-Level Scheduling for High Throughput and Load Balanced LLM Serving

Optimizing LLM Inference Throughput via Memory-aware and SLA-constrained Dynamic Batching

GazeNoter: Co-Piloted AR Note-Taking via Gaze Selection of LLM Suggestions to Match Users' Intentions

ADOR: A Design Exploration Framework for LLM Serving with Enhanced Latency and Throughput

LLM-Generated Microservice Implementations from RESTful API Definitions

ABFS: Natural Robustness Testing for LLM-based NLP Software

HLoRA: Efficient Federated Learning System for LLM Heterogeneous Fine-Tuning

Interact, Instruct to Improve: A LLM-Driven Parallel Actor-Reasoner Framework for Enhancing Autonomous Vehicle Interactions

Make LLM Inference Affordable to Everyone: Augmenting GPU Memory with NDP-DIMM

FilterLLM: Text-To-Distribution LLM for Billion-Scale Cold-Start Recommendation

LLMKey: LLM-Powered Wireless Key Generation Scheme for Next-Gen IoV Systems

SVDq: 1.25-bit and 410x Key Cache Compression for LLM Attention

Multiscale Byte Language Models -- A Hierarchical Architecture for Causal Million-Length Sequence Modeling

SolSearch: An LLM-Driven Framework for Efficient SAT-Solving Code Generation

MaskPrune: Mask-based LLM Pruning for Layer-wise Uniform Structures

SCOOT: SLO-Oriented Performance Tuning for LLM Inference Engines

Every Expert Matters: Towards Effective Knowledge Distillation for Mixture-of-Experts Language Models

Distributed On-Device LLM Inference With Over-the-Air Computation