语言大模型 / LLM - arXivDaily 专题

2406.06059 2024-12-24 cs.NI 85%

LLM-Based Intent Processing and Network Optimization Using Attention-Based Hierarchical Reinforcement Learning

Md Arafat Habib, Pedro Enrique Iturria Rivera, Yigit Ozcan, Medhat Elsayed, Majid Bavand, Raimundus Gaigalas, Melike Erol-Kantarci

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

Comments Accepted paper at WCNC 2025

2402.03408 2024-12-24 cs.SE cs.DC 85%

A Framework for Effective Invocation Methods of Various LLM Services

Can Wang, Dianbo Sui, Bolin Zhang, Xiaoyu Liu, Jiabao Kang, Zhidong Qiao, Zhiying Tu

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

2412.15676 2024-12-23 cs.SE 85%

Code Review Automation Via Multi-task Federated LLM -- An Empirical Study

Jahnavi Kumar, Sridhar Chimalakonda

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

2411.11532 2024-12-23 cs.SE cs.CR 85%

CKGFuzzer: LLM-Based Fuzz Driver Generation Enhanced By Code Knowledge Graph

Hanxiang Xu, Wei Ma, Ting Zhou, Yanjie Zhao, Kai Chen, Qiang Hu, Yang Liu, Haoyu Wang

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

Comments 12 pages, 3 figures

2308.10144 2024-12-23 cs.LG cs.AI cs.CL 85%

ExpeL: LLM Agents Are Experiential Learners

Andrew Zhao, Daniel Huang, Quentin Xu, Matthieu Lin, Yong-Jin Liu, Gao Huang

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 by the 38th Annual AAAI Conference on Artificial Intelligence (AAAI-24)

2412.09916 2024-12-18 cs.HC 85%

ProxyLLM : LLM-Driven Framework for Customer Support Through Text-Style Transfer

Sehyeong Jo, Jungwon Seo

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

2311.04448 2024-12-13 cs.SE 85%

Boosting Static Resource Leak Detection via LLM-based Resource-Oriented Intention Inference

Chong Wang, Jianan Liu, Xin Peng, Yang Liu, Yiling Lou

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

Comments Accepted by ICSE'25

2407.08152 2024-12-05 cs.CR cs.AI cs.CL cs.LG 85%

Privacy-Preserving Data Deduplication for Enhancing Federated Learning of Language Models (Extended Version)

Aydin Abadi, Vishnu Asutosh Dasu, Sumanta Sarkar

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 Accepted at the Network and Distributed Systems Security (NDSS) Symposium, 2025

2412.00447 2024-12-03 cs.CV 85%

ATP-LLaVA: Adaptive Token Pruning for Large Vision Language Models

Xubing Ye, Yukang Gan, Yixiao Ge, Xiao-Ping Zhang, Yansong Tang

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

Comments 11 pages, 4 figures

2412.00216 2024-12-03 cs.SE 85%

Enhanced LLM-Based Framework for Predicting Null Pointer Dereference in Source Code

Md. Fahim Sultan, Tasmin Karim, Md. Shazzad Hossain Shaon, Mohammad Wardat, Mst Shapna Akter

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

2411.18191 2024-12-02 cs.CR 85%

InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks

Xinyao Zheng, Husheng Han, Shangyi Shi, Qiyan Fang, Zidong Du, Xing Hu, Qi Guo

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

2405.19100 2024-11-27 cs.CV 85%

Enhancing Zero-Shot Facial Expression Recognition by LLM Knowledge Transfer

Zengqun Zhao, Yu Cao, Shaogang Gong, Ioannis Patras

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

Comments Accepted at WACV 2025 (Camera-Ready Version)

2411.15662 2024-11-26 cs.CY 85%

Gaps Between Research and Practice When Measuring Representational Harms Caused by LLM-Based Systems

Emma Harvey, Emily Sheng, Su Lin Blodgett, Alexandra Chouldechova, Jean Garcia-Gathright, Alexandra Olteanu, Hanna Wallach

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

Comments NeurIPS 2024 Workshop on Evaluating Evaluations (EvalEval)

2411.08912 2024-11-15 cs.CY cs.SE 85%

Can Large-Language Models Help us Better Understand and Teach the Development of Energy-Efficient Software?

Ryan Hasler, Konstantin Läufer, George K. Thiruvathukal, Huiyun Peng, Kyle Robinson, Kirsten Davis, Yung-Hsiang Lu, James C. Davis

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

2411.06535 2024-11-12 cs.AI cs.CL cs.LG 85%

Probabilistic Consensus through Ensemble Validation: A Framework for LLM Reliability

Ninad Naik

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 8 pages, 6 tables

2411.05555 2024-11-11 cs.DC 85%

AcceLLM: Accelerating LLM Inference using Redundancy for Load Balancing and Data Locality

Ilias Bournias, Lukas Cavigelli, Georgios Zacharopoulos

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

Comments 10 pages

2410.14331 2024-11-08 cs.HC cs.IR 85%

ChartifyText: Automated Chart Generation from Data-Involved Texts via LLM

Songheng Zhang, Lei Wang, Toby Jia-Jun Li, Qiaomu Shen, Yixin Cao, Yong Wang

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

2411.03513 2024-11-07 cs.CL cs.AI cs.LG 85%

Change Is the Only Constant: Dynamic LLM Slicing based on Layer Redundancy

Razvan-Gabriel Dumitru, Paul-Ioan Clotan, Vikas Yadav, Darius Peteleaza, Mihai Surdeanu

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 EMNLP Findings 2024

2411.00593 2024-11-07 cs.CL cs.AI cs.LG 85%

Adapting Language Models via Token Translation

Zhili Feng, Tanya Marwah, Nicolo Fusi, David Alvarez-Melis, Lester Mackey

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

2410.23099 2024-10-31 cs.CL cs.AI cs.LG 85%

Comparative Analysis of Demonstration Selection Algorithms for LLM In-Context Learning

Dong Shu, Mengnan Du

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 6 pages, 4 figures

2311.01908 2024-10-28 eess.IV cs.CV 85%

LLM-driven Multimodal Target Volume Contouring in Radiation Oncology

Yujin Oh, Sangjoon Park, Hwa Kyung Byun, Yeona Cho, Ik Jae Lee, Jin Sung Kim, Jong Chul Ye

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

Comments Published in Nature Communications, see https://www.nature.com/articles/s41467-024-53387-y

Journal ref Nat Commun 15, 9186 (2024)

2410.09047 2024-10-14 cs.CL cs.AI cs.LG 85%

Unraveling and Mitigating Safety Alignment Degradation of Vision-Language Models

Qin Liu, Chao Shang, Ling Liu, Nikolaos Pappas, Jie Ma, Neha Anna John, Srikanth Doss, Lluis Marquez, Miguel Ballesteros, Yassine Benajiba

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

Comments Preprint

2409.16949 2024-09-26 cs.CV 85%

DALDA: Data Augmentation Leveraging Diffusion Model and LLM with Adaptive Guidance Scaling

Kyuheon Jung, Yongdeuk Seo, Seongwoo Cho, Jaeyoung Kim, Hyun-seok Min, Sungchul Choi

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

Comments Accepted to ECCV Synthetic Data for Computer Vision Workshop (Oral)

2409.15654 2024-09-25 cs.AR 85%

Cambricon-LLM: A Chiplet-Based Hybrid Architecture for On-Device Inference of 70B LLM

Zhongkai Yu, Shengwen Liang, Tianyun Ma, Yunke Cai, Ziyuan Nan, Di Huang, Xinkai Song, Yifan Hao, Jie Zhang, Tian Zhi, Yongwei Zhao, Zidong Du, Xing Hu, Qi Guo, Tianshi Chen

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

Comments 15 pages, 16 figures

Journal ref MICRO 2024

2409.14961 2024-09-25 cs.DC 85%

UELLM: A Unified and Efficient Approach for LLM Inference Serving

Yiyuan He, Minxian Xu, Jingfeng Wu, Wanyi Zheng, Kejiang Ye, Chengzhong Xu

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

Comments 15 pages, 5 figures, ICSOC 2024

2409.10354 2024-09-18 cs.HC 85%

Learnings from a Large-Scale Deployment of an LLM-Powered Expert-in-the-Loop Healthcare Chatbot

Bhuvan Sachdeva, Pragnya Ramjee, Geeta Fulari, Kaushik Murali, Mohit Jain

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

Comments The first two authors contributed equally to this research

2409.08931 2024-09-16 cs.IR 85%

LLM-based Weak Supervision Framework for Query Intent Classification in Video Search

Farnoosh Javadi, Phanideep Gampa, Alyssa Woo, Xingxing Geng, Hang Zhang, Jose Sepulveda, Belhassen Bayar, Fei Wang

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

Comments 6 pages, 5 figures

2409.00661 2024-09-04 cs.AR 85%

Research on LLM Acceleration Using the High-Performance RISC-V Processor "Xiangshan" (Nanhu Version) Based on the Open-Source Matrix Instruction Set Extension (Vector Dot Product)

Xu-Hao Chen, Si-Peng Hu, Hong-Chao Liu, Bo-Ran Liu, Dan Tang, Di Zhao

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

Comments 10 pages, in Chinese language, 6 figures

2407.02392 2024-08-29 cs.CV 85%

TokenPacker: Efficient Visual Projector for Multimodal LLM

Wentong Li, Yuqian Yuan, Jian Liu, Dongqi Tang, Song Wang, Jie Qin, Jianke Zhu, Lei Zhang

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

Comments 16 pages, Codes:https://github.com/CircleRadon/TokenPacker

2408.06810 2024-08-14 cs.AR 85%

HLSPilot: LLM-based High-Level Synthesis

Chenwei Xiong, Cheng Liu, Huawei Li, Xiaowei Li

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 22405 篇

LLM-Based Intent Processing and Network Optimization Using Attention-Based Hierarchical Reinforcement Learning

A Framework for Effective Invocation Methods of Various LLM Services

Code Review Automation Via Multi-task Federated LLM -- An Empirical Study

CKGFuzzer: LLM-Based Fuzz Driver Generation Enhanced By Code Knowledge Graph

ExpeL: LLM Agents Are Experiential Learners

ProxyLLM : LLM-Driven Framework for Customer Support Through Text-Style Transfer

Boosting Static Resource Leak Detection via LLM-based Resource-Oriented Intention Inference

Privacy-Preserving Data Deduplication for Enhancing Federated Learning of Language Models (Extended Version)

ATP-LLaVA: Adaptive Token Pruning for Large Vision Language Models

Enhanced LLM-Based Framework for Predicting Null Pointer Dereference in Source Code

InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks

Enhancing Zero-Shot Facial Expression Recognition by LLM Knowledge Transfer

Gaps Between Research and Practice When Measuring Representational Harms Caused by LLM-Based Systems

Can Large-Language Models Help us Better Understand and Teach the Development of Energy-Efficient Software?

Probabilistic Consensus through Ensemble Validation: A Framework for LLM Reliability

AcceLLM: Accelerating LLM Inference using Redundancy for Load Balancing and Data Locality

ChartifyText: Automated Chart Generation from Data-Involved Texts via LLM

Change Is the Only Constant: Dynamic LLM Slicing based on Layer Redundancy

Adapting Language Models via Token Translation

Comparative Analysis of Demonstration Selection Algorithms for LLM In-Context Learning

LLM-driven Multimodal Target Volume Contouring in Radiation Oncology

Unraveling and Mitigating Safety Alignment Degradation of Vision-Language Models

DALDA: Data Augmentation Leveraging Diffusion Model and LLM with Adaptive Guidance Scaling

Cambricon-LLM: A Chiplet-Based Hybrid Architecture for On-Device Inference of 70B LLM

UELLM: A Unified and Efficient Approach for LLM Inference Serving

Learnings from a Large-Scale Deployment of an LLM-Powered Expert-in-the-Loop Healthcare Chatbot

LLM-based Weak Supervision Framework for Query Intent Classification in Video Search

Research on LLM Acceleration Using the High-Performance RISC-V Processor "Xiangshan" (Nanhu Version) Based on the Open-Source Matrix Instruction Set Extension (Vector Dot Product)

TokenPacker: Efficient Visual Projector for Multimodal LLM

HLSPilot: LLM-based High-Level Synthesis