语言大模型 / LLM - arXivDaily 专题

2412.09807 2024-12-31 cs.CL 85%

LLM Distillation for Efficient Few-Shot Multiple Choice Question Answering

Patrick Sutanto, Joan Santoso, Esther Irawati Setiawan, Aji Prasetya Wibawa

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

2412.18695 2024-12-30 cs.RO cs.DC cs.LG 85%

TimelyLLM: Segmented LLM Serving System for Time-sensitive Robotic Applications

Neiwen Ling, Guojun Chen, Lin Zhong

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

2408.10945 2024-12-30 cs.CV cs.AI 85%

HiRED: Attention-Guided Token Dropping for Efficient Inference of High-Resolution Vision-Language Models

Kazi Hasan Ibn Arif, JinYi Yoon, Dimitrios S. Nikolopoulos, Hans Vandierendonck, Deepu John, Bo Ji

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

Comments Accepted in AAAI 2025

2412.17846 2024-12-25 cs.CL 85%

Enhancing Knowledge Distillation for LLMs with Response-Priming Prompting

Vijay Goyal, Mustafa Khan, Aprameya Tirupati, Harveer Saini, Michael Lam, Kevin Zhu

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

Comments Accepted to SoCal NLP Symposium 2024

2412.11672 2024-12-17 cs.AI cs.HC 85%

LLM-DaaS: LLM-driven Drone-as-a-Service Operations from Text User Requests

Lillian Wassim, Kamal Mohamed, Ali Hamdi

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

2407.05858 2024-12-17 cs.AI 85%

Fast On-device LLM Inference with NPUs

Daliang Xu, Hao Zhang, Liming Yang, Ruiqi Liu, Gang Huang, Mengwei Xu, Xuanzhe Liu

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

2409.06223 2024-12-16 cs.SD cs.CL eess.AS 85%

Enhancing Temporal Understanding in Audio Question Answering for Large Audio Language Models

Arvind Krishna Sridhar, Yinyi Guo, Erik Visser

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

Comments 9 pages, 6 figures

2404.16283 2024-12-16 cs.DC cs.LG 85%

Andes: Defining and Enhancing Quality-of-Experience in LLM-Based Text Streaming Services

Jiachen Liu, Jae-Won Chung, Zhiyu Wu, Fan Lai, Myungjin Lee, Mosharaf Chowdhury

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

Comments 16 pages, 21 figures

2411.05276 2024-12-10 cs.LG 85%

GPT Semantic Cache: Reducing LLM Costs and Latency via Semantic Embedding Caching

Sajal Regmi, Chetan Phakami Pun

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

2406.11232 2024-12-10 cs.SE cs.AI 85%

SLEGO: A Collaborative Data Analytics System with LLM Recommender for Diverse Users

Siu Lung Ng, Hirad Baradaran Rezaei, Fethi Rabhi

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

Comments 14 pages, 9 figures

2408.09439 2024-12-09 cs.IR cs.AI 85%

Towards Boosting LLMs-driven Relevance Modeling with Progressive Retrieved Behavior-augmented Prompting

Zeyuan Chen, Haiyan Wu, Kaixin Wu, Wei Chen, Mingjie Zhong, Jia Xu, Zhongyi Liu, Wei Zhang

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

Comments Accepted By COLING 2025

2406.02532 2024-12-03 cs.CL 85%

SpecExec: Massively Parallel Speculative Decoding for Interactive LLM Inference on Consumer Devices

Ruslan Svirschevski, Avner May, Zhuoming Chen, Beidi Chen, Zhihao Jia, Max Ryabinin

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

2408.05499 2024-12-02 cs.DC cs.AI 85%

LLMServingSim: A HW/SW Co-Simulation Infrastructure for LLM Inference Serving at Scale

Jaehong Cho, Minsu Kim, Hyunmin Choi, Guseul Heo, Jongse Park

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

Comments 15 pages, 11 figures

Journal ref IISWC 2024

2411.17309 2024-12-01 cs.AR cs.AI cs.DC cs.ET 85%

PIM-AI: A Novel Architecture for High-Efficiency LLM Inference

Cristobal Ortega, Yann Falevoz, Renaud Ayrignac

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

Comments 14 pages, 5 figures

2411.15399 2024-11-26 cs.PF cs.DC cs.LG 85%

Less is More: Optimizing Function Calling for LLM Execution on Edge Devices

Varatheepan Paramanayakam, Andreas Karatzas, Iraklis Anagnostopoulos, Dimitrios Stamoulis

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

Comments Accepted at DATE 2025

2411.14164 2024-11-22 cs.CV cs.AI 85%

FoPru: Focal Pruning for Efficient Large Vision-Language Models

Lei Jiang, Weizhe Huang, Tongxuan Liu, Yuting Zeng, Jing Li, Lechao Cheng, Xiaohua Xu

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

Comments 11 pages, 7 figures

2411.11560 2024-11-19 cs.DC cs.AI 85%

Topology-aware Preemptive Scheduling for Co-located LLM Workloads

Ping Zhang, Lei Su, Jinjie Yang, Xin Chen

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

Comments 17 Pages, 11 Figures, 5 Tables

2406.16758 2024-11-12 cs.CL 85%

Towards Fast Multilingual LLM Inference: Speculative Decoding and Specialized Drafters

Euiin Yi, Taehyeon Kim, Hongseok Jeung, Du-Seong Chang, Se-Young Yun

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

2311.16442 2024-11-12 cs.LG cs.DC 85%

Fast and Efficient 2-bit LLM Inference on GPU: 2/4/16-bit in a Weight Matrix with Asynchronous Dequantization

Jinhao Li, Jiaming Xu, Shiyao Li, Shan Huang, Jun Liu, Yaoxiu Lian, Guohao Dai

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

2411.05045 2024-11-11 cs.CL 85%

Performance-Guided LLM Knowledge Distillation for Efficient Text Classification at Scale

Flavio Di Palo, Prateek Singhi, Bilal Fadlallah

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

Comments Published in EMNLP 2024

2411.04319 2024-11-08 cs.DB cs.LG 85%

Towards Optimizing SQL Generation via LLM Routing

Mohammadhossein Malekpour, Nour Shaheen, Foutse Khomh, Amine Mhedhbi

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

Comments Table Representation Learning Workshop at NeurIPS 2024

2410.13006 2024-11-05 cs.LG cs.SI 85%

LLM Chain Ensembles for Scalable and Accurate Data Annotation

David Farr, Nico Manzonelli, Iain Cruickshank, Kate Starbird, Jevin West

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

2408.08217 2024-11-05 cs.LG cs.SI 85%

RED-CT: A Systems Design Methodology for Using LLM-labeled Data to Train and Deploy Edge Classifiers for Computational Social Science

David Farr, Nico Manzonelli, Iain Cruickshank, Jevin West

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

2406.02214 2024-11-05 cs.LG 85%

SLTrain: a sparse plus low-rank approach for parameter and memory efficient pretraining

Andi Han, Jiaxiang Li, Wei Huang, Mingyi Hong, Akiko Takeda, Pratik Jawanpuria, Bamdev Mishra

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

2409.14556 2024-11-04 cs.DB cs.AI 85%

RACOON: An LLM-based Framework for Retrieval-Augmented Column Type Annotation with a Knowledge Graph

Lindsey Linxi Wei, Guorui Xiao, Magdalena Balazinska

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

2410.22315 2024-10-30 cs.CL cs.CV 85%

Natural Language Inference Improves Compositionality in Vision-Language Models

Paola Cascante-Bonilla, Yu Hou, Yang Trista Cao, Hal Daumé, Rachel Rudinger

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

Comments Project page: https://cece-vlm.github.io/

2409.15518 2024-10-30 cs.LG 85%

Eagle: Efficient Training-Free Router for Multi-LLM Inference

Zesen Zhao, Shuowei Jin, Z. Morley Mao

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

2410.20488 2024-10-29 cs.CL 85%

FIRP: Faster LLM inference via future intermediate representation prediction

Pengfei Wu, Jiahao Liu, Zhuocheng Gong, Qifan Wang, Jinpeng Li, Jingang Wang, Xunliang Cai, Dongyan Zhao

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

Journal ref NLPCC2024

2410.14740 2024-10-24 cs.LG cs.DC 85%

Harnessing Your DRAM and SSD for Sustainable and Accessible LLM Inference with Mixed-Precision and Multi-level Caching

Jie Peng, Zhang Cao, Huaizhi Qu, Zhengyu Zhang, Chang Guo, Yanyong Zhang, Zhichao Cao, Tianlong Chen

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

Comments 24 pages, 13 figures

2410.12568 2024-10-22 cs.RO cs.AI 85%

Robust RL with LLM-Driven Data Synthesis and Policy Adaptation for Autonomous Driving

Sihao Wu, Jiaxu Liu, Xiangyu Yin, Guangliang Cheng, Xingyu Zhao, Meng Fang, Xinping Yi, Xiaowei Huang

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

1. 效率与部署 22368 篇

LLM Distillation for Efficient Few-Shot Multiple Choice Question Answering

TimelyLLM: Segmented LLM Serving System for Time-sensitive Robotic Applications

HiRED: Attention-Guided Token Dropping for Efficient Inference of High-Resolution Vision-Language Models

Enhancing Knowledge Distillation for LLMs with Response-Priming Prompting

LLM-DaaS: LLM-driven Drone-as-a-Service Operations from Text User Requests

Fast On-device LLM Inference with NPUs

Enhancing Temporal Understanding in Audio Question Answering for Large Audio Language Models

Andes: Defining and Enhancing Quality-of-Experience in LLM-Based Text Streaming Services

GPT Semantic Cache: Reducing LLM Costs and Latency via Semantic Embedding Caching

SLEGO: A Collaborative Data Analytics System with LLM Recommender for Diverse Users

Towards Boosting LLMs-driven Relevance Modeling with Progressive Retrieved Behavior-augmented Prompting

SpecExec: Massively Parallel Speculative Decoding for Interactive LLM Inference on Consumer Devices

LLMServingSim: A HW/SW Co-Simulation Infrastructure for LLM Inference Serving at Scale

PIM-AI: A Novel Architecture for High-Efficiency LLM Inference

Less is More: Optimizing Function Calling for LLM Execution on Edge Devices

FoPru: Focal Pruning for Efficient Large Vision-Language Models

Topology-aware Preemptive Scheduling for Co-located LLM Workloads

Towards Fast Multilingual LLM Inference: Speculative Decoding and Specialized Drafters

Fast and Efficient 2-bit LLM Inference on GPU: 2/4/16-bit in a Weight Matrix with Asynchronous Dequantization

Performance-Guided LLM Knowledge Distillation for Efficient Text Classification at Scale

Towards Optimizing SQL Generation via LLM Routing

LLM Chain Ensembles for Scalable and Accurate Data Annotation

RED-CT: A Systems Design Methodology for Using LLM-labeled Data to Train and Deploy Edge Classifiers for Computational Social Science

SLTrain: a sparse plus low-rank approach for parameter and memory efficient pretraining

RACOON: An LLM-based Framework for Retrieval-Augmented Column Type Annotation with a Knowledge Graph

Natural Language Inference Improves Compositionality in Vision-Language Models

Eagle: Efficient Training-Free Router for Multi-LLM Inference

FIRP: Faster LLM inference via future intermediate representation prediction

Harnessing Your DRAM and SSD for Sustainable and Accessible LLM Inference with Mixed-Precision and Multi-level Caching

Robust RL with LLM-Driven Data Synthesis and Policy Adaptation for Autonomous Driving