语言大模型 / LLM - arXivDaily 专题

2404.01365 2024-08-13 cs.LG cs.AI cs.CL 85%

Prompt-prompted Adaptive Structured Pruning for Efficient LLM Generation

Harry Dong, Beidi Chen, Yuejie Chi

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 Revision 1: Updated abstract with code link; re-ran top-k + sampling rows in Table 4, conclusions unchanged Revision 2: Reframing and new experiments, conclusions unchanged

2406.07174 2024-08-09 cs.SE 85%

LUNAR: Unsupervised LLM-based Log Parsing

Junjie Huang, Zhihan Jiang, Zhuangbin Chen, Michael R. Lyu

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

2408.00352 2024-08-02 cs.CV 85%

Autonomous LLM-Enhanced Adversarial Attack for Text-to-Motion

Honglei Miao, Fan Ma, Ruijie Quan, Kun Zhan, Yi Yang

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

2309.11359 2024-08-01 cs.RO 85%

Prompt, Plan, Perform: LLM-based Humanoid Control via Quantized Imitation Learning

Jingkai Sun, Qiang Zhang, Yiqun Duan, Xiaoyang Jiang, Chong Cheng, Renjing Xu

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

Journal ref Published as oral presentation paper at the 2024 IEEE International Conference on Robotics and Automation (ICRA2024), Yokohama, Japan

2407.14057 2024-07-22 cs.CL cs.AI cs.LG 85%

LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference

Qichen Fu, Minsik Cho, Thomas Merth, Sachin Mehta, Mohammad Rastegari, Mahyar Najibi

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

2406.12381 2024-07-17 cs.CL cs.AI cs.LG 85%

QOG:Question and Options Generation based on Language Model

Jincheng Zhou

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

2407.09801 2024-07-16 cs.LG cs.AI cs.CL cs.CV cs.MM 85%

IoT-LM: Large Multisensory Language Models for the Internet of Things

Shentong Mo, Russ Salakhutdinov, Louis-Philippe Morency, Paul Pu Liang

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 arXiv admin note: text overlap with arXiv:2311.06217

2407.08931 2024-07-15 cs.CV 85%

Global-Local Collaborative Inference with LLM for Lidar-Based Open-Vocabulary Detection

Xingyu Peng, Yan Bai, Chen Gao, Lirong Yang, Fei Xia, Beipeng Mu, Xiaofei Wang, Si Liu

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

Comments accepted by ECCV 2024

2407.04014 2024-07-08 cs.DC 85%

Offline Energy-Optimal LLM Serving: Workload-Based Energy Models for LLM Inference on Heterogeneous Systems

Grant Wilkins, Srinivasan Keshav, Richard Mortier

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

Comments 7 pages, appearing at HotCarbon 2024

2401.02669 2024-07-08 cs.DC cs.AR 85%

Infinite-LLM: Efficient LLM Service for Long Context with DistAttention and Distributed KVCache

Bin Lin, Chen Zhang, Tao Peng, Hanyu Zhao, Wencong Xiao, Minmin Sun, Anmin Liu, Zhipeng Zhang, Lanbo Li, Xiafei Qiu, Shen Li, Zhigang Ji, Tao Xie, Yong Li, Wei Lin

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

2407.02486 2024-07-03 cs.CL cs.AI cs.LG 85%

Neurocache: Efficient Vector Retrieval for Long-range Language Modeling

Ali Safaya, Deniz Yuret

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 Long paper, published at the main conference NAACL'24

2405.02543 2024-07-02 cs.NE 85%

Exploring Extreme Quantization in Spiking Language Models

Malyaban Bal, Yi Jiang, Abhronil Sengupta

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

2406.19995 2024-07-01 cs.CL cs.AI cs.LG 85%

Single Parent Family: A Spectrum of Family Members from a Single Pre-Trained Foundation Model

Habib Hajimolahoseini, Mohammad Hassanpour, Foozhan Ataiefard, Boxing Chen, Yang Liu

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

2402.14905 2024-06-28 cs.LG cs.AI cs.CL 85%

MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases

Zechun Liu, Changsheng Zhao, Forrest Iandola, Chen Lai, Yuandong Tian, Igor Fedorov, Yunyang Xiong, Ernie Chang, Yangyang Shi, Raghuraman Krishnamoorthi, Liangzhen Lai, Vikas Chandra

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. Code is available at https://github.com/facebookresearch/MobileLLM

2310.10912 2024-06-27 cs.CV 85%

Towards Training-free Open-world Segmentation via Image Prompt Foundation Models

Lv Tang, Peng-Tao Jiang, Hao-Ke Xiao, Bo Li

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

Comments This paper is accepted by IJCV2024

2405.20853 2024-06-19 cs.CV 85%

MeshXL: Neural Coordinate Field for Generative 3D Foundation Models

Sijin Chen, Xin Chen, Anqi Pang, Xianfang Zeng, Wei Cheng, Yijun Fu, Fukun Yin, Yanru Wang, Zhibin Wang, Chi Zhang, Jingyi Yu, Gang Yu, Bin Fu, Tao Chen

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

2404.02015 2024-06-14 cs.DC 85%

MuxServe: Flexible Spatial-Temporal Multiplexing for Multiple LLM Serving

Jiangfei Duan, Runyu Lu, Haojie Duanmu, Xiuhong Li, Xingcheng Zhang, Dahua Lin, Ion Stoica, Hao Zhang

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

2401.17197 2024-06-05 cs.IR 85%

Data-efficient Fine-tuning for LLM-based Recommendation

Xinyu Lin, Wenjie Wang, Yongqi Li, Shuo Yang, Fuli Feng, Yinwei Wei, Tat-Seng Chua

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

Comments Accepted by SIGIR 2024

2405.14636 2024-05-24 cs.DC cs.NI 85%

PerLLM: Personalized Inference Scheduling with Edge-Cloud Collaboration for Diverse LLM Services

Zheming Yang, Yuanhao Yang, Chang Zhao, Qi Guo, Wenkai He, Wen Ji

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

2405.14371 2024-05-24 cs.DC 85%

EdgeShard: Efficient LLM Inference via Collaborative Edge Computing

Mingjin Zhang, Jiannong Cao, Xiaoming Shen, Zeyang Cui

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

Comments Under review

2405.13954 2024-05-24 cs.LG cs.AI cs.CL 85%

What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence Functions

Sang Keun Choe, Hwijeen Ahn, Juhan Bae, Kewen Zhao, Minsoo Kang, Youngseog Chung, Adithya Pratapa, Willie Neiswanger, Emma Strubell, Teruko Mitamura, Jeff Schneider, Eduard Hovy, Roger Grosse, Eric Xing

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

2307.02666 2024-05-22 cs.AR 85%

Chiplet Cloud: Building AI Supercomputers for Serving Large Generative Language Models

Huwan Peng, Scott Davidson, Richard Shi, Shuaiwen Leon Song, Michael Taylor

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

2311.18677 2024-05-21 cs.AR cs.DC 85%

Splitwise: Efficient generative LLM inference using phase splitting

Pratyush Patel, Esha Choukse, Chaojie Zhang, Aashaka Shah, Íñigo Goiri, Saeed Maleki, Ricardo Bianchini

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

Comments 12 pages, 19 figures

2405.10625 2024-05-20 cs.CL cs.AI cs.LG q-bio.BM 85%

Specialising and Analysing Instruction-Tuned and Byte-Level Language Models for Organic Reaction Prediction

Jiayun Pang, Ivan Vulić

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

Comments Preprint

2405.06856 2024-05-14 cs.DC 85%

Aladdin: Joint Placement and Scaling for SLO-Aware LLM Serving

Chengyi Nie, Rodrigo Fonseca, Zhenhua Liu

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

2404.14619 2024-05-03 cs.CL cs.AI cs.LG 85%

OpenELM: An Efficient Language Model Family with Open Training and Inference Framework

Sachin Mehta, Mohammad Hossein Sekhavat, Qingqing Cao, Maxwell Horton, Yanzi Jin, Chenfan Sun, Iman Mirzadeh, Mahyar Najibi, Dmitry Belenko, Peter Zatloukal, Mohammad Rastegari

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 Minor corrections

2404.10830 2024-05-03 cs.CL cs.AI cs.LG 85%

Fewer Truncations Improve Language Modeling

Hantian Ding, Zijian Wang, Giovanni Paolini, Varun Kumar, Anoop Deoras, Dan Roth, Stefano Soatto

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

2404.14618 2024-04-24 cs.LG cs.AI cs.CL 85%

Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing

Dujian Ding, Ankur Mallick, Chi Wang, Robert Sim, Subhabrata Mukherjee, Victor Ruhle, Laks V. S. Lakshmanan, Ahmed Hassan Awadallah

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 to ICLR 2024 (main conference)

2307.15517 2024-04-22 cs.AR 85%

A Dataflow Compiler for Efficient LLM Inference using Custom Microscaling Formats

Jianyi Cheng, Cheng Zhang, Zhewen Yu, Christos-Savvas Bouganis, George A. Constantinides, Yiren Zhao

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

2306.11134 2024-04-12 cs.IR 85%

OpenP5: An Open-Source Platform for Developing, Training, and Evaluating LLM-based Recommender Systems

Shuyuan Xu, Wenyue Hua, Yongfeng Zhang

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

Comments In SIGIR 2024 Resource & Reproducibility Track

1. 效率与部署 22405 篇

Prompt-prompted Adaptive Structured Pruning for Efficient LLM Generation

LUNAR: Unsupervised LLM-based Log Parsing

Autonomous LLM-Enhanced Adversarial Attack for Text-to-Motion

Prompt, Plan, Perform: LLM-based Humanoid Control via Quantized Imitation Learning

LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference

QOG:Question and Options Generation based on Language Model

IoT-LM: Large Multisensory Language Models for the Internet of Things

Global-Local Collaborative Inference with LLM for Lidar-Based Open-Vocabulary Detection

Offline Energy-Optimal LLM Serving: Workload-Based Energy Models for LLM Inference on Heterogeneous Systems

Infinite-LLM: Efficient LLM Service for Long Context with DistAttention and Distributed KVCache

Neurocache: Efficient Vector Retrieval for Long-range Language Modeling

Exploring Extreme Quantization in Spiking Language Models

Single Parent Family: A Spectrum of Family Members from a Single Pre-Trained Foundation Model

MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases

Towards Training-free Open-world Segmentation via Image Prompt Foundation Models

MeshXL: Neural Coordinate Field for Generative 3D Foundation Models

MuxServe: Flexible Spatial-Temporal Multiplexing for Multiple LLM Serving

Data-efficient Fine-tuning for LLM-based Recommendation

PerLLM: Personalized Inference Scheduling with Edge-Cloud Collaboration for Diverse LLM Services

EdgeShard: Efficient LLM Inference via Collaborative Edge Computing

What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence Functions

Chiplet Cloud: Building AI Supercomputers for Serving Large Generative Language Models

Splitwise: Efficient generative LLM inference using phase splitting

Specialising and Analysing Instruction-Tuned and Byte-Level Language Models for Organic Reaction Prediction

Aladdin: Joint Placement and Scaling for SLO-Aware LLM Serving

OpenELM: An Efficient Language Model Family with Open Training and Inference Framework

Fewer Truncations Improve Language Modeling

Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing

A Dataflow Compiler for Efficient LLM Inference using Custom Microscaling Formats

OpenP5: An Open-Source Platform for Developing, Training, and Evaluating LLM-based Recommender Systems