语言大模型 / LLM - arXivDaily 专题

2410.18146 2024-10-25 cs.CL cs.AI cs.PL 86%

Meaning Typed Prompting: A Technique for Efficient, Reliable Structured Output Generation

Chandra Irugalbandara

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

2408.12320 2024-10-25 cs.AI cs.LG 86%

TensorOpera Router: A Multi-Model Router for Efficient LLM Inference

Dimitris Stripelis, Zijian Hu, Jipeng Zhang, Zhaozhuo Xu, Alay Dilipbhai Shah, Han Jin, Yuhang Yao, Salman Avestimehr, Chaoyang He

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

Comments 14 pages, 7 figures, 2 tables

2410.14687 2024-10-24 cs.NE cs.CL cs.LG 86%

BrainTransformers: SNN-LLM

Zhengzheng Tang, Eva Zhu

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

2405.06626 2024-10-24 cs.LG cs.CL 86%

Characterizing the Accuracy -- Efficiency Trade-off of Low-rank Decomposition in Language Models

Chakshu Moar, Faraz Tahmasebi, Michael Pellauer, Hyoukjun Kwon

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

2410.12187 2024-10-18 cs.LG cs.AI 86%

DAQ: Density-Aware Post-Training Weight-Only Quantization For LLMs

Yingsong Luo, Ling Chen

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

Comments 9 pages, 4 figures

2410.10714 2024-10-17 cs.LG cs.AI 86%

SeedLM: Compressing LLM Weights into Seeds of Pseudo-Random Generators

Rasoul Shafipour, David Harrison, Maxwell Horton, Jeffrey Marker, Houman Bedayat, Sachin Mehta, Mohammad Rastegari, Mahyar Najibi, Saman Naderiparizi

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

2402.05913 2024-10-15 cs.CL cs.LG 86%

Efficient Stagewise Pretraining via Progressive Subnetworks

Abhishek Panigrahi, Nikunj Saunshi, Kaifeng Lyu, Sobhan Miryoosefi, Sashank Reddi, Satyen Kale, Sanjiv Kumar

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

2404.04793 2024-10-11 cs.LG cs.CL 86%

SqueezeAttention: 2D Management of KV-Cache in LLM Inference via Layer-wise Optimal Budget

Zihao Wang, Bin Cui, Shaoduo Gan

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

2404.15153 2024-10-10 cs.CL cs.AI cs.PF 86%

Performance Characterization of Expert Router for Scalable LLM Inference

Josef Pichlmeier, Philipp Ross, Andre Luckow

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

2410.05292 2024-10-10 cs.LG cs.AI q-bio.QM 86%

CaLMFlow: Volterra Flow Matching using Causal Language Models

Sizhuang He, Daniel Levine, Ivan Vrkic, Marco Francesco Bressana, David Zhang, Syed Asad Rizvi, Yangtian Zhang, Emanuele Zappala, David van Dijk

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

Comments 10 pages, 9 figures, 7 tables

2410.03953 2024-10-08 cs.CL cs.LG 86%

LLM-TOPLA: Efficient LLM Ensemble by Maximising Diversity

Selim Furkan Tekin, Fatih Ilhan, Tiansheng Huang, Sihao Hu, Ling Liu

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

2410.03752 2024-10-08 cs.SD cs.AI cs.CL eess.AS 86%

Efficient Streaming LLM for Speech Recognition

Junteng Jia, Gil Keren, Wei Zhou, Egor Lakomkin, Xiaohui Zhang, Chunyang Wu, Frank Seide, Jay Mahadeokar, Ozlem Kalinli

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

2410.02425 2024-10-04 cs.DC cs.CL cs.LG 86%

LLM-Pilot: Characterize and Optimize Performance of your LLM Inference Services

Małgorzata Łazuka, Andreea Anghel, Thomas Parnell

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

Comments Accepted to the International Conference for High Performance Computing, Networking, Storage and Analysis (SC '24)

2410.01724 2024-10-03 cs.CL cs.AI 86%

Auto-Demo Prompting: Leveraging Generated Outputs as Demonstrations for Enhanced Batch Prompting

Longyu Feng, Mengze Hong, Chen Jason Zhang

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

2407.09111 2024-10-02 cs.AI cs.LG 86%

Inference Optimization of Foundation Models on AI Accelerators

Youngsuk Park, Kailash Budhathoki, Liangfu Chen, Jonas Kübler, Jiaji Huang, Matthäus Kleindessner, Jun Huan, Volkan Cevher, Yida Wang, George Karypis

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

Comments [v2] Tutorial website added [v1] Tutorial published at KDD 2024. Camera-ready version

2408.09794 2024-10-01 cs.AI cs.CL 86%

AutoML-guided Fusion of Entity and LLM-based Representations for Document Classification

Boshko Koloski, Senja Pollak, Roberto Navigli, Blaž Škrlj

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

Comments Accepted at the 2024 Discovery Science Conference, oral presentation track

2408.09785 2024-10-01 cs.AI cs.CL cs.SE 86%

GoNoGo: An Efficient LLM-based Multi-Agent System for Streamlining Automotive Software Release Decision-Making

Arsham Gholamzadeh Khoee, Yinan Yu, Robert Feldt, Andris Freimanis, Patrick Andersson Rhodin, Dhasarathy Parthasarathy

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

2404.04281 2024-10-01 cs.CL cs.AI 86%

Similar Data Points Identification with LLM: A Human-in-the-loop Strategy Using Summarization and Hidden State Insights

Xianlong Zeng, Yijing Gao, Fanghao Song, Ang Liu

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

2402.10712 2024-09-27 cs.CL cs.AI 86%

An Empirical Study on Cross-lingual Vocabulary Adaptation for Efficient Language Model Inference

Atsuki Yamaguchi, Aline Villavicencio, Nikolaos Aletras

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

Comments Accepted at EMNLP 2024 Findings

2409.11155 2024-09-18 cs.DC cs.CL cs.LG cs.PF 86%

ISO: Overlap of Computation and Communication within Seqenence For LLM Inference

Bin Xiao, Lei Su

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

2406.02616 2024-09-12 cs.LG cs.AI 86%

Adaptive Layer Splitting for Wireless LLM Inference in Edge Computing: A Model-Based Reinforcement Learning Approach

Yuxuan Chen, Rongpeng Li, Xiaoxue Yu, Zhifeng Zhao, Honggang Zhang

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

2407.03637 2024-09-09 cs.LG cs.CL 86%

QET: Enhancing Quantized LLM Parameters and KV cache Compression through Element Substitution and Residual Clustering

Yanshu Wang, Wang Li, Zhaoqian Yao, Tong Yang

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

2409.01483 2024-09-04 cs.LG cs.CL 86%

Revisiting SMoE Language Models by Evaluating Inefficiencies with Task Specific Expert Pruning

Soumajyoti Sarkar, Leonard Lausen, Volkan Cevher, Sheng Zha, Thomas Brox, George Karypis

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

2406.10774 2024-08-28 cs.CL cs.LG 86%

Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference

Jiaming Tang, Yilong Zhao, Kan Zhu, Guangxuan Xiao, Baris Kasikci, Song Han

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

Comments ICML 2024

2408.11849 2024-08-23 cs.CL cs.AI eess.AS 86%

Style-Talker: Finetuning Audio Language Model and Style-Based Text-to-Speech Model for Fast Spoken Dialogue Generation

Yinghao Aaron Li, Xilin Jiang, Jordan Darefsky, Ge Zhu, Nima Mesgarani

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

Comments CoLM 2024

2403.00952 2024-08-09 cs.CL cs.LG 86%

MediSwift: Efficient Sparse Pre-trained Biomedical Language Models

Vithursan Thangarasa, Mahmoud Salem, Shreyas Saxena, Kevin Leong, Joel Hestness, Sean Lie

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

Comments 14 pages, 2 Figures, 5 Tables (Main Paper) + 3 pages (Supplementary Material). Published at ACL 2024

2408.03561 2024-08-08 cs.CR cs.AI cs.LG 86%

MPC-Minimized Secure LLM Inference

Deevashwer Rathee, Dacheng Li, Ion Stoica, Hao Zhang, Raluca Popa

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

2408.01935 2024-08-06 cs.CL cs.AI 86%

Defining and Evaluating Decision and Composite Risk in Language Models Applied to Natural Language Inference

Ke Shen, Mayank Kejriwal

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

Comments arXiv admin note: text overlap with arXiv:2310.03283

2408.01453 2024-08-06 cs.CY cs.AI cs.CL 86%

Reporting and Analysing the Environmental Impact of Language Models on the Example of Commonsense Question Answering with External Knowledge

Aida Usmanova, Junbo Huang, Debayan Banerjee, Ricardo Usbeck

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

Comments Presented at Bonn Sustainable AI 2023 conference

2307.05908 2024-07-30 cs.CL cs.LG 86%

Predictive Pipelined Decoding: A Compute-Latency Trade-off for Exact LLM Decoding

Seongjun Yang, Gibbeum Lee, Jaewoong Cho, Dimitris Papailiopoulos, Kangwook Lee

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

Comments ES-FoMo Workshop at ICML 2023 / Published in TMLR

1. 效率与部署 22280 篇

Meaning Typed Prompting: A Technique for Efficient, Reliable Structured Output Generation

TensorOpera Router: A Multi-Model Router for Efficient LLM Inference

BrainTransformers: SNN-LLM

Characterizing the Accuracy -- Efficiency Trade-off of Low-rank Decomposition in Language Models

DAQ: Density-Aware Post-Training Weight-Only Quantization For LLMs

SeedLM: Compressing LLM Weights into Seeds of Pseudo-Random Generators

Efficient Stagewise Pretraining via Progressive Subnetworks

SqueezeAttention: 2D Management of KV-Cache in LLM Inference via Layer-wise Optimal Budget

Performance Characterization of Expert Router for Scalable LLM Inference

CaLMFlow: Volterra Flow Matching using Causal Language Models

LLM-TOPLA: Efficient LLM Ensemble by Maximising Diversity

Efficient Streaming LLM for Speech Recognition

LLM-Pilot: Characterize and Optimize Performance of your LLM Inference Services

Auto-Demo Prompting: Leveraging Generated Outputs as Demonstrations for Enhanced Batch Prompting

Inference Optimization of Foundation Models on AI Accelerators

AutoML-guided Fusion of Entity and LLM-based Representations for Document Classification

GoNoGo: An Efficient LLM-based Multi-Agent System for Streamlining Automotive Software Release Decision-Making

Similar Data Points Identification with LLM: A Human-in-the-loop Strategy Using Summarization and Hidden State Insights

An Empirical Study on Cross-lingual Vocabulary Adaptation for Efficient Language Model Inference

ISO: Overlap of Computation and Communication within Seqenence For LLM Inference

Adaptive Layer Splitting for Wireless LLM Inference in Edge Computing: A Model-Based Reinforcement Learning Approach

QET: Enhancing Quantized LLM Parameters and KV cache Compression through Element Substitution and Residual Clustering

Revisiting SMoE Language Models by Evaluating Inefficiencies with Task Specific Expert Pruning

Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference

Style-Talker: Finetuning Audio Language Model and Style-Based Text-to-Speech Model for Fast Spoken Dialogue Generation

MediSwift: Efficient Sparse Pre-trained Biomedical Language Models

MPC-Minimized Secure LLM Inference

Defining and Evaluating Decision and Composite Risk in Language Models Applied to Natural Language Inference

Reporting and Analysing the Environmental Impact of Language Models on the Example of Commonsense Question Answering with External Knowledge

Predictive Pipelined Decoding: A Compute-Latency Trade-off for Exact LLM Decoding