语言大模型 / LLM - arXivDaily 专题

2412.16260 2024-12-24 cs.LG cs.CC cs.CL 84%

Inference Scaling vs Reasoning: An Empirical Analysis of Compute-Optimal LLM Problem-Solving

Marwan AbdElhameed, Pavly Halim

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

2412.16176 2024-12-24 cs.SD cs.CL cs.LG eess.AS 84%

Efficient VoIP Communications through LLM-based Real-Time Speech Reconstruction and Call Prioritization for Emergency Services

Danush Venkateshperumal, Rahman Abdul Rafi, Shakil Ahmed, Ashfaq Khokhar

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

Comments 15 pages,8 figures

2409.01227 2024-12-20 cs.CL cs.LG 84%

Prompt Compression with Context-Aware Sentence Encoding for Fast and Improved LLM Inference

Barys Liskavets, Maxim Ushakov, Shuvendu Roy, Mark Klibanov, Ali Etemad, Shane Luke

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

Comments Accepted in AAAI Conference on Artificial Intelligence (AAAI-25)

2406.13362 2024-12-20 cs.CV cs.CL cs.LG 84%

VisualRWKV: Exploring Recurrent Neural Networks for Visual Language Models

Haowen Hou, Peigen Zeng, Fei Ma, Fei Richard Yu

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

Comments Accepted at COLING 2025 main conference

2412.11053 2024-12-17 cs.CL cs.AI 84%

NITRO: LLM Inference on Intel Laptop NPUs

Anthony Fei, Mohamed S. Abdelfattah

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

Comments 11 pages, 7 figures

2407.15012 2024-12-16 cs.CY cs.CL cs.LG cs.SI 84%

Transformative Influence of LLM and AI Tools in Student Social Media Engagement: Analyzing Personalization, Communication Efficiency, and Collaborative Learning

Masoud Bashiri, Kamran Kowsari

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

2410.13229 2024-12-10 cs.LG cs.AI 84%

Quamba: A Post-Training Quantization Recipe for Selective State Space Models

Hung-Yueh Chiang, Chi-Chih Chang, Natalia Frumkin, Kai-Chiang Wu, Diana Marculescu

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

2411.13009 2024-11-22 cs.LG cs.CL 84%

LLMSteer: Improving Long-Context LLM Inference by Steering Attention on Reused Contexts

Zhuohan Gu, Jiayi Yao, Kuntai Du, Junchen Jiang

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

2411.12307 2024-11-20 cs.CL cs.AI cs.IR 84%

Balancing Accuracy and Efficiency in Multi-Turn Intent Classification for LLM-Powered Dialog Systems in Production

Junhua Liu, Yong Keat Tan, Bin Fu, Kwan Hui Lim

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

2407.11798 2024-11-19 cs.CL cs.DC cs.LG 84%

PipeInfer: Accelerating LLM Inference using Asynchronous Pipelined Speculation

Branden Butler, Sixing Yu, Arya Mazaheri, Ali Jannesari

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

Comments 11 pages, submitted to SC24 conference

2411.07536 2024-11-13 cs.LG cs.AI cs.DS stat.ML 84%

Model Stealing for Any Low-Rank Language Model

Allen Liu, Ankur Moitra

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

2407.16958 2024-11-13 cs.LG cs.AI 84%

Wonderful Matrices: More Efficient and Effective Architecture for Language Modeling Tasks

Jingze Shi, Bingheng Wu, Lu He, Luchang Jiang

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

Comments 28 pages, 8 figures, 7 tables

2404.15146 2024-11-13 cs.LG cs.CL 84%

Rethinking LLM Memorization through the Lens of Adversarial Compression

Avi Schwarzschild, Zhili Feng, Pratyush Maini, Zachary C. Lipton, J. Zico Kolter

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

Comments https://locuslab.github.io/acr-memorization

2402.08958 2024-11-06 cs.LG cs.AI 84%

Towards Next-Level Post-Training Quantization of Hyper-Scale Transformers

Junhan Kim, Chungman Lee, Eulrang Cho, Kyungphil Park, Ho-young Kim, Joonyoung Kim, Yongkweon Jeon

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

Comments Accepted to NeurIPS 2024

2404.15420 2024-11-04 cs.CL cs.AI 84%

XC-Cache: Cross-Attending to Cached Context for Efficient LLM Inference

João Monteiro, Étienne Marcotte, Pierre-André Noël, Valentina Zantedeschi, David Vázquez, Nicolas Chapados, Christopher Pal, Perouz Taslakian

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

2410.23317 2024-11-01 cs.CV cs.AI cs.CL cs.DC cs.PF 84%

VL-Cache: Sparsity and Modality-Aware KV Cache Compression for Vision-Language Model Inference Acceleration

Dezhan Tu, Danylo Vashchilenko, Yuzhe Lu, Panpan Xu

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

2410.22480 2024-10-31 cs.CL cs.AI 84%

Scaling LLM Inference with Optimized Sample Compute Allocation

Kexun Zhang, Shang Zhou, Danqing Wang, William Yang Wang, Lei Li

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

2410.17375 2024-10-24 cs.CL cs.DC cs.LG 84%

AMUSD: Asynchronous Multi-Device Speculative Decoding for LLM Acceleration

Bradley McDanel

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

Comments 4 pages, 5 figures, 1 table, 1 algorithm

2410.15778 2024-10-23 cs.CV cs.AI cs.LG cs.MM 84%

Reducing Hallucinations in Vision-Language Models via Latent Space Steering

Sheng Liu, Haotian Ye, Lei Xing, James Zou

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

Comments 21 pages

2406.13170 2024-10-21 cs.AI cs.CL 84%

Amphista: Bi-directional Multi-head Decoding for Accelerating LLM Inference

Zeping Li, Xinlong Yang, Ziheng Gao, Ji Liu, Guanchen Li, Zhuang Liu, Dong Li, Jinzhang Peng, Lu Tian, Emad Barsoum

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

2410.12856 2024-10-18 cs.CL cs.AI 84%

Optimized Biomedical Question-Answering Services with LLM and Multi-BERT Integration

Cheng Qian, Xianglong Shi, Shanshan Yao, Yichen Liu, Fengming Zhou, Zishu Zhang, Junaid Akram, Ali Braytee, Ali Anaissi

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

Comments 10 pages, 12 figures, accepted and to be published in the proceedings of 2024 IEEE International Conference on Data Mining Workshops (ICDMW)

2410.12707 2024-10-17 cs.DC cs.AI cs.LG 84%

FusionLLM: A Decentralized LLM Training System on Geo-distributed GPUs with Adaptive Compression

Zhenheng Tang, Xueze Kang, Yiming Yin, Xinglin Pan, Yuxin Wang, Xin He, Qiang Wang, Rongfei Zeng, Kaiyong Zhao, Shaohuai Shi, Amelie Chi Zhou, Bo Li, Bingsheng He, Xiaowen Chu

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

2410.11410 2024-10-16 cs.CL cs.AI 84%

PMMT: Preference Alignment in Multilingual Machine Translation via LLM Distillation

Shuqiao Sun, Yutong Yao, Peiwen Wu, Feijun Jiang, Kaifu Zhang

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

2410.10728 2024-10-15 cs.LG cs.AI 84%

Towards LLM-guided Efficient and Interpretable Multi-linear Tensor Network Rank Selection

Giorgos Iacovides, Wuyang Zhou, Danilo Mandic

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

2404.08811 2024-10-15 cs.ET cs.AI cs.AR cs.LG 84%

Reducing the Barriers to Entry for Foundation Model Training

Paolo Faraboschi, Ellis Giles, Justin Hotard, Konstanty Owczarek, Andrew Wheeler

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

2410.06541 2024-10-14 cs.CL cs.AI 84%

Chip-Tuning: Classify Before Language Models Say

Fangwei Zhu, Dian Li, Jiajun Huang, Gang Liu, Hui Wang, Zhifang Sui

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

2410.04275 2024-10-08 cs.LG cs.CL 84%

Language Model-Driven Data Pruning Enables Efficient Active Learning

Abdul Hameed Azeemi, Ihsan Ayyub Qazi, Agha Ali Raza

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

Comments 20 pages, 4 figures

2406.17404 2024-10-08 cs.CL cs.LG 84%

Make Some Noise: Unlocking Language Model Parallel Inference Capability through Noisy Training

Yixuan Wang, Xianzhen Luo, Fuxuan Wei, Yijun Liu, Qingfu Zhu, Xuanyu Zhang, Qing Yang, Dongliang Xu, Wanxiang Che

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

Comments EMNLP 2024, camera ready

2409.17819 2024-09-27 cs.CL cs.AI 84%

Inference-Time Language Model Alignment via Integrated Value Guidance

Zhixuan Liu, Zhanhui Zhou, Yuanfu Wang, Chao Yang, Yu Qiao

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

Comments EMNLP 2024 Findings

2409.14436 2024-09-24 cs.CL cs.AI cs.RO 84%

Automotive innovation landscaping using LLM

Raju Gorain, Omkar Salunke

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

Comments 9pages, 4Figures, 1 Flow chart

1. 效率与部署 22405 篇

Inference Scaling vs Reasoning: An Empirical Analysis of Compute-Optimal LLM Problem-Solving

Efficient VoIP Communications through LLM-based Real-Time Speech Reconstruction and Call Prioritization for Emergency Services

Prompt Compression with Context-Aware Sentence Encoding for Fast and Improved LLM Inference

VisualRWKV: Exploring Recurrent Neural Networks for Visual Language Models

NITRO: LLM Inference on Intel Laptop NPUs

Transformative Influence of LLM and AI Tools in Student Social Media Engagement: Analyzing Personalization, Communication Efficiency, and Collaborative Learning

Quamba: A Post-Training Quantization Recipe for Selective State Space Models

LLMSteer: Improving Long-Context LLM Inference by Steering Attention on Reused Contexts

Balancing Accuracy and Efficiency in Multi-Turn Intent Classification for LLM-Powered Dialog Systems in Production

PipeInfer: Accelerating LLM Inference using Asynchronous Pipelined Speculation

Model Stealing for Any Low-Rank Language Model

Wonderful Matrices: More Efficient and Effective Architecture for Language Modeling Tasks

Rethinking LLM Memorization through the Lens of Adversarial Compression

Towards Next-Level Post-Training Quantization of Hyper-Scale Transformers

XC-Cache: Cross-Attending to Cached Context for Efficient LLM Inference

VL-Cache: Sparsity and Modality-Aware KV Cache Compression for Vision-Language Model Inference Acceleration

Scaling LLM Inference with Optimized Sample Compute Allocation

AMUSD: Asynchronous Multi-Device Speculative Decoding for LLM Acceleration

Reducing Hallucinations in Vision-Language Models via Latent Space Steering

Amphista: Bi-directional Multi-head Decoding for Accelerating LLM Inference

Optimized Biomedical Question-Answering Services with LLM and Multi-BERT Integration

FusionLLM: A Decentralized LLM Training System on Geo-distributed GPUs with Adaptive Compression

PMMT: Preference Alignment in Multilingual Machine Translation via LLM Distillation

Towards LLM-guided Efficient and Interpretable Multi-linear Tensor Network Rank Selection

Reducing the Barriers to Entry for Foundation Model Training

Chip-Tuning: Classify Before Language Models Say

Language Model-Driven Data Pruning Enables Efficient Active Learning

Make Some Noise: Unlocking Language Model Parallel Inference Capability through Noisy Training

Inference-Time Language Model Alignment via Integrated Value Guidance

Automotive innovation landscaping using LLM