语言大模型 / LLM - arXivDaily 专题

1911.10235 2019-12-03 cs.CL cs.LG 81%

Improving N-gram Language Models with Pre-trained Deep Transformer

Yiren Wang, Hongzhao Huang, Zhe Liu, Yutong Pang, Yongqiang Wang, ChengXiang Zhai, Fuchun Peng

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

1906.09777 2019-11-07 cs.CL cs.LG 81%

A Tensorized Transformer for Language Modeling

Xindian Ma, Peng Zhang, Shuai Zhang, Nan Duan, Yuexian Hou, Dawei Song, Ming Zhou

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

Comments Accepted by NeurIPS 2019

1910.10670 2019-10-24 cs.CL cs.LG 81%

Efficient Dynamic WFST Decoding for Personalized Language Models

Jun Liu, Jiedan Zhu, Vishal Kathuria, Fuchun Peng

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

Comments 5 pages, 4 figures

1910.06294 2019-10-18 cs.CL cs.LG 81%

Training Compact Models for Low Resource Entity Tagging using Pre-trained Language Models

Peter Izsak, Shira Guskin, Moshe Wasserblat

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

Comments Accepted to the 5th Workshop on Energy Efficient Machine Learning and Cognitive Computing - NeurIPS 2019

1910.03432 2019-10-09 cs.CL cs.LG 81%

Federated Learning of N-gram Language Models

Mingqing Chen, Ananda Theertha Suresh, Rajiv Mathews, Adeline Wong, Cyril Allauzen, Françoise Beaufays, Michael Riley

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

Comments 10 pages

1906.03805 2019-09-10 cs.LG cs.CL stat.ML 81%

Improving Neural Language Modeling via Adversarial Training

Dilin Wang, Chengyue Gong, Qiang Liu

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

Journal ref International Conference on Machine Learning 2019

1909.00325 2019-09-04 cs.CL cs.LG 81%

Repurposing Decoder-Transformer Language Models for Abstractive Summarization

Luke de Oliveira, Alfredo Láinez Rodrigo

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

1907.01677 2019-07-04 cs.CL cs.LG 81%

Scalable Multi Corpora Neural Language Models for ASR

Anirudh Raju, Denis Filimonov, Gautam Tiwari, Guitang Lan, Ariya Rastrow

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

Comments Interspeech 2019 (accepted: oral)

1906.06438 2019-06-18 cs.CL cs.LG 81%

Scalable Syntax-Aware Language Models Using Knowledge Distillation

Adhiguna Kuncoro, Chris Dyer, Laura Rimell, Stephen Clark, Phil Blunsom

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

Comments ACL 2019

1902.02380 2019-04-09 cs.CL cs.LG 81%

Compression of Recurrent Neural Networks for Efficient Language Modeling

Artem M. Grachev, Dmitry I. Ignatov, Andrey V. Savchenko

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

Comments 25 pages, 3 tables, 4 figures

1812.02142 2018-12-06 cs.CL cs.LG 81%

End-to-end contextual speech recognition using class language models and a token passing decoder

Zhehuai Chen, Mahaveer Jain, Yongqiang Wang, Michael L. Seltzer, Christian Fuegen

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

Comments submit to ICASSP2019

1809.10282 2018-09-30 cs.CL cs.LG 81%

Adaptive Pruning of Neural Language Models for Mobile Devices

Raphael Tang, Jimmy Lin

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

Comments 10 pages, 3 figures, 2 tables, submitted to ICLR 2019

1712.07473 2018-03-07 cs.CL cs.CR cs.LG 81%

Differentially Private Distributed Learning for Language Modeling Tasks

Vadim Popov, Mikhail Kudinov, Irina Piontkovskaya, Petr Vytovtov, Alex Nevidomsky

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

1801.09866 2018-01-31 cs.CL cs.LG 81%

Accelerating recurrent neural network language model based online speech recognition system

Kyungmin Lee, Chiyoun Park, Namhoon Kim, Jaewon Lee

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

Comments 4 pages, 4 figures, 3 tables, ICASSP2018(Accepted)

1712.01996 2017-12-07 eess.AS cs.AI cs.CL cs.SD 81%

An analysis of incorporating an external language model into a sequence-to-sequence model

Anjuli Kannan, Yonghui Wu, Patrick Nguyen, Tara N. Sainath, Zhifeng Chen, Rohit Prabhavalkar

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

1709.04109 2017-11-27 cs.CL cs.LG 81%

Empower Sequence Labeling with Task-Aware Neural Language Model

Liyuan Liu, Jingbo Shang, Frank F. Xu, Xiang Ren, Huan Gui, Jian Peng, Jiawei Han

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

Comments AAAI 2018

1701.03578 2017-10-11 cs.CL cs.AI 81%

Efficient Transfer Learning Schemes for Personalized Language Modeling using Recurrent Neural Network

Seunghyun Yoon, Hyeongu Yun, Yuna Kim, Gyu-tae Park, Kyomin Jung

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

Comments AAAI workshop on Crowdsourcing, Deep Learning and Artificial Intelligence Agents, Feb 2017, San Francisco CA, USA

1707.07240 2017-09-20 cs.CL cs.LG stat.ML 81%

Language modeling with Neural trans-dimensional random fields

Bin Wang, Zhijian Ou

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

Comments 6 pages, 2 figures and 3 tables, accepted to ASRU 2017

1512.04906 2015-12-16 cs.CL cs.LG 81%

Strategies for Training Large Vocabulary Neural Language Models

Welin Chen, David Grangier, Michael Auli

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

Comments 12 pages; journal paper; under review

1412.6650 2015-07-08 cs.NE cs.CL cs.LG 81%

Incremental Adaptation Strategies for Neural Network Language Models

Aram Ter-Sarkisov, Holger Schwenk, Loic Barrault, Fethi Bougares

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

Comments accepted as workshop paper at ACL-IJCNLP 2015

1312.7077 2014-10-06 cs.CL cs.LG stat.ML 81%

Language Modeling with Power Low Rank Ensembles

Ankur P. Parikh, Avneesh Saluja, Chris Dyer, Eric P. Xing

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

2606.11553 2026-06-11 cs.LG 新提交 80%

APEX: A Network-Native Time-Series Foundation Model for Forecasting and Anomaly Detection for Wireless Edge Operations

APEX：面向无线边缘运维的预测与异常检测的网络原生时间序列基础模型

Swadhin Pradhan, Niloo Bahadori, Peiman Amini

机构 * Cisco Systems, USA（思科系统公司）

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

AI总结提出网络原生解码器Transformer APEX，针对企业AP遥测数据预训练，在DHCP退化基准上MAE比最强基线降低18%，异常检测F1=0.93，边缘版本实现亚秒级隐私保护推理。

Comments 5 pages, 1 figure, 4 tables. Discusses a network-native time-series foundation model for wireless edge operations

2511.02979 2026-01-26 cs.HC cs.AI 80%

Systematizing LLM Persona Design: A Four-Quadrant Technical Taxonomy for AI Companion Applications

对LLM人设设计的系统化：面向AI陪伴应用的四象限技术分类

Esther Sun, Zichu Wu

机构 * Carnegie Mellon University（卡内基梅隆大学）

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

AI总结本文提出四象限技术分类系统，系统化LLM人设设计，涵盖虚拟与具身、情感与功能增强，分析不同应用场景的技术挑战与核心问题。

Comments Accepted to Neurips 2025 workshop: LLM Persona Workshop

2510.11176 2026-01-06 cs.CV cs.AI 80%

G2L:From Giga-Scale to Cancer-Specific Large-Scale Pathology Foundation Models via Knowledge Distillation

G2L：从千兆级到癌症特异性大规模病理基础模型的知识蒸馏

Yesung Cho, Sungmin Lee, Geongyu Lee, Minkyung Lee, Jongbae Park, Dongmyung Shin

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

AI总结 G2L框架通过知识蒸馏将千兆级模型能力转移到大规模模型，以更少的参数和数据实现癌症特异性任务的高性能表现。

Comments Accepted in AAAI 2026 workshop in Health Intelligence Special Theme on Foundation Models and AI Agents

2410.14879 2025-10-31 cs.HC cs.AI 80%

Vital Insight: Assisting Experts' Context-Driven Sensemaking of Multi-modal Personal Tracking Data Using Visualization and Human-In-The-Loop LLM

Jiachen Li, Xiwen Li, Justin Steinberg, Akshat Choube, Bingsheng Yao, Xuhai Xu, Dakuo Wang, Elizabeth Mynatt, Varun Mishra

机构 * Northeastern University（东北大学）； Columbia University（哥伦比亚大学）

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

Comments Jiachen Li, Xiwen Li, Justin Steinberg, Akshat Choube, Bingsheng Yao, Xuhai Xu, Dakuo Wang, Elizabeth Mynatt, and Varun Mishra. 2025. Vital Insight: Assisting Experts' Context-Driven Sensemaking of Multi-modal Personal Tracking Data Using Visualization and Human-in-the-Loop LLM. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. 9, 3, Article 101 (September 2025), 37 pages

Journal ref Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. 9 (2025) 101:1-37

2305.14019 2025-10-14 cs.AI cs.AR cs.PL 80%

ChipGPT: How far are we from natural language hardware design

Kaiyan Chang, Ying Wang, Haimeng Ren, Mengdi Wang, Shengwen Liang, Yinhe Han, Huawei Li, Xiaowei Li

机构 * State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences, China（处理器国家重点实验室，计算技术研究所，中国科学院，中国）； University of Chinese Academy of Sciences（中国科学院大学）； School of Information Science and Technology, ShanghaiTech University, China（信息科学与技术学院，上海科技大学，中国）

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

Comments Accepted by 2023 NeurIPS SysML Workshop, retitled to "Improving Large Language Model Hardware Generating Quality through Post-LLM Search"

2507.09514 2025-07-15 cs.CV cs.AI 80%

QuarterMap: Efficient Post-Training Token Pruning for Visual State Space Models

Tien-Yu Chi, Hung-Yueh Chiang, Diana Marculescu, Kai-Chiang Wu

机构 * National Yang Ming Chiao Tung University（国立阳明交通大学）； The University of Texas at Austin（德克萨斯大学奥斯汀分校）

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

Comments Accepted by Efficient Systems for Foundation Models Workshop at the International Conference on Machine Learning (ICML) 2025

2505.22637 2025-05-29 cs.LG 80%

Understanding (Un)Reliability of Steering Vectors in Language Models

Joschka Braun, Carsten Eickhoff, David Krueger, Seyed Ali Bahrainian, Dmitrii Krasheninnikov

机构 * University of Tübingen（图宾根大学）； Mila, University of Montreal（蒙特利尔大学机器学习研究所）； University of Cambridge（剑桥大学）

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

Comments 17 pages, 10 figures. Presented at the ICLR 2025 Workshop on Foundation Models in the Wild

2402.13991 2025-02-14 cs.CL 80%

Analysing The Impact of Sequence Composition on Language Model Pre-Training

Yu Zhao, Yuanbin Qu, Konrad Staniszewski, Szymon Tworkowski, Wei Liu, Piotr Miłoś, Yuxiang Wu, Pasquale Minervini

机构 * University of Edinburgh（爱丁堡大学）； Xiaomi AI Lab（小米AI实验室）； University of Warsaw（华沙大学）； Weco AI（维科人工智能）

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

Journal ref Analysing The Impact of Sequence Composition on Language Model Pre-Training (Zhao et al., ACL 2024)

2410.00531 2024-10-02 cs.DC cs.AI 80%

TPI-LLM: Serving 70B-scale LLMs Efficiently on Low-resource Edge Devices

Zonghang Li, Wenjiao Feng, Mohsen Guizani, Hongfang Yu

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

Comments This paper is currently under review. Find the code at https://github.com/Lizonghang/TPI-LLM

1. 效率与部署 22497 篇

Improving N-gram Language Models with Pre-trained Deep Transformer

A Tensorized Transformer for Language Modeling

Efficient Dynamic WFST Decoding for Personalized Language Models

Training Compact Models for Low Resource Entity Tagging using Pre-trained Language Models

Federated Learning of N-gram Language Models

Improving Neural Language Modeling via Adversarial Training

Repurposing Decoder-Transformer Language Models for Abstractive Summarization

Scalable Multi Corpora Neural Language Models for ASR

Scalable Syntax-Aware Language Models Using Knowledge Distillation

Compression of Recurrent Neural Networks for Efficient Language Modeling

End-to-end contextual speech recognition using class language models and a token passing decoder

Adaptive Pruning of Neural Language Models for Mobile Devices

Differentially Private Distributed Learning for Language Modeling Tasks

Accelerating recurrent neural network language model based online speech recognition system

An analysis of incorporating an external language model into a sequence-to-sequence model

Empower Sequence Labeling with Task-Aware Neural Language Model

Efficient Transfer Learning Schemes for Personalized Language Modeling using Recurrent Neural Network

Language modeling with Neural trans-dimensional random fields

Strategies for Training Large Vocabulary Neural Language Models

Incremental Adaptation Strategies for Neural Network Language Models

Language Modeling with Power Low Rank Ensembles

APEX: A Network-Native Time-Series Foundation Model for Forecasting and Anomaly Detection for Wireless Edge Operations

Systematizing LLM Persona Design: A Four-Quadrant Technical Taxonomy for AI Companion Applications

G2L:From Giga-Scale to Cancer-Specific Large-Scale Pathology Foundation Models via Knowledge Distillation

Vital Insight: Assisting Experts' Context-Driven Sensemaking of Multi-modal Personal Tracking Data Using Visualization and Human-In-The-Loop LLM

ChipGPT: How far are we from natural language hardware design

QuarterMap: Efficient Post-Training Token Pruning for Visual State Space Models

Understanding (Un)Reliability of Steering Vectors in Language Models

Analysing The Impact of Sequence Composition on Language Model Pre-Training

TPI-LLM: Serving 70B-scale LLMs Efficiently on Low-resource Edge Devices