语言大模型 / LLM - arXivDaily 专题

2312.01987 2024-04-05 cs.CV 85%

Bootstrapping SparseFormers from Vision Foundation Models

Ziteng Gao, Zhan Tong, Kevin Qinghong Lin, Joya Chen, Mike Zheng Shou

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

Comments CVPR 2024

2404.02781 2024-04-04 eess.AS cs.SD 85%

CLaM-TTS: Improving Neural Codec Language Model for Zero-Shot Text-to-Speech

Jaehyeon Kim, Keon Lee, Seungjun Chung, Jaewoong Cho

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

Comments ICLR 2024

2312.06742 2024-04-02 cs.CV cs.AI cs.CL cs.LG 85%

Honeybee: Locality-enhanced Projector for Multimodal LLM

Junbum Cha, Wooyoung Kang, Jonghwan Mun, Byungseok Roh

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 CVPR 2024 camera-ready

2309.14592 2024-04-02 cs.LG cs.AI cs.CL 85%

Efficient Post-training Quantization with FP8 Formats

Haihao Shen, Naveen Mellempudi, Xin He, Qun Gao, Chang Wang, Mengni Wang

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

2403.19735 2024-04-01 q-fin.RM 85%

Enhancing Anomaly Detection in Financial Markets with an LLM-based Multi-Agent Framework

Taejin Park

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

2403.17759 2024-03-27 cs.IR 85%

TWOLAR: a TWO-step LLM-Augmented distillation method for passage Reranking

Davide Baldelli, Junfeng Jiang, Akiko Aizawa, Paolo Torroni

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

2309.10668 2024-03-20 cs.LG cs.AI cs.CL cs.IT math.IT 85%

Language Modeling Is Compression

Grégoire Delétang, Anian Ruoss, Paul-Ambroise Duquenne, Elliot Catt, Tim Genewein, Christopher Mattern, Jordi Grau-Moya, Li Kevin Wenliang, Matthew Aitchison, Laurent Orseau, Marcus Hutter, Joel Veness

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

2403.11421 2024-03-19 cs.DC cs.PF 85%

FastDecode: High-Throughput GPU-Efficient LLM Serving using Heterogeneous Pipelines

Jiaao He, Jidong Zhai

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

Comments 15 pages, 15 figures

2403.10082 2024-03-18 cs.CV 85%

CrossGLG: LLM Guides One-shot Skeleton-based 3D Action Recognition in a Cross-level Manner

Tingbing Yan, Wenzheng Zeng, Yang Xiao, Xingyu Tong, Bo Tan, Zhiwen Fang, Zhiguo Cao, Joey Tianyi Zhou

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

2311.00257 2024-03-14 cs.DC 85%

AMSP: Reducing Communication Overhead of ZeRO for Efficient LLM Training

Qiaoling Chen, Qinghao Hu, Guoteng Wang, Yingtong Xiong, Ting Huang, Xun Chen, Yang Gao, Hang Yan, Yonggang Wen, Tianwei Zhang, Peng Sun

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

2306.11980 2024-03-06 cs.HC 85%

LLM-based Smart Reply (LSR): Enhancing Collaborative Performance with ChatGPT-mediated Smart Reply System

Ashish Bastola, Hao Wang, Judsen Hembree, Pooja Yadav, Zihao Gong, Emma Dixon, Abolfazl Razi, Nathan McNeese

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

2403.01273 2024-03-05 cs.LG cs.AI cs.CL 85%

NoMAD-Attention: Efficient LLM Inference on CPUs Through Multiply-add-free Attention

Tianyi Zhang, Jonah Wonkyu Yi, Bowen Yao, Zhaozhuo Xu, Anshumali Shrivastava

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

2402.14833 2024-02-26 cs.CL cs.AI cs.LG 85%

CliqueParcel: An Approach For Batching LLM Prompts That Jointly Optimizes Efficiency And Faithfulness

Jiayi Liu, Tinghan Yang, Jennifer Neville

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

2402.13088 2024-02-21 cs.CV 85%

Slot-VLM: SlowFast Slots for Video-Language Modeling

Jiaqi Xu, Cuiling Lan, Wenxuan Xie, Xuejin Chen, Yan Lu

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

Comments 16 pages, 10 figures

2401.13803 2024-01-26 cs.HC cond-mat.mtrl-sci 85%

Synergizing Human Expertise and AI Efficiency with Language Model for Microscopy Operation and Automated Experiment Design

Yongtao Liu, Marti Checa, Rama K. Vasudevan

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

Comments 16 pages; 7 figures

2401.11181 2024-01-23 cs.DC 85%

Inference without Interference: Disaggregate LLM Inference for Mixed Downstream Workloads

Cunchen Hu, Heyang Huang, Liangliang Xu, Xusheng Chen, Jiang Xu, Shuang Chen, Hao Feng, Chenxi Wang, Sa Wang, Yungang Bao, Ninghui Sun, Yizhou Shan

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

2306.13649 2024-01-18 cs.LG cs.AI cs.CL 85%

On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes

Rishabh Agarwal, Nino Vieillard, Yongchao Zhou, Piotr Stanczyk, Sabela Ramos, Matthieu Geist, Olivier Bachem

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

Comments Accepted at ICLR 2024. First two authors contributed equally

2312.09158 2023-12-15 cs.CV 85%

General Object Foundation Model for Images and Videos at Scale

Junfeng Wu, Yi Jiang, Qihao Liu, Zehuan Yuan, Xiang Bai, Song Bai

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

Comments Project homepage: https://glee-vision.github.io

2311.11696 2023-11-21 cs.CL cs.AI cs.LG 85%

Sparse Low-rank Adaptation of Pre-trained Language Models

Ning Ding, Xingtai Lv, Qiaosen Wang, Yulin Chen, Bowen Zhou, Zhiyuan Liu, Maosong Sun

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 Accepted to EMNLP 2023 (Main Conference)

2309.16134 2023-09-29 cs.SE 85%

Let's Chat to Find the APIs: Connecting Human, LLM and Knowledge Graph through AI Chain

Qing Huang, Zhenyu Wan, Zhenchang Xing, Changjing Wang, Jieshan Chen, Xiwei Xu, Qinghua Lu

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

Comments Accepted on ASE'2023

2309.13574 2023-09-26 cs.SE 85%

LLM for Test Script Generation and Migration: Challenges, Capabilities, and Opportunities

Shengcheng Yu, Chunrong Fang, Yuchen Ling, Chentian Wu, Zhenyu Chen

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

Comments Accepted by the 23rd IEEE International Conference on Software Quality, Reliability, and Security (QRS 2023)

2307.09782 2023-07-24 cs.LG cs.AI cs.CL 85%

ZeroQuant-FP: A Leap Forward in LLMs Post-Training W4A8 Quantization Using Floating-Point Formats

Xiaoxia Wu, Zhewei Yao, Yuxiong He

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

2306.15656 2023-07-19 cs.LG cs.AI cs.CC cs.CL cs.MS 85%

SparseOptimizer: Sparsify Language Models through Moreau-Yosida Regularization and Accelerate via Compiler Co-design

Fu-Ming Guo

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

2307.02390 2023-07-06 cs.AI cs.CL cs.LG 85%

Causal Discovery with Language Models as Imperfect Experts

Stephanie Long, Alexandre Piché, Valentina Zantedeschi, Tibor Schuster, Alexandre Drouin

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 Peer reviewed and accepted for presentation at the Structured Probabilistic Inference & Generative Modeling (SPIGM) workshop at ICML 2023, Hawaii, USA

2212.10511 2023-07-04 cs.CL cs.AI cs.LG 85%

When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories

Alex Mallen, Akari Asai, Victor Zhong, Rajarshi Das, Daniel Khashabi, Hannaneh Hajishirzi

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 ACL 2023; Code and data available at https://github.com/AlexTMallen/adaptive-retrieval

2203.01543 2022-03-07 cs.CL cs.AI cs.LG 85%

QaNER: Prompting Question Answering Models for Few-shot Named Entity Recognition

Andy T. Liu, Wei Xiao, Henghui Zhu, Dejiao Zhang, Shang-Wen Li, Andrew Arnold

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

Comments 8 pages, 6 figures

2604.24971 2026-04-29 cs.LG cs.CL cs.DC 84%

PolyKV: A Shared Asymmetrically-Compressed KV Cache Pool for Multi-Agent LLM Inference

PolyKV：一种用于多智能体LLM推理的共享非对称压缩KV缓存池

Ishan Patel, Ishan Joshi

机构 * Independent Researcher（独立研究者）

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

AI总结 PolyKV通过非对称压缩技术实现多个并发推理代理共享单一KV缓存池，提升内存效率并减少推理延迟。

Comments 10 pages, 6 tables. Code: https://github.com/ishan1410/PolyKV Keywords: KV cache compression, multi-agent LLM inference, asymmetric quantization, FWHT, TurboQuant, shared memory

2602.07546 2026-02-10 cs.CL cs.LG 84%

Improving Variable-Length Generation in Diffusion Language Models via Length Regularization

通过长度正则化改进扩散语言模型的变长生成

Zicong Cheng, Ruixuan Jia, Jia Li, Guo-Wei Yang, Meng-Hao Guo, Shi-Min Hu

机构 * Tsinghua University（清华大学）； Proxseer Inc.（Proxseer公司）

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

AI总结本文提出LR-DLLM，通过长度正则化改进扩散语言模型的变长生成能力，提升了在未知长度下的生成效果。

Comments diffusion language models

2510.14961 2025-10-17 cs.LG cs.CL 84%

Efficient Parallel Samplers for Recurrent-Depth Models and Their Connection to Diffusion Language Models

Jonas Geiping, Xinyu Yang, Guinan Su

机构 * ELLIS Institute Tübingen & Max-Planck Institute for Intelligent Systems, Tübingen AI Center（图宾根ELLIS研究所及图宾根马克斯·普朗克智能系统研究所AI中心）

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

Comments Code can be found at https://github.com/seal-rg/recurrent-pretraining

2608.16647 2026-08-25 cs.CL 版本更新 84%

Every Coin Has Two Sides: On the Dual Nature of Generalization in On-Policy Distillation of Large Language Models

硬币皆有两面：关于大型语言模型的策略内蒸馏中泛化的双重性质

Zhaoyi Li, Deyang Kong, Yuan Wei, Evan Yang, Ranran Shen, Mahardika Krisna Ihsani, Ming Yang, Wei Zhang, Chuan Hao, Jian Yang, Ran Tao, Bryan Dai, Shikun Zhang, Wei Ye, Ying Wei, Defu Lian

机构 * University of Science and Technology of China（中国科学技术大学）； Peking University（北京大学）； IQuest Research（IQuest研究院）； MBZUAI（穆罕默德·本·扎耶德人工智能大学）； Zhejiang University（浙江大学）

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

AI总结本研究探究大型语言模型策略内蒸馏（OPD）的泛化特性，发现其迁移教师推理行为而非答案，同源配对泛化性强，异源配对适配性有限，多教师组合存在能力跷跷板效应，为诊断多教师OPD提供了视角。

Comments Under Review

1. 效率与部署 22405 篇

Bootstrapping SparseFormers from Vision Foundation Models

CLaM-TTS: Improving Neural Codec Language Model for Zero-Shot Text-to-Speech

Honeybee: Locality-enhanced Projector for Multimodal LLM

Efficient Post-training Quantization with FP8 Formats

Enhancing Anomaly Detection in Financial Markets with an LLM-based Multi-Agent Framework

TWOLAR: a TWO-step LLM-Augmented distillation method for passage Reranking

Language Modeling Is Compression

FastDecode: High-Throughput GPU-Efficient LLM Serving using Heterogeneous Pipelines

CrossGLG: LLM Guides One-shot Skeleton-based 3D Action Recognition in a Cross-level Manner

AMSP: Reducing Communication Overhead of ZeRO for Efficient LLM Training

LLM-based Smart Reply (LSR): Enhancing Collaborative Performance with ChatGPT-mediated Smart Reply System

NoMAD-Attention: Efficient LLM Inference on CPUs Through Multiply-add-free Attention

CliqueParcel: An Approach For Batching LLM Prompts That Jointly Optimizes Efficiency And Faithfulness

Slot-VLM: SlowFast Slots for Video-Language Modeling

Synergizing Human Expertise and AI Efficiency with Language Model for Microscopy Operation and Automated Experiment Design

Inference without Interference: Disaggregate LLM Inference for Mixed Downstream Workloads

On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes

General Object Foundation Model for Images and Videos at Scale

Sparse Low-rank Adaptation of Pre-trained Language Models

Let's Chat to Find the APIs: Connecting Human, LLM and Knowledge Graph through AI Chain

LLM for Test Script Generation and Migration: Challenges, Capabilities, and Opportunities

ZeroQuant-FP: A Leap Forward in LLMs Post-Training W4A8 Quantization Using Floating-Point Formats

SparseOptimizer: Sparsify Language Models through Moreau-Yosida Regularization and Accelerate via Compiler Co-design

Causal Discovery with Language Models as Imperfect Experts

When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories

QaNER: Prompting Question Answering Models for Few-shot Named Entity Recognition

PolyKV: A Shared Asymmetrically-Compressed KV Cache Pool for Multi-Agent LLM Inference

Improving Variable-Length Generation in Diffusion Language Models via Length Regularization

Efficient Parallel Samplers for Recurrent-Depth Models and Their Connection to Diffusion Language Models

Every Coin Has Two Sides: On the Dual Nature of Generalization in On-Policy Distillation of Large Language Models