语言大模型 / LLM - arXivDaily 专题

2407.18213 2025-06-06 cs.LG cs.AI cs.CL cs.CR 82%

Scaling Trends in Language Model Robustness

Nikolaus Howe, Ian McKenzie, Oskar Hollinsworth, Michał Zajac, Tom Tseng, Aaron Tucker, Pierre-Luc Bacon, Adam Gleave

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

Comments 59 pages; updated to ICML version

2506.00045 2025-06-03 cs.SD eess.AS 82%

ACE-Step: A Step Towards Music Generation Foundation Model

Junmin Gong, Sean Zhao, Sen Wang, Shengyuan Xu, Joe Guo

机构 * ACE Studio（ACE工作室）

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

Comments 14 pages, 5 figures, ace-step's tech report

2505.22857 2025-05-30 eess.AS cs.AI cs.CL cs.LG cs.SD 82%

NGPU-LM: GPU-Accelerated N-Gram Language Model for Context-Biasing in Greedy ASR Decoding

Vladimir Bataev, Andrei Andrusenko, Lilit Grigoryan, Aleksandr Laptev, Vitaly Lavrukhin, Boris Ginsburg

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

Comments Accepted to Interspeech 2025

2504.14775 2025-05-29 cs.DC 82%

gLLM: Global Balanced Pipeline Parallelism System for Distributed LLM Serving with Token Throttling

Tianyu Guo, Xianwei Zhang, Jiangsu Du, Zhiguang Chen, Nong Xiao, Yutong Lu

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

2412.18232 2025-05-29 cs.IR 82%

Efficient Long Context Language Model Retrieval with Compression

Minju Seo, Jinheon Baek, Seongyun Lee, Sung Ju Hwang

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

Comments ACL 2025

2505.19179 2025-05-27 cs.SD eess.AS eess.SP 82%

BR-ASR: Efficient and Scalable Bias Retrieval Framework for Contextual Biasing ASR in Speech LLM

Xun Gong, Anqi Lv, Zhiming Wang, Huijia Zhu, Yanmin Qian

机构 * AI Institute School of Computer Science, Shanghai Jiao Tong University（人工智能研究院计算机学院，上海交通大学）； MoE Key Lab of AI AntGroup（AI人工智能混合专家实验室，蚂蚁集团）

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

Comments Accepted by InterSpeech 2025

2409.07267 2025-05-22 cs.CV 82%

MiniDrive: More Efficient Vision-Language Models with Multi-Level 2D Features as Text Tokens for Autonomous Driving

Enming Zhang, Xingyuan Dai, Min Huang, Yisheng Lv, Qinghai Miao

机构 * School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）； State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）

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

2503.04606 2025-04-30 cs.CV cs.AI cs.CL cs.LG 82%

The Best of Both Worlds: Integrating Language Models and Diffusion Models for Video Generation

Aoxiong Yin, Kai Shen, Yichong Leng, Xu Tan, Xinyu Zhou, Juncheng Li, Siliang Tang

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

Comments Our code is available at https://github.com/LanDiff/LanDiff

2504.17449 2025-04-25 cs.LG cs.AI cs.CL 82%

HMI: Hierarchical Knowledge Management for Efficient Multi-Tenant Inference in Pretrained Language Models

Jun Zhang, Jue Wang, Huan Li, Lidan Shou, Ke Chen, Gang Chen, Qin Xie, Guiming Xie, Xuejian Gong

机构 * The State Key Laboratory of Blockchain and Data Security, Zhejiang University（区块链与数据安全国家重点实验室，浙江大学）； Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security（杭州高新技术区（滨江）区块链与数据安全研究院）； OPPO AI Center（OPPO人工智能中心）

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

Comments Accepted by VLDBJ 2025

2504.10150 2025-04-23 cs.IR cs.MM 82%

HistLLM: A Unified Framework for LLM-Based Multimodal Recommendation with User History Encoding and Compression

Chen Zhang, Bo Hu, Weidong Chen, Zhendong Mao

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

Comments We want to withdraw this paper and revise its experimental details. The revised version will be uploaded after further verification

2504.12137 2025-04-17 cs.CV cs.AI cs.CL cs.LG 82%

Efficient Contrastive Decoding with Probabilistic Hallucination Detection - Mitigating Hallucinations in Large Vision Language Models -

Laura Fieback, Nishilkumar Balar, Jakob Spiegelberg, Hanno Gottschalk

机构 * Volkswagen AG（大众汽车集团）； Technical University Berlin（柏林工业大学）； University of Siegen（锡根大学）

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

2504.10854 2025-04-16 cs.CV 82%

LVLM_CSP: Accelerating Large Vision Language Models via Clustering, Scattering, and Pruning for Reasoning Segmentation

Hanning Chen, Yang Ni, Wenjun Huang, Hyunwoo Oh, Yezi Liu, Tamoghno Das, Mohsen Imani

机构 * University of California, Irvine（加州大学欧文分校）

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

2504.06279 2025-04-10 q-fin.ST 82%

Financial Analysis: Intelligent Financial Data Analysis System Based on LLM-RAG

Jingru Wang, Wen Ding, Xiaotong Zhu

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

2503.15369 2025-03-20 cs.CV 82%

EfficientLLaVA:Generalizable Auto-Pruning for Large Vision-language Models

Yinan Liang, Ziwei Wang, Xiuwei Xu, Jie Zhou, Jiwen Lu

机构 * Tsinghua University（清华大学）； Nanyang Technological University（南洋理工大学）

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

Comments Accepted by CVPR 2025

2503.15252 2025-03-20 cs.DC cs.PF 82%

Efficient allocation of image recognition and LLM tasks on multi-GPU system

Marcin Lawenda, Krzesimir Samborski, Kyrylo Khloponin, Łukasz Szustak

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

2411.11223 2025-03-19 cs.CV 82%

Efficient Transfer Learning for Video-language Foundation Models

Haoxing Chen, Zizheng Huang, Yan Hong, Yanshuo Wang, Zhongcai Lyu, Zhuoer Xu, Jun Lan, Zhangxuan Gu

机构 * Ant Group（蚂蚁集团）； Nanjing Univeristy（南京大学）； Shanghai Innovation Institute（上海创新研究院）； Australian National University（澳大利亚国立大学）

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

Comments Accepted by CVPR 2025

2412.13817 2025-03-18 cs.CV 82%

Nullu: Mitigating Object Hallucinations in Large Vision-Language Models via HalluSpace Projection

Le Yang, Ziwei Zheng, Boxu Chen, Zhengyu Zhao, Chenhao Lin, Chao Shen

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

Comments CVPR 2025

2503.01001 2025-03-18 cs.IR 82%

Towards An Efficient LLM Training Paradigm for CTR Prediction

Allen Lin, Renqin Cai, Yun He, Hanchao Yu, Jing Qian, Rui Li, Qifan Wang, James Caverlee

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

2412.06858 2025-03-18 cs.LG cs.AI cs.CL 82%

Taming Sensitive Weights : Noise Perturbation Fine-tuning for Robust LLM Quantization

Dongwei Wang, Huanrui Yang

机构 * University of Arizona（亚利桑那大学）

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

Comments Accepted as poster by CPAL2025

2405.14105 2025-03-18 cs.DC cs.AI cs.CL cs.LG 82%

Distributed Speculative Inference (DSI): Speculation Parallelism for Provably Faster Lossless Language Model Inference

Nadav Timor, Jonathan Mamou, Daniel Korat, Moshe Berchansky, Oren Pereg, Moshe Wasserblat, Tomer Galanti, Michal Gordon, David Harel

机构 * Weizmann Institute of Science（魏茨曼科学研究所）； Intel Labs（英特尔实验室）； Texas A&M University（得克萨斯农工大学）

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

Comments Published at ICLR 2025. (Link: https://openreview.net/forum?id=cJd1BgZ9CS)

Journal ref The 13th International Conference on Learning Representations (ICLR), 2025

2503.06976 2025-03-11 cs.CV 82%

Task-Specific Knowledge Distillation from the Vision Foundation Model for Enhanced Medical Image Segmentation

Pengchen Liang, Haishan Huang, Bin Pu, Jianguo Chen, Xiang Hua, Jing Zhang, Weibo Ma, Zhuangzhuang Chen, Yiwei Li, Qing Chang

机构 * Shanghai Jiao Tong University School of Medicine（上海交通大学医学院）； Shanghai University（上海大学）； Sun Yat-sen University（中山大学）； The Hong Kong University of Science and Technology（香港科技大学）； East China Normal University（华东师范大学）； Shanghai Jiao Tong University（上海交通大学）

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

Comments 29 pages, 10 figures, 16 tables

2503.06482 2025-03-11 cs.CV 82%

PathVQ: Reforming Computational Pathology Foundation Model for Whole Slide Image Analysis via Vector Quantization

Honglin Li, Zhongyi Shui, Yunlong Zhang, Chenglu Zhu, Lin Yang

机构 * Zhejiang University（浙江大学）； Research Center for Industries of the Future（未来产业研究中心）； School of Engineering, Westlake University（西湖大学工程学院）

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

2410.07516 2025-03-11 cs.SE 82%

Exploring and Lifting the Robustness of LLM-powered Automated Program Repair with Metamorphic Testing

Pengyu Xue, Linhao Wu, Zhen Yang, Zhongxing Yu, Zhi Jin, Ge Li, Yan Xiao, Shuo Liu, Xinyi Li, Hongyi Lin, Jingwen Wu

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

2411.17102 2025-03-05 cs.IR 82%

Scholar Name Disambiguation with Search-enhanced LLM Across Language

Renyu Zhao, Yunxin Chen

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

2503.00761 2025-03-04 cs.RO cs.CV cs.MA cs.SY eess.SY 82%

TRACE: A Self-Improving Framework for Robot Behavior Forecasting with Vision-Language Models

Gokul Puthumanaillam, Paulo Padrao, Jose Fuentes, Pranay Thangeda, William E. Schafer, Jae Hyuk Song, Karan Jagdale, Leonardo Bobadilla, Melkior Ornik

机构 * University of Illinois Urbana-Champaign (UIUC)（伊利诺伊大学厄巴纳-香槟分校）； Florida International University (FIU)（佛罗里达国际大学）； Lucid Group, Inc.（lucid集团公司）

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

2502.19712 2025-02-28 cs.IR 82%

Teaching Dense Retrieval Models to Specialize with Listwise Distillation and LLM Data Augmentation

Manveer Singh Tamber, Suleman Kazi, Vivek Sourabh, Jimmy Lin

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

2502.15964 2025-02-27 cs.LG cs.AI cs.CL cs.DC 82%

Minions: Cost-efficient Collaboration Between On-device and Cloud Language Models

Avanika Narayan, Dan Biderman, Sabri Eyuboglu, Avner May, Scott Linderman, James Zou, Christopher Re

机构 * Stanford University（斯坦福大学）； Together AI

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

2502.17535 2025-02-26 cs.LG cs.AI cs.CL cs.FL 82%

The Lottery LLM Hypothesis, Rethinking What Abilities Should LLM Compression Preserve?

Zhenheng Tang, Xiang Liu, Qian Wang, Peijie Dong, Bingsheng He, Xiaowen Chu, Bo Li

机构 * The Hong Kong University of Science and Technology（香港科技大学）； The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））； National University of Singapore（新加坡国立大学）

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

2502.16982 2025-02-25 cs.LG cs.AI cs.CL 82%

Muon is Scalable for LLM Training

Jingyuan Liu, Jianlin Su, Xingcheng Yao, Zhejun Jiang, Guokun Lai, Yulun Du, Yidao Qin, Weixin Xu, Enzhe Lu, Junjie Yan, Yanru Chen, Huabin Zheng, Yibo Liu, Shaowei Liu, Bohong Yin, Weiran He, Han Zhu, Yuzhi Wang, Jianzhou Wang, Mengnan Dong, Zheng Zhang, Yongsheng Kang, Hao Zhang, Xinran Xu, Yutao Zhang, Yuxin Wu, Xinyu Zhou, Zhilin Yang

机构 * Moonshot AI（月之暗面科技）； UCLA（加利福尼亚大学洛杉矶分校）

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

2502.16842 2025-02-25 cs.CV 82%

Exploring Causes and Mitigation of Hallucinations in Large Vision Language Models

Yaqi Sun, Kyohei Atarashi, Koh Takeuchi, Hisashi Kashima

机构 * Kyoto University（京都大学）

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

Comments 19 pages, 6 figures

1. 效率与部署 22497 篇

Scaling Trends in Language Model Robustness

ACE-Step: A Step Towards Music Generation Foundation Model

NGPU-LM: GPU-Accelerated N-Gram Language Model for Context-Biasing in Greedy ASR Decoding

gLLM: Global Balanced Pipeline Parallelism System for Distributed LLM Serving with Token Throttling

Efficient Long Context Language Model Retrieval with Compression

BR-ASR: Efficient and Scalable Bias Retrieval Framework for Contextual Biasing ASR in Speech LLM

MiniDrive: More Efficient Vision-Language Models with Multi-Level 2D Features as Text Tokens for Autonomous Driving

The Best of Both Worlds: Integrating Language Models and Diffusion Models for Video Generation

HMI: Hierarchical Knowledge Management for Efficient Multi-Tenant Inference in Pretrained Language Models

HistLLM: A Unified Framework for LLM-Based Multimodal Recommendation with User History Encoding and Compression

Efficient Contrastive Decoding with Probabilistic Hallucination Detection - Mitigating Hallucinations in Large Vision Language Models -

LVLM_CSP: Accelerating Large Vision Language Models via Clustering, Scattering, and Pruning for Reasoning Segmentation

Financial Analysis: Intelligent Financial Data Analysis System Based on LLM-RAG

EfficientLLaVA:Generalizable Auto-Pruning for Large Vision-language Models

Efficient allocation of image recognition and LLM tasks on multi-GPU system

Efficient Transfer Learning for Video-language Foundation Models

Nullu: Mitigating Object Hallucinations in Large Vision-Language Models via HalluSpace Projection

Towards An Efficient LLM Training Paradigm for CTR Prediction

Taming Sensitive Weights : Noise Perturbation Fine-tuning for Robust LLM Quantization

Distributed Speculative Inference (DSI): Speculation Parallelism for Provably Faster Lossless Language Model Inference

Task-Specific Knowledge Distillation from the Vision Foundation Model for Enhanced Medical Image Segmentation

PathVQ: Reforming Computational Pathology Foundation Model for Whole Slide Image Analysis via Vector Quantization

Exploring and Lifting the Robustness of LLM-powered Automated Program Repair with Metamorphic Testing

Scholar Name Disambiguation with Search-enhanced LLM Across Language

TRACE: A Self-Improving Framework for Robot Behavior Forecasting with Vision-Language Models

Teaching Dense Retrieval Models to Specialize with Listwise Distillation and LLM Data Augmentation

Minions: Cost-efficient Collaboration Between On-device and Cloud Language Models

The Lottery LLM Hypothesis, Rethinking What Abilities Should LLM Compression Preserve?

Muon is Scalable for LLM Training

Exploring Causes and Mitigation of Hallucinations in Large Vision Language Models