语言大模型 / LLM - arXivDaily 专题

2509.07436 2025-09-10 eess.SP 82%

SA-OOSC: A Multimodal LLM-Distilled Semantic Communication Framework for Enhanced Coding Efficiency with Scenario Understanding

Feifan Zhang, Yuyang Du, Yifan Xiang, Xiaoyan Liu, Soung Chang Liew

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

2509.06768 2025-09-09 cs.RO 82%

Embodied Hazard Mitigation using Vision-Language Models for Autonomous Mobile Robots

Oluwadamilola Sotomi, Devika Kodi, Kiruthiga Chandra Shekar, Aliasghar Arab

机构 * Department of Mechanical and Aerospace Engineering, Tandon School of Engineering, New York University（机械与航空航天工程系，坦顿工程学院，纽约大学）； GenAuto.ai by General Autonomy Inc.（General Autonomy Inc. 的 GenAuto.ai）

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

2509.06321 2025-09-09 cs.CV 82%

Text4Seg++: Advancing Image Segmentation via Generative Language Modeling

Mengcheng Lan, Chaofeng Chen, Jiaxing Xu, Zongrui Li, Yiping Ke, Xudong Jiang, Yingchen Yu, Yunqing Zhao, Song Bai

机构 * College of Computing and Data Science, Nanyang Technological University（computing and Data Science学院，南洋理工大学）； School of Electrical and Electronic Engineering, Nanyang Technological University（Electrical and Electronic Engineering学院，南洋理工大学）； School of Artificial Intelligence, Wuhan University（Artificial Intelligence学院，武汉大学）； ByteDance（字节跳动）

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

Comments Extended version of our conference paper arXiv:2410.09855

2509.05962 2025-09-09 cs.HC 82%

The Reel Deal: Designing and Evaluating LLM-Generated Short-Form Educational Videos

Lazaros Stavrinou, Argyris Constantinides, Marios Belk, Vasos Vassiliou, Fotis Liarokapis, Marios Constantinides

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

Comments 9 pages, 3 figures, 1 table

2509.05925 2025-09-09 cs.CV cs.IT math.IT 82%

Compression Beyond Pixels: Semantic Compression with Multimodal Foundation Models

Ruiqi Shen, Haotian Wu, Wenjing Zhang, Jiangjing Hu, Deniz Gunduz

机构 * Department of Electrical and Electronic Engineering, Imperial College London（帝国理工学院电子与电气工程系）

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

Comments Published as a conference paper at IEEE 35th Workshop on Machine Learning for Signal Processing (MLSP)

2509.05355 2025-09-09 cs.RO cs.MA 82%

Human-LLM Synergy in Context-Aware Adaptive Architecture for Scalable Drone Swarm Operation

Ahmed R. Sadik, Muhammad Ashfaq, Niko Mäkitalo, Tommi Mikkonen

机构 * Honda Research Institute Europe, Germany（本田欧洲研究机构）

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

2508.18306 2025-08-27 cs.LG cs.AI cs.CL 82%

SALMAN: Stability Analysis of Language Models Through the Maps Between Graph-based Manifolds

Wuxinlin Cheng, Yupeng Cao, Jinwen Wu, Koduvayur Subbalakshmi, Tian Han, Zhuo Feng

机构 * Stevens Institute of Technology（史蒂文斯理工学院）

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

2508.11864 2025-08-21 cs.CV 82%

Impact of Clinical Image Quality on Efficient Foundation Model Finetuning

Yucheng Tang, Pawel Rajwa, Alexander Ng, Yipei Wang, Wen Yan, Natasha Thorley, Aqua Asif, Clare Allen, Louise Dickinson, Francesco Giganti, Shonit Punwani, Daniel C. Alexander, Veeru Kasivisvanathan, Yipeng Hu

机构 * UCL Hawkes Insitute, University College London Dept. of Medical Physics \& Biomedical Engineering, University College London Division of Surgery \& Interventional Science, University College London Centre of Medical Imaging, University College London Department of Radiology, UCLH NHS Foundation Trust Department of Urology, UCLH NHS Foundation Trust Department of Computer Science, University College London

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

Comments This paper was accepted to the 1st MICCAI Workshop on Efficient Medical AI (EMA4MICCAI2025) and selected for oral presentation

2504.05410 2025-08-19 cs.CL cs.AI cs.LG 82%

Fast Controlled Generation from Language Models with Adaptive Weighted Rejection Sampling

Benjamin Lipkin, Benjamin LeBrun, Jacob Hoover Vigly, João Loula, David R. MacIver, Li Du, Jason Eisner, Ryan Cotterell, Vikash Mansinghka, Timothy J. O'Donnell, Alexander K. Lew, Tim Vieira

机构 * MIT（麻省理工学院）； ETH Zürich（苏黎世联邦理工学院）； McGill（麦吉尔大学）； Canada CIFAR AI Chair（加拿大 CIFAR 人工智能主席）； Mila（蒙特利尔人工智能研究院）； Johns Hopkins（约翰霍普金斯大学）； Yale（耶鲁大学）； CHI FRO

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

Comments COLM 2025

2502.01906 2025-08-19 cs.CV 82%

D-Attn: Decomposed Attention for Large Vision-and-Language Models

Chia-Wen Kuo, Sijie Zhu, Fan Chen, Xiaohui Shen, Longyin Wen

机构 * ByteDance Intelligent Creation（字节跳动智能创作）

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

2508.00260 2025-08-04 cs.CV cs.MM 82%

Instruction-Grounded Visual Projectors for Continual Learning of Generative Vision-Language Models

Hyundong Jin, Hyung Jin Chang, Eunwoo Kim

机构 * School of Computer Science and Engineering, Chung-Ang University（Chung-Ang 大学计算机科学与工程学院）； School of Computer Science, University of Birmingham（布拉德福德大学计算机科学学院）

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

Comments Accepted to ICCV 2025

2507.22352 2025-07-31 cs.HC 82%

Mitigating Response Delays in Free-Form Conversations with LLM-powered Intelligent Virtual Agents

Mykola Maslych, Mohammadreza Katebi, Christopher Lee, Yahya Hmaiti, Amirpouya Ghasemaghaei, Christian Pumarada, Janneese Palmer, Esteban Segarra Martinez, Marco Emporio, Warren Snipes, Ryan P. McMahan, Joseph J. LaViola

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

Comments 15 pages, 8 figures. Published at the 7th ACM Conference on Conversational User Interfaces (CUI '25), July 8-10, 2025, Waterloo, Canada. Open-source code available at https://github.com/ISUE/iva-cui

Journal ref Proceedings of the 7th ACM Conference on Conversational User Interfaces (CUI '25), 2025, Article 49, 1-15

2507.20511 2025-07-30 cs.CV 82%

Beyond Class Tokens: LLM-guided Dominant Property Mining for Few-shot Classification

Wei Zhuo, Runjie Luo, Wufeng Xue, Linlin Shen

机构 * School of Artificial Intelligence and the National Engineering Laboratory of Big Data System Computing Technology, Shenzhen University（人工智能学院和大数据系统计算技术国家工程实验室，深圳大学）； School of Biomedical Engineering, Shenzhen University Medical School（生物医学工程学院，深圳大学医学院）

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

Comments 11 pages, 7 figures

2507.20842 2025-07-29 cs.CV 82%

METEOR: Multi-Encoder Collaborative Token Pruning for Efficient Vision Language Models

Yuchen Liu, Yaoming Wang, Bowen Shi, Xiaopeng Zhang, Wenrui Dai, Chenglin Li, Hongkai Xiong, Qi Tian

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

Comments Accepted by ICCV 2025

2507.19845 2025-07-29 cs.DC 82%

MegatronApp: Efficient and Comprehensive Management on Distributed LLM Training

Bohan Zhao, Guang Yang, Shuo Chen, Ruitao Liu, Tingrui Zhang, Yongchao He, Wei Xu

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

2412.01661 2025-07-23 cs.DB cs.AI cs.CL cs.LG 82%

R-Bot: An LLM-based Query Rewrite System

Zhaoyan Sun, Xuanhe Zhou, Guoliang Li, Xiang Yu, Jianhua Feng, Yong Zhang

机构 * Tsinghua University（清华大学）； Shanghai Jiao Tong University（上海交通大学）； Huawei Company（华为公司）

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

2507.12621 2025-07-21 cs.HC cs.GR cs.MA 82%

NLI4VolVis: Natural Language Interaction for Volume Visualization via LLM Multi-Agents and Editable 3D Gaussian Splatting

Kuangshi Ai, Kaiyuan Tang, Chaoli Wang

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

Comments IEEE VIS 2025. Project Page: https://nli4volvis.github.io/

Journal ref IEEE Transactions on Visualization and Computer Graphics (TVCG), vol. 32, no. 1, 2026

2411.13789 2025-07-17 cs.IR 82%

LEADRE: Multi-Faceted Knowledge Enhanced LLM Empowered Display Advertisement Recommender System

Fengxin Li, Yi Li, Yue Liu, Chao Zhou, Yuan Wang, Xiaoxiang Deng, Wei Xue, Dapeng Liu, Lei Xiao, Haijie Gu, Jie Jiang, Hongyan Liu, Biao Qin, Jun He

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

Comments Accepted by VLDB 2025 Industrial Track

2411.02820 2025-07-16 cs.MA cs.AI cs.CL cs.LG 82%

DroidSpeak: KV Cache Sharing for Cross-LLM Communication and Multi-LLM Serving

Yuhan Liu, Yuyang Huang, Jiayi Yao, Shaoting Feng, Zhuohan Gu, Kuntai Du, Hanchen Li, Yihua Cheng, Junchen Jiang, Shan Lu, Madan Musuvathi, Esha Choukse

机构 * University of Chicago（芝加哥大学）； Microsoft（微软公司）

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

2507.10392 2025-07-15 cs.DC 82%

Zorse: Optimizing LLM Training Efficiency on Heterogeneous GPU Clusters

Runsheng Benson Guo, Utkarsh Anand, Khuzaima Daudjee, Rathijit Sen

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

2507.08410 2025-07-14 cs.CV 82%

Multi-modal Mutual-Guidance Conditional Prompt Learning for Vision-Language Models

Shijun Yang, Xiang Zhang, Wanqing Zhao, Hangzai Luo, Sheng Zhong, Jinye Peng, Jianping Fan

机构 * School of Information and Technology, Northwest University（信息与技术学院，西北大学）

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

Comments 21 pages, 8 figures

2505.12890 2025-07-08 cs.CV 82%

Specialized Foundation Models for Intelligent Operating Rooms

Ege Özsoy, Chantal Pellegrini, David Bani-Harouni, Kun Yuan, Matthias Keicher, Nassir Navab

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

2503.21817 2025-07-04 cs.CV 82%

Skip-Vision: Efficient and Scalable Acceleration of Vision-Language Models via Adaptive Token Skipping

Weili Zeng, Ziyuan Huang, Kaixiang Ji, Yichao Yan

机构 * MoE Key Lab of Artificial Intelligence, AI Institute Shanghai Jiao Tong University（人工智能大模型关键实验室，上海交通大学AI研究院）

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

Comments Accepted by ICCV2025

2506.22033 2025-06-30 cs.DC 82%

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference

Yongchao He, Bohan Zhao, Zheng Cao

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

2506.21593 2025-06-30 cs.IR cs.DB 82%

PentaRAG: Large-Scale Intelligent Knowledge Retrieval for Enterprise LLM Applications

Abu Hanif Muhammad Syarubany, Chang Dong Yoo

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

Comments Annual Conference of The Institute of Electronics and Information Engineers

2506.19303 2025-06-25 cs.RO 82%

Robotic Perception with a Large Tactile-Vision-Language Model for Physical Property Inference

Zexiang Guo, Hengxiang Chen, Xinheng Mai, Qiusang Qiu, Gan Ma, Zhanat Kappassov, Qiang Li, Nutan Chen

机构 * College of Big Data and Internet, Shenzhen Technology University, China（大数据与互联网学院，深圳科技大学，中国）； Sino-German College of Intelligent Manufacturing, Shenzhen Technology University, China（中德智能制造学院，深圳科技大学，中国）； Robotics Department, Institute of Smart Systems and Artificial Intelligence (ISSAI), Nazarbayev University, Kazakhstan（机器人系，智能系统与人工智能研究所（ISSAI），纳扎尔巴耶夫大学，哈萨克斯坦）； Foundation Robotics Labs, Germany（基础机器人实验室，德国）

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

Comments This paper has been accepted by the 2025 International Conference on Climbing and Walking Robots (CLAWAR). These authors contributed equally to this work: Zexiang Guo, Hengxiang Chen, Xinheng Mai

2505.20518 2025-06-18 physics.geo-ph 82%

SeisCoDE: 3D Seismic Interpretation Foundation Model with Contrastive Self-Distillation Learning

Goodluck Archibong, Ardiansyah Koeshidayatullah, Umair Waheed, Weichang Li, Dicky Harishidayat, Motaz Alfarraj

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

Comments After an initial submission, we recognized the need to conduct additional experiments to strengthen the validity. Furthermore, we aim to incorporate comprehensive feedback from all co-authors to ensure the work reflects a unified and thoroughly vetted perspective. These steps are essential to uphold the quality and integrity of the research before resubmission or formal publication

2506.07533 2025-06-10 cs.CV 82%

MoQAE: Mixed-Precision Quantization for Long-Context LLM Inference via Mixture of Quantization-Aware Experts

Wei Tao, Haocheng Lu, Xiaoyang Qu, Bin Zhang, Kai Lu, Jiguang Wan, Jianzong Wang

机构 * Huazhong University of Science and Technology（华中科技大学）； Ping An Technology (Shenzhen) Co., Ltd（平安科技（深圳）有限公司）

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

Comments Accepted by the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

2506.07154 2025-06-10 cs.CL cs.AI cs.LG 82%

Syntactic Control of Language Models by Posterior Inference

Vicky Xefteri, Tim Vieira, Ryan Cotterell, Afra Amini

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

2506.05754 2025-06-09 cs.AI cs.CL cs.LG 82%

Constrained Sampling for Language Models Should Be Easy: An MCMC Perspective

Emmanuel Anaya Gonzalez, Sairam Vaidya, Kanghee Park, Ruyi Ji, Taylor Berg-Kirkpatrick, Loris D'Antoni

机构 * UCSD（加州大学圣地亚哥分校）； Peking University（北京大学）

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

1. 效率与部署 22497 篇

SA-OOSC: A Multimodal LLM-Distilled Semantic Communication Framework for Enhanced Coding Efficiency with Scenario Understanding

Embodied Hazard Mitigation using Vision-Language Models for Autonomous Mobile Robots

Text4Seg++: Advancing Image Segmentation via Generative Language Modeling

The Reel Deal: Designing and Evaluating LLM-Generated Short-Form Educational Videos

Compression Beyond Pixels: Semantic Compression with Multimodal Foundation Models

Human-LLM Synergy in Context-Aware Adaptive Architecture for Scalable Drone Swarm Operation

SALMAN: Stability Analysis of Language Models Through the Maps Between Graph-based Manifolds

Impact of Clinical Image Quality on Efficient Foundation Model Finetuning

Fast Controlled Generation from Language Models with Adaptive Weighted Rejection Sampling

D-Attn: Decomposed Attention for Large Vision-and-Language Models

Instruction-Grounded Visual Projectors for Continual Learning of Generative Vision-Language Models

Mitigating Response Delays in Free-Form Conversations with LLM-powered Intelligent Virtual Agents

Beyond Class Tokens: LLM-guided Dominant Property Mining for Few-shot Classification

METEOR: Multi-Encoder Collaborative Token Pruning for Efficient Vision Language Models

MegatronApp: Efficient and Comprehensive Management on Distributed LLM Training

R-Bot: An LLM-based Query Rewrite System

NLI4VolVis: Natural Language Interaction for Volume Visualization via LLM Multi-Agents and Editable 3D Gaussian Splatting

LEADRE: Multi-Faceted Knowledge Enhanced LLM Empowered Display Advertisement Recommender System

DroidSpeak: KV Cache Sharing for Cross-LLM Communication and Multi-LLM Serving

Zorse: Optimizing LLM Training Efficiency on Heterogeneous GPU Clusters

Multi-modal Mutual-Guidance Conditional Prompt Learning for Vision-Language Models

Specialized Foundation Models for Intelligent Operating Rooms

Skip-Vision: Efficient and Scalable Acceleration of Vision-Language Models via Adaptive Token Skipping

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference

PentaRAG: Large-Scale Intelligent Knowledge Retrieval for Enterprise LLM Applications

Robotic Perception with a Large Tactile-Vision-Language Model for Physical Property Inference

SeisCoDE: 3D Seismic Interpretation Foundation Model with Contrastive Self-Distillation Learning

MoQAE: Mixed-Precision Quantization for Long-Context LLM Inference via Mixture of Quantization-Aware Experts

Syntactic Control of Language Models by Posterior Inference

Constrained Sampling for Language Models Should Be Easy: An MCMC Perspective