语言大模型 / LLM - arXivDaily 专题

2601.20885 2026-01-30 cs.CR 88%

What Hard Tokens Reveal: Exploiting Low-confidence Tokens for Membership Inference Attacks against Large Language Models

硬token揭示：利用低置信度token对大型语言模型进行成员推断攻击

Md Tasnim Jawad, Mingyan Xiao, Yanzhao Wu

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

AI总结本文提出HT-MIA方法，通过分析低置信度token的概率改进，提升对大型语言模型的成员推断攻击效果，并探讨差分隐私训练作为防御机制。

2601.05278 2026-01-15 hep-ex 88%

Large Language Model Integration for Knowledge Retrieval and Interaction for the DUNE Experiment

大型语言模型整合用于DUNE实验的知识检索与交互

A. Rafique, A. Singh, R. Srinivas

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

AI总结 DUNE-GPT利用大型语言模型和检索增强生成技术，实现对DUNE实验内部文档的自然语言查询，提升协作效率与数据隐私保护。

2510.20322 2025-12-19 cs.CV 88%

HyperET: Efficient Training in Hyperbolic Space for Multi-modal Large Language Models

HyperET: 在超几何空间中为多模态大语言模型实现高效训练

Zelin Peng, Zhengqin Xu, Qingyang Liu, Xiaokang Yang, Wei Shen

机构 * MoE Key Lab of Artificial Intelligence, AI Institute, School of Computer Science, SJTU（摩埃人工智能重点实验室、人工智能学院、计算机科学学院、上海交通大学）

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

AI总结 HyperET通过在双曲空间中动态调整半径，实现多模态大语言模型的高效训练，提升跨模态对齐性能。

Comments Accepted by NeurIPS2025 (Oral)

2512.01949 2025-12-02 cs.CV 88%

Script: Graph-Structured and Query-Conditioned Semantic Token Pruning for Multimodal Large Language Models

脚本：图结构和查询条件的语义令牌修剪用于多模态大语言模型

Zhongyu Yang, Dannong Xu, Wei Pang, Yingfang Yuan

机构 * BCML, Heriot-Watt University（赫瑞瓦德大学BCML中心）

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

AI总结 Script通过图结构和查询条件的语义令牌修剪，提升多模态大语言模型的效率和准确性，实现显著的性能提升。

Comments Published in Transactions on Machine Learning Research, Project in https://01yzzyu.github.io/script.github.io/

2511.21106 2025-11-27 cs.CV 88%

EM-KD: Distilling Efficient Multimodal Large Language Model with Unbalanced Vision Tokens

EM-KD: 通过不平衡视觉标记的知识蒸馏提升高效多模态大语言模型

Ze Feng, Sen Yang, Boqiang Duan, Wankou Yang, Jingdong Wang

机构 * Baidu VIS（百度视觉）

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

AI总结 EM-KD通过改进的知识蒸馏方法，有效提升高效多模态大语言模型的视觉理解和效率。

Comments accepted by AAAI 2026

2511.18920 2025-11-25 cs.CV 88%

EventSTU: Event-Guided Efficient Spatio-Temporal Understanding for Video Large Language Models

EventSTU: 基于事件的高效空间-时间理解用于视频大语言模型

Wenhao Xu, Xin Dong, Yue Li, Haoyuan Shi, Zhiwei Xiong

机构 * University of Science and Technology of China（中国科学技术大学）

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

AI总结 EventSTU通过事件引导的方法，高效处理视频大语言模型的空间-时间理解，实现显著的计算效率提升和性能优化。

Comments 8 pages, 7 figures

2511.09920 2025-11-18 cs.CY 88%

Uncovering Strategic Egoism Behaviors in Large Language Models

Yaoyuan Zhang, Aishan Liu, Zonghao Ying, Xianglong Liu, Jiangfan Liu, Yisong Xiao, Qihang Zhang

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

Comments PersonaNLP@NeurIPS 2025

2505.12658 2025-11-11 cs.DC 88%

HydraInfer: Hybrid Disaggregated Scheduling for Multimodal Large Language Model Serving

Xianzhe Dong, Tongxuan Liu, Yuting Zeng, Liangyu Liu, Yang Liu, Siyu Wu, Yu Wu, Hailong Yang, Ke Zhang, Jing Li

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

2504.14872 2025-10-30 cs.SE 88%

Efficient Function Orchestration for Large Language Models

Xiaoxia Liu, Peng Di, Cong Li, Jun Sun, Jingyi Wang

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

Comments Accepted for publication in IEEE Transactions on Software Engineering (TSE), 2025

2506.10337 2025-10-21 cs.CV 88%

GeoCAD: Local Geometry-Controllable CAD Generation with Large Language Models

Zhanwei Zhang, Kaiyuan Liu, Junjie Liu, Wenxiao Wang, Binbin Lin, Liang Xie, Chen Shen, Deng Cai

机构 * State Key Lab of CAD&CG（CAD与计算机图形学国家重点实验室）； Alibaba Cloud Computing（阿里云计算）； Zhejiang University of Technology（浙江工业大学）； School of Software Technology, Zhejiang University（浙江大学软件技术学院）

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

Comments Accepted by NeurIPS 2025

2405.01668 2025-10-14 cs.CR cs.SE 88%

LineBreaker: Finding Token-Inconsistency Bugs with Large Language Models

Hongbo Chen, Yifan Zhang, Xing Han, Tianhao Mao, Huanyao Rong, Yuheng Zhang, XiaoFeng Wang, Luyi Xing, Xun Chen, Hang Zhang

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

Comments ASE 2025 Accepted, with Appendix added

2510.04605 2025-10-07 cs.SE 88%

Exploring the Power of Diffusion Large Language Models for Software Engineering: An Empirical Investigation

Jingyao Zhang, Tianlin Li, Xiaoyu Zhang, Qiang Hu, Bin Shi

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

2510.03232 2025-10-06 cs.CV 88%

LEAML: Label-Efficient Adaptation to Out-of-Distribution Visual Tasks for Multimodal Large Language Models

Ci-Siang Lin, Min-Hung Chen, Yu-Yang Sheng, Yu-Chiang Frank Wang

机构 * Graduate Institute of Communication Engineering, National Taiwan University, Taiwan（台湾国立台湾大学通信工程研究所）； NVIDIA

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

2505.20873 2025-10-01 cs.CV 88%

Fork-Merge Decoding: Enhancing Multimodal Understanding in Audio-Visual Large Language Models

Chaeyoung Jung, Youngjoon Jang, Jongmin Choi, Joon Son Chung

机构 * Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）

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

2509.22512 2025-09-29 cs.AR 88%

AxLLM: accelerator architecture for large language models with computation reuse capability

Soroush Ahadi, Mehdi Modarressi, Masoud Daneshtalab

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

Comments 7 pages, 9 figures

2509.13265 2025-09-17 cs.CY 88%

Beyond Private or Public: Large Language Models as Quasi-Public Goods in the AI Economy

Yukun Zhang, TianYang Zhang

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

2501.18177 2025-09-03 cs.IR cs.CY cs.MA 88%

Investigating Tax Evasion Emergence Using Dual Large Language Model and Deep Reinforcement Learning Powered Agent-based Simulation

Teddy Lazebnik, Labib Shami

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

2508.04192 2025-08-07 cs.CV 88%

From Learning to Unlearning: Biomedical Security Protection in Multimodal Large Language Models

Dunyuan Xu, Xikai Yang, Yaoqian Li, Jinpeng Li, Pheng-Ann Heng

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

2507.16781 2025-07-23 cs.DC 88%

Cooling Matters: Benchmarking Large Language Models and Vision-Language Models on Liquid-Cooled Versus Air-Cooled H100 GPU Systems

Imran Latif, Muhammad Ali Shafique, Hayat Ullah, Alex C. Newkirk, Xi Yu, Arslan Munir

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

Comments 11 pages

2507.13035 2025-07-18 cs.SE 88%

Investigating the Performance of Small Language Models in Detecting Test Smells in Manual Test Cases

Keila Lucas, Rohit Gheyi, Márcio Ribeiro, Fabio Palomba, Luana Martins, Elvys Soares

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

Comments 7 pages, Accepted at Insightful Ideas and Emerging Results (IIER) Track of the Brazilian Symposium on Software Engineering (SBES 2025)

2410.00603 2025-07-17 cs.SE 88%

An Empirical Study of Large Language Models for Type and Call Graph Analysis in Python and JavaScript

Ashwin Prasad Shivarpatna Venkatesh, Rose Sunil, Samkutty Sabu, Amir M. Mir, Sofia Reis, Eric Bodden

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

Comments Accepted to be published in the EMSE journal

2507.09334 2025-07-15 cs.CV 88%

Fast3D: Accelerating 3D Multi-modal Large Language Models for Efficient 3D Scene Understanding

Wencan Huang, Daizong Liu, Wei Hu

机构 * Wangxuan Institute of Computer Technology, Peking University（北京大学王轩计算机技术研究所）

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

Comments Accepted by ACM MM 2025

2507.02279 2025-07-04 cs.CV 88%

LaCo: Efficient Layer-wise Compression of Visual Tokens for Multimodal Large Language Models

Juntao Liu, Liqiang Niu, Wenchao Chen, Jie Zhou, Fandong Meng

机构 * Pattern Recognition Center, WeChat AI, Tencent Inc（模式识别中心、微信AI、腾讯公司）

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

2506.23862 2025-07-01 stat.ME 88%

Large Language Models for Statistical Inference: Context Augmentation with Applications to the Two-Sample Problem and Regression

Marc Ratkovic

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

2501.16297 2025-07-01 cs.CV 88%

FALCON: Resolving Visual Redundancy and Fragmentation in High-resolution Multimodal Large Language Models via Visual Registers

Renshan Zhang, Rui Shao, Gongwei Chen, Miao Zhang, Kaiwen Zhou, Weili Guan, Liqiang Nie

机构 * Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））

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

Comments Accepted to the IEEE/CVF International Conference on Computer Vision (ICCV) 2025

2506.16968 2025-06-23 cs.CR cs.CY 88%

MM-AttacKG: A Multimodal Approach to Attack Graph Construction with Large Language Models

Yongheng Zhang, Xinyun Zhao, Yunshan Ma, Haokai Ma, Yingxiao Guan, Guozheng Yang, Yuliang Lu, Xiang Wang

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

2411.06752 2025-06-18 cs.RO 88%

Semantic Enhancement for Object SLAM with Heterogeneous Multimodal Large Language Model Agents

Jungseok Hong, Ran Choi, John J. Leonard

机构 * Computer Science and Artificial Intelligence Laboratory (CSAIL) at the Massachusetts Institute of Technology (MIT)（麻省理工学院计算机科学与人工智能实验室）

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

2506.12710 2025-06-17 cs.RO 88%

Multimodal Large Language Models-Enabled UAV Swarm: Towards Efficient and Intelligent Autonomous Aerial Systems

Yuqi Ping, Tianhao Liang, Huahao Ding, Guangyu Lei, Junwei Wu, Xuan Zou, Kuan Shi, Rui Shao, Chiya Zhang, Weizheng Zhang, Weijie Yuan, Tingting Zhang

机构 * College of Informatics, Harbin Institute of Technology（信息学院，哈尔滨工业大学）； Key Laboratory of Forest and Grassland Fire Risk Prevention, Ministry of Emergency Management, China Fire and Rescue Institute（森林和草原火灾风险预防重点实验室，应急管理部，中国消防救援学院）； Southern University of Science and Technology（南方科技大学）

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

Comments 8 pages, 5 figures,submitted to IEEE wcm

2410.07524 2025-06-17 cs.CL cs.AI cs.LG 88%

Upcycling Large Language Models into Mixture of Experts

Ethan He, Abhinav Khattar, Ryan Prenger, Vijay Korthikanti, Zijie Yan, Tong Liu, Shiqing Fan, Ashwath Aithal, Mohammad Shoeybi, Bryan Catanzaro

机构 * NVIDIA

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

2504.14966 2025-06-13 cs.DC 88%

SLO-Aware Scheduling for Large Language Model Inferences

Jinqi Huang, Yi Xiong, Xuebing Yu, Wenjie Huang, Entong Li, Li Zeng, Xin Chen

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

1. 效率与部署 22280 篇

What Hard Tokens Reveal: Exploiting Low-confidence Tokens for Membership Inference Attacks against Large Language Models

Large Language Model Integration for Knowledge Retrieval and Interaction for the DUNE Experiment

HyperET: Efficient Training in Hyperbolic Space for Multi-modal Large Language Models

Script: Graph-Structured and Query-Conditioned Semantic Token Pruning for Multimodal Large Language Models

EM-KD: Distilling Efficient Multimodal Large Language Model with Unbalanced Vision Tokens

EventSTU: Event-Guided Efficient Spatio-Temporal Understanding for Video Large Language Models

Uncovering Strategic Egoism Behaviors in Large Language Models

HydraInfer: Hybrid Disaggregated Scheduling for Multimodal Large Language Model Serving

Efficient Function Orchestration for Large Language Models

GeoCAD: Local Geometry-Controllable CAD Generation with Large Language Models

LineBreaker: Finding Token-Inconsistency Bugs with Large Language Models

Exploring the Power of Diffusion Large Language Models for Software Engineering: An Empirical Investigation

LEAML: Label-Efficient Adaptation to Out-of-Distribution Visual Tasks for Multimodal Large Language Models

Fork-Merge Decoding: Enhancing Multimodal Understanding in Audio-Visual Large Language Models

AxLLM: accelerator architecture for large language models with computation reuse capability

Beyond Private or Public: Large Language Models as Quasi-Public Goods in the AI Economy

Investigating Tax Evasion Emergence Using Dual Large Language Model and Deep Reinforcement Learning Powered Agent-based Simulation

From Learning to Unlearning: Biomedical Security Protection in Multimodal Large Language Models

Cooling Matters: Benchmarking Large Language Models and Vision-Language Models on Liquid-Cooled Versus Air-Cooled H100 GPU Systems

Investigating the Performance of Small Language Models in Detecting Test Smells in Manual Test Cases

An Empirical Study of Large Language Models for Type and Call Graph Analysis in Python and JavaScript

Fast3D: Accelerating 3D Multi-modal Large Language Models for Efficient 3D Scene Understanding

LaCo: Efficient Layer-wise Compression of Visual Tokens for Multimodal Large Language Models

Large Language Models for Statistical Inference: Context Augmentation with Applications to the Two-Sample Problem and Regression

FALCON: Resolving Visual Redundancy and Fragmentation in High-resolution Multimodal Large Language Models via Visual Registers

MM-AttacKG: A Multimodal Approach to Attack Graph Construction with Large Language Models

Semantic Enhancement for Object SLAM with Heterogeneous Multimodal Large Language Model Agents

Multimodal Large Language Models-Enabled UAV Swarm: Towards Efficient and Intelligent Autonomous Aerial Systems

Upcycling Large Language Models into Mixture of Experts

SLO-Aware Scheduling for Large Language Model Inferences