语言大模型 / LLM

A Cost-Benefit Analysis of On-Premise Large Language Model Deployment: Breaking Even with Commercial LLM Services

Guanzhong Pan, Vishal Chodnekar, Abinas Roy, Haibo Wang

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

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

ConfGuard: A Simple and Effective Backdoor Detection for Large Language Models

Zihan Wang, Rui Zhang, Hongwei Li, Wenshu Fan, Wenbo Jiang, Qingchuan Zhao, Guowen Xu

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

Comments This is an extended version of the copyrighted publication at AAAI

Quality Over Quantity? LLM-Based Curation for a Data-Efficient Audio-Video Foundation Model

Ali Vosoughi, Dimitra Emmanouilidou, Hannes Gamper

机构 * University of Rochester（罗切斯特大学） ； Microsoft Research（微软研究院） 纠错

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

Comments Accepted at EUSIPCO 2025 - 5 pages, 5 figures, 2 tables

Synera: Synergistic LLM Serving across Device and Cloud at Scale

Genglin Wang, Liekang Zeng, Bufang Yang, Kaiwei Liu, Guoliang Xing, Chumin Sun, Li Zhou, Jie Sun, Zhenyu Yan

机构 * The Chinese University of Hong Kong Hong Kong SAR China（香港中文大学） ； Theory Lab, Central Research Institute, 2012 Labs, Huawei Technologies Co. Ltd.（理论实验室、中央研究院、2012实验室、华为技术有限公司） 纠错

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

Prudential Reliability of Large Language Models in Reinsurance: Governance, Assurance, and Capital Efficiency

Stella C. Dong

机构 * Reinsurance Analytics（再保险分析） 纠错

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

Comments 48 pages, 9 figures, 5 tables. Submitted to the Journal of Risk and Insurance (JRI), November 2025

Comparative Analysis of Large Language Models for the Machine-Assisted Resolution of User Intentions

Justus Flerlage, Alexander Acker, Odej Kao

机构 * logsight.ai GmbH（logsight.ai公司） 纠错

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

Comments Accepted at First International Workshop on Human-AI Collaborative Systems (HAIC), published in CEUR-WS.org Vol-4072 (2025). URN: urn:nbn:de:0074-4072-x

From Semantics, Scene to Instance-awareness: Distilling Foundation Model for Grounded Open-vocabulary Situation Recognition

Chen Cai, Tianyi Liu, Jianjun Gao, Wenyang Liu, Kejun Wu, Ruoyu Wang, Yi Wang, Soo Chin Liew

机构 * National University of Singapore（新加坡国立大学） ； Nanyang Technological University（南洋理工大学） ； Huazhong University of Science and Technology（华中科技大学） ； The Hong Kong Polytechnic University（香港理工大学） 纠错

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

ProST: Progressive Sub-task Training for Pareto-Optimal Multi-agent Systems Using Small Language Models

Biddut Sarker Bijoy, Mohammad Saqib Hasan, Pegah Alipoormolabashi, Avirup Sil, Aruna Balasubramanian, Niranjan Balasubramanian

机构 * Stony Brook University（石溪大学） ； Oracle Applied Science（Oracle应用科学） 纠错

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

LLM Optimization Unlocks Real-Time Pairwise Reranking

Jingyu Wu, Aditya Shrivastava, Jing Zhu, Alfy Samuel, Anoop Kumar, Daben Liu

机构 * AI Foundations, Capital One（人工智能基础，Capital One） 纠错

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

Network and Systems Performance Characterization of MCP-Enabled LLM Agents

Zihao Ding, Mufeng Zhu, Yao Liu

机构 * Rutgers University（罗格斯大学） 纠错

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

FedRW: Efficient Privacy-Preserving Data Reweighting for Enhancing Federated Learning of Language Models

Pukang Ye, Junwei Luo, Xiaolei Dong, Yunbo Yang

机构 * East China Normal University（华东师范大学） ； Wuhan University（武汉大学） ； Zhejiang University（浙江大学） ； ZStack ； Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security Q（杭州高新区（滨江）区块链与数据安全研究院） 纠错

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

Comments Accepted at NeurIPS 2025. Code is available at https://github.com/Hecateto/FedRW

DynaKV: Enabling Accurate and Efficient Long-Sequence LLM Decoding on Smartphones

Tuowei Wang, Minxing Huang, Fengzu Li, Ligeng Chen, Jinrui Zhang, Ju Ren

机构 * Tsinghua University（清华大学） ； Honor Device Co., Ltd.（荣耀设备有限公司） 纠错

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

LLM Output Drift: Cross-Provider Validation & Mitigation for Financial Workflows

Raffi Khatchadourian, Rolando Franco

机构 * IBM -- Financial Services Market（IBM金融服务市场） 纠错

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 11 pages, 5 figures. To appear in AI4F @ ACM ICAIF '25, November 15-18, 2025, Singapore

From Attention to Disaggregation: Tracing the Evolution of LLM Inference

Madabattula Rajesh Kumar, Srinivasa Rao Aravilli, Mustafa Saify, Shashank Srivastava

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

Tool-Aided Evolutionary LLM for Generative Policy Toward Efficient Resource Management in Wireless Federated Learning

Chongyang Tan, Ruoqi Wen, Rongpeng Li, Zhifeng Zhao, Ekram Hossain, Honggang Zhang

机构 * College of Information Science and Electronic Engineering, Zhejiang University（浙江大学信息科学与电子工程学院） ； Zhejiang Lab（浙江实验室） ； University of Manitoba（曼尼托巴大学） ； Macau University of Science and Technology（澳门科学理工学院） 纠错

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

Alignment-Constrained Dynamic Pruning for LLMs: Identifying and Preserving Alignment-Critical Circuits

Dev Patel, Gabrielle Gervacio, Diekola Raimi, Kevin Zhu, Ryan Lagasse, Gabriel Grand, Ashwinee Panda, Maheep Chaudhary

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

Intelligent Orchestration of Distributed Large Foundation Model Inference at the Edge

Fernando Koch, Aladin Djuhera, Alecio Binotto

机构 * Florida Atlantic University, USA（佛罗里达大学） ； Technical University Munich, Germany（慕尼黑技术大学） ； Carl Zeiss AG, Germany（蔡司股份公司） 纠错

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

Comments 26 pages, 3 figures, 4 tables, 52 references

Journal ref Computer Networks and Communications, 2025

HarmoQ: Harmonized Post-Training Quantization for High-Fidelity Image

Hongjun Wang, Jiyuan Chen, Xuan Song, Yinqiang Zheng

专题命中 效率与部署 ：post-training(title,abstract)

PLUTO-4: Frontier Pathology Foundation Models

Harshith Padigela, Shima Nofallah, Atchuth Naveen Chilaparasetti, Ryun Han, Andrew Walker, Judy Shen, Chintan Shah, Blake Martin, Aashish Sood, Elliot Miller, Ben Glass, Andy Beck, Harsha Pokkalla, Syed Ashar Javed

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

An Evaluation of LLMs Inference on Popular Single-board Computers

Tung, Nguyen, Tuyen Nguyen

机构 * BillulloNex ； University of Technology Sydney（悉尼技术大学） 纠错

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

Comments 9 pages, 3 figures

Visual Bridge: Universal Visual Perception Representations Generating

Yilin Gao, Shuguang Dou, Junzhou Li, Zhiheng Yu, Yin Li, Dongsheng Jiang, Shugong Xu

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

Comments Accepted by AAAI2026

CryptoMoE: Privacy-Preserving and Scalable Mixture of Experts Inference via Balanced Expert Routing

Yifan Zhou, Tianshi Xu, Jue Hong, Ye Wu, Meng Li

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

Comments NeurIPS 2025

Enhancing reliability in AI inference services: An empirical study on real production incidents

Bhala Ranganathan, Mickey Zhang, Kai Wu

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

Hybrid Quantum-Classical Selective State Space Artificial Intelligence

Amin Ebrahimi, Farzan Haddadi

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

Comments 21 pages

LoopLLM: Transferable Energy-Latency Attacks in LLMs via Repetitive Generation

Xingyu Li, Xiaolei Liu, Cheng Liu, Yixiao Xu, Kangyi Ding, Bangzhou Xin, Jia-Li Yin

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

Comments 14 pages with 7 figures; accepted by the AAAI 2026

Enhancing Speech-to-Speech Dialogue Modeling with End-to-End Retrieval-Augmented Generation

Pengchao Feng, Ziyang Ma, Wenxi Chen, Yao Li, Sheng Wang, Kai Yu, Xie Chen

机构 * MoE Key Lab of Artificial Intelligence（人工智能增强实验室） ； Jiangsu Key Lab of Language Computing（江苏语言计算重点实验室） ； X-LANCE Lab（X-LANCE实验室） ； School of Computer Science, Shanghai Jiao Tong University（上海交通大学计算机科学学院） ； Shanghai Innovation Institute（上海创新研究院） ； Shanghai Aviation Electric Co., Ltd（上海航空电器有限公司） 纠错

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

Comments Accepted to EMNLP 2025 Findings

Journal ref Findings of the Association for Computational Linguistics: EMNLP 2025, pages 4499-4507

Parallel Sampling via Autospeculation

Nima Anari, Carlo Baronio, CJ Chen, Alireza Haqi, Frederic Koehler, Anqi Li, Thuy-Duong Vuong

专题命中 效率与部署 ：large language model(abstract)；language model(abstract)；分类 cs.LG

SCOPE: Intrinsic Semantic Space Control for Mitigating Copyright Infringement in LLMs

Zhenliang Zhang, Xinyu Hu, Xiaojun Wan

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

Comments Accepted by the AAAI 2026 (Main Track)

FIRST: Federated Inference Resource Scheduling Toolkit for Scientific AI Model Access

Aditya Tanikanti, Benoit Côté, Yanfei Guo, Le Chen, Nickolaus Saint, Ryan Chard, Ken Raffenetti, Rajeev Thakur, Thomas Uram, Ian Foster, Michael E. Papka, Venkatram Vishwanath

机构 * Argonne National Laboratory（阿贡国家实验室） ； The University of Chicago（芝加哥大学） ； University of Illinois Chicago（伊利诺伊大学芝加哥分校） 纠错

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

Journal ref SC Workshops '25, Proceedings of the SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis, ACM, pp. 52-60, 2025

ElasticMM: Efficient Multimodal LLMs Serving with Elastic Multimodal Parallelism

Zedong Liu, Shenggan Cheng, Guangming Tan, Yang You, Dingwen Tao

机构 * Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所） ； University of Electronic Science and Technology of China（电子科技大学） ； National University of Singapore（新加坡国立大学） 纠错

专题命中 效率与部署 ：large language model(abstract)；language model(abstract)；分类 cs.LG

Comments Accepted at NeurIPS 2025 Oral (Thirty-Ninth Conference on Neural Information Processing Systems)