语言大模型 / LLM

FlexQ: Efficient Post-training INT6 Quantization for LLM Serving via Algorithm-System Co-Design

Hao Zhang, Aining Jia, Weifeng Bu, Yushu Cai, Kai Sheng, Hao Chen, Xin He

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

RepoMark: A Data-Usage Auditing Framework for Code Large Language Models

Wenjie Qu, Yuguang Zhou, Bo Wang, Yuexin Li, Lionel Z. Wang, Jinyuan Jia, Jiaheng Zhang

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

ShortV: Efficient Multimodal Large Language Models by Freezing Visual Tokens in Ineffective Layers

Qianhao Yuan, Qingyu Zhang, Yanjiang Liu, Jiawei Chen, Yaojie Lu, Hongyu Lin, Jia Zheng, Xianpei Han, Le Sun

机构 * Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所） ； University of Chinese Academy of Sciences（中国科学院大学） 纠错

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

Comments Published as a conference paper at ICCV 2025. Project page: https://github.com/icip-cas/ShortV

Modular Task Decomposition and Dynamic Collaboration in Multi-Agent Systems Driven by Large Language Models

Shuaidong Pan, Di Wu

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

Duplex: A Device for Large Language Models with Mixture of Experts, Grouped Query Attention, and Continuous Batching

Sungmin Yun, Kwanhee Kyung, Juhwan Cho, Jaewan Choi, Jongmin Kim, Byeongho Kim, Sukhan Lee, Kyomin Sohn, Jung Ho Ahn

机构 * Seoul National University（首尔国立大学） ； Samsung Electronics（三星电子） 纠错

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

Comments 15 pages, 16 figures, accepted at MICRO 2024

Scaling Graph Chain-of-Thought Reasoning: A Multi-Agent Framework with Efficient LLM Serving

Chengying Huan, Ziheng Meng, Yongchao Liu, Zhengyi Yang, Yun Zhu, Yue Yun, Shipeng Li, Rong Gu, Xiabao Wu, Haitao Zhang, Chuntao Hong, Shaonan Ma, Guihai Chen, Chen Tian

机构 * Nanjing University（南京大学） ； Ant Group（蚂蚁集团） ； University of New South Wales（新南威尔士大学） ； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室） ； Tsinghua University（清华大学） 纠错

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

GTAlign: Game-Theoretic Alignment of LLM Assistants for Social Welfare

Siqi Zhu, David Zhang, Pedro Cisneros-Velarde, Jiaxuan You

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） ； VMware Research（VMware研究） 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、cs.LG

Comments 31 pages, 6 figures

LiteVLM: A Low-Latency Vision-Language Model Inference Pipeline for Resource-Constrained Environments

Jin Huang, Yuchao Jin, Le An, Josh Park

机构 * NVIDIA（英伟达） 纠错

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

SmartMLOps Studio: Design of an LLM-Integrated IDE with Automated MLOps Pipelines for Model Development and Monitoring

Jiawei Jin, Yingxin Su, Xiaotong Zhu

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

Urban-MAS: Human-Centered Urban Prediction with LLM-Based Multi-Agent System

Shangyu Lou

机构 * University of California, Santa Barbara \& San Diego State University California USA ； University of California, Santa Barbara \& San Diego State University 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

Comments Accepted to The 3rd ACM SIGSPATIAL International Workshop on Advances in Urban AI (UrbanAI'25)

ShadowLogic: Backdoors in Any Whitebox LLM

Kasimir Schulz, Amelia Kawasaki, Leo Ring

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

Journal ref Proceedings of Machine Learning Research 299:1-11, 2025 Conference on Applied Machine Learning for Information Security

KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systems

Hancheng Ye, Zhengqi Gao, Mingyuan Ma, Qinsi Wang, Yuzhe Fu, Ming-Yu Chung, Yueqian Lin, Zhijian Liu, Jianyi Zhang, Danyang Zhuo, Yiran Chen

机构 * Duke University（杜克大学） ； MIT（麻省理工学院） ； NVIDIA（英伟达） 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

Comments Accepted for publication in NeurIPS2025. Code is available at \url{https://github.com/FastMAS/KVCOMM}

Harmony in Divergence: Towards Fast, Accurate, and Memory-efficient Zeroth-order LLM Fine-tuning

Qitao Tan, Jun Liu, Zheng Zhan, Caiwei Ding, Yanzhi Wang, Xiaolong Ma, Jaewoo Lee, Jin Lu, Geng Yuan

机构 * University of Georgia（佐治亚大学） ； Northeastern University（东北大学） ； University of Minnesota（明尼苏达大学） ； University of Arizona（亚利桑那大学） 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

ParaRNN: Unlocking Parallel Training of Nonlinear RNNs for Large Language Models

Federico Danieli, Pau Rodriguez, Miguel Sarabia, Xavier Suau, Luca Zappella

机构 * Apple（苹果公司） 纠错

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

Beyond Autoregression: An Empirical Study of Diffusion Large Language Models for Code Generation

Chengze Li, Yitong Zhang, Jia Li, Liyi Cai, Ge Li

机构 * College of AI, Tsinghua University（清华大学人工智能学院） ； School of Computer Science, Nanjing University（南京大学计算机科学学院） ； School of Computer Science and Engineering, Beihang University（北航计算机科学与工程学院） ； School of Computer Science, Peking University（北京大学计算机科学学院） 纠错

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

URDF-Anything: Constructing Articulated Objects with 3D Multimodal Language Model

Zhe Li, Xiang Bai, Jieyu Zhang, Zhuangzhe Wu, Che Xu, Ying Li, Chengkai Hou, Shanghang Zhang

机构 * State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University（多媒体信息处理国家重点实验室，计算机学院，北京大学） ； University of Washington（华盛顿大学） 纠错

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

Comments Accepted to the 39th Conference on Neural Information Processing Systems (NeurIPS 2025)

Transferring Linear Features Across Language Models With Model Stitching

Alan Chen, Jack Merullo, Alessandro Stolfo, Ellie Pavlick

机构 * Brown University（布朗大学） ； ETH Zürich（苏黎世联邦理工学院） 纠错

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

Generalizing Test-time Compute-optimal Scaling as an Optimizable Graph

Fali Wang, Jihai Chen, Shuhua Yang, Runxue Bao, Tianxiang Zhao, Zhiwei Zhang, Xianfeng Tang, Hui Liu, Qi He, Suhang Wang

机构 * The Pennsylvania State University（宾夕法尼亚州立大学） ； University of Pittsburgh（匹兹堡大学） ； Amazon（亚马逊） ； Microsoft（微软） 纠错

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

Comments Under review

PixelRefer: A Unified Framework for Spatio-Temporal Object Referring with Arbitrary Granularity

Yuqian Yuan, Wenqiao Zhang, Xin Li, Shihao Wang, Kehan Li, Wentong Li, Jun Xiao, Lei Zhang, Beng Chin Ooi

机构 * Zhejiang University（浙江大学） ； DAMO Academy, Alibaba Group（阿里云图研究院） ； Hupan Lab（鸿篇实验室） ； The Hong Kong Polytechnic University（香港理工大学） 纠错

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

Comments 22 pages, 13 figures

Diffusion LLMs are Natural Adversaries for any LLM

David Lüdke, Tom Wollschläger, Paul Ungermann, Stephan Günnemann, Leo Schwinn

机构 * Department of Computer Science \& Munich Data Science Institute Technical University of Munich, Germany 纠错

专题命中 效率与部署 ：LLM(title)；prompting(abstract)；分类 cs.LG

Vision-Language Model-Based Semantic-Guided Imaging Biomarker for Lung Nodule Malignancy Prediction

Luoting Zhuang, Seyed Mohammad Hossein Tabatabaei, Ramin Salehi-Rad, Linh M. Tran, Denise R. Aberle, Ashley E. Prosper, William Hsu

机构 * organization= Medical \& Imaging Informatics, Department of Radiological Sciences, David Geffen School of Medicine at UCLA , city= Los Angeles , postcode= 90095 , state= CA , country= USA ； organization= Department of Medicine, Division of Pulmonology ； Critical Care, David Geffen School of Medicine at UCLA , city= Los Angeles , postcode= 90095 , state= CA , country= USA 纠错

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

Journal ref Journal of Biomedical Informatics 172 (2025) 104947

When, What, and How: Rethinking Retrieval-Enhanced Speculative Decoding

Min Fang, Zhihui Fu, Qibin Zhao, Jun Wang

机构 * OPPO Research Institute（OPPO研究院） 纠错

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

Outlier-Aware Post-Training Quantization for Image Super-Resolution

Hailing Wang, jianglin Lu, Yitian Zhang, Yun Fu

机构 * Northeastern University, USA（东北大学） 纠错

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

STAF: Leveraging LLMs for Automated Attack Tree-Based Security Test Generation

Tanmay Khule, Stefan Marksteiner, Jose Alguindigue, Hannes Fuchs, Sebastian Fischmeister, Apurva Narayan

机构 * Department of Systems Design Engineering, University of Waterloo, ON Canada（滑铁卢大学系统设计工程系） ； Smart Calibration and Virtual Testing Department, AVL List GmbH, Graz, Austria（AVL List GmbH智能校准与虚拟测试部门） ； Department of Computer Science, Western University, London, ON, Canada（温哥华大学计算机科学系） 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 18 pages, 2 figures, accepted for 23rd escar Europe (Nov 05-06, 2025, Frankfurt, Germany)

Journal ref 23rd escar Europe : The World's Leading Automotive Cyber Security Conference 2025

PolyG: Adaptive Graph Traversal for Diverse GraphRAG Questions

Renjie Liu, Haitian Jiang, Xiao Yan, Bo Tang, Jinyang Li

机构 * Southern University of Science and Technology（南方科技大学） ； New York University（纽约大学） ； Wuhan University（武汉大学） 纠错

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

FlashEVA: Accelerating LLM inference via Efficient Attention

Juan Gabriel Kostelec, Qinghai Guo

机构 * Huawei Technologies（华为技术） 纠错

专题命中 效率与部署 ：LLM(title)；分类 cs.CL、cs.AI

Comments Technical Report

Sherlock: Reliable and Efficient Agentic Workflow Execution

Yeonju Ro, Haoran Qiu, Íñigo Goiri, Rodrigo Fonseca, Ricardo Bianchini, Aditya Akella, Zhangyang Wang, Mattan Erez, Esha Choukse

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

A Graph-based RAG for Energy Efficiency Question Answering

Riccardo Campi, Nicolò Oreste Pinciroli Vago, Mathyas Giudici, Pablo Barrachina Rodriguez-Guisado, Marco Brambilla, Piero Fraternali

机构 * Politecnico di Milano, DEIB Department（米兰Politecnico大学DEIB部门） ； Voltiva Energy（Voltiva能源公司） 纠错

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

Journal ref Verma, H., Bozzon, A., Mauri, A., Yang, J. (eds) Web Engineering. ICWE 2025. Lecture Notes in Computer Science, vol 15749. Springer, Cham

Localist LLMs -- A Mathematical Framework for Dynamic Locality Control

Joachim Diederich

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

Learning When to Quit in Sales Conversations

Emaad Manzoor, Eva Ascarza, Oded Netzer

机构 * Cornell University（康奈尔大学） ； Harvard Business School（哈佛商学院） ； Columbia Business School（哥伦比亚商学院） 纠错

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