语言大模型 / LLM

Towards Privacy-Preserving Large Language Model: Text-free Inference Through Alignment and Adaptation

面向隐私保护的大语言模型：通过对齐与适应实现文本-free推理

Jeongho Yoon, Chanhee Park, Yongchan Chun, Hyeonseok Moon, Heuiseok Lim

机构 * Department of Computer Science and Engineering, Korea University（高丽大学计算机科学与工程系） ； Samsung Mobile eXperience Business（三星移动体验事业部） 纠错

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

AI总结 本文提出PPFT方法，通过客户端编码器与服务器投影模块的协同训练，实现无需传输原始文本的隐私保护推理，平衡隐私与模型效用。

Structural Rigidity and the 57-Token Predictive Window: A Physical Framework for Inference-Layer Governability in Large Language Models

结构刚性和57个标记的预测窗口：一种用于大语言模型推理层可控性的物理框架

Gregory M. Ruddell

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

AI总结 本文提出一种物理框架，通过分析大语言模型的推理行为，揭示了预提交信号的存在条件，并展示了结构刚性在不同几何区域中的统一度量。

Comments Extends arXiv:2603.21415. 30 pages. Also available on Zenodo (10.5281/zenodo.19393882)

CLASP: Defending Hybrid Large Language Models Against Hidden State Poisoning Attacks

CLASP：防御混合大语言模型中的隐藏状态污染攻击

Alexandre Le Mercier, Thomas Demeester, Chris Develder

机构 * Ghent University–imec（根特大学–imec） 纠错

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

AI总结 CLASP通过分析Mamba块输出嵌入的差异模式，利用XGBoost分类器检测恶意token，实现高效防御隐藏状态污染攻击，具有轻量级部署优势。

Comments 22 pages, 6 figures

Deployment and Evaluation of an EHR-integrated, Large Language Model-Powered Tool to Triage Surgical Patients

一种集成电子健康记录的大型语言模型驱动工具在手术患者分诊中的部署与评估

Jane Wang, Timothy Keyes, April S Liang, Stephen P Ma, Jason Shen, Jerry Liu, Nerissa Ambers, Abby Pandya, Rita Pandya, Jason Hom, Natasha Steele, Jonathan H Chen, Kevin Schulman

机构 * Division of Hospital Medicine, Department of Medicine, Stanford University（斯坦福大学医院医学部，医学部） ； Stanford University School of Medicine（斯坦福大学医学院） ； Stanford Health Care, Technology and Digital Solutions（斯坦福健康，技术与数字解决方案） ； Division of Computational Medicine, Stanford University（斯坦福大学计算医学部） ； Stanford Health Care, Nursing Informatics（斯坦福健康，护理信息学） 纠错

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

AI总结 本文提出一种基于大型语言模型的工具，用于自动化手术患者分诊，通过电子健康记录实现，具有高灵敏度和中等特异性，展示了人工智能在医疗分诊中的应用价值。

Comments 35 pages, 4 figures, 5 tables

Efficient Continual Learning for Small Language Models with a Discrete Key-Value Bottleneck

小语言模型高效持续学习中的离散键值瓶颈

Andor Diera, Lukas Galke, Fabian Karl, Ansgar Scherp

机构 * Ulm University（乌尔姆大学） ； University of Southern Denmark（南部丹麦大学） 纠错

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

AI总结 本研究提出了一种适用于小语言模型的离散键值瓶颈结构，通过局部更新实现高效的持续学习，有效缓解灾难性遗忘并降低计算成本。

Deep Hierarchical Learning with Nested Subspace Networks for Large Language Models

基于嵌套子空间网络的深度分层学习用于大型语言模型

Paulius Rauba, Mihaela van der Schaar

机构 * University of Cambridge（剑桥大学） 纠错

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

AI总结 本文提出嵌套子空间网络，通过动态调整计算预算实现高效的大语言模型推理，实验证明在精度损失较小的情况下显著降低计算量。

Comments Published as a conference paper at ICLR 2026

Unveiling Super Experts in Mixture-of-Experts Large Language Models

揭示混合专家大语言模型中的超级专家

Zunhai Su, Qingyuan Li, Hao Zhang, Weihao Ye, Qibo Xue, YuLei Qian, Yuchen Xie, Ngai Wong, Kehong Yuan

机构 * Tsinghua University（清华大学） ； Meituan（美团） ； Xiamen University（厦门大学） ； Nanjing University（南京大学） ； The University of Hong Kong（香港大学） 纠错

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

AI总结 研究揭示了混合专家大语言模型中起关键作用的超级专家，通过分析其影响发现其在数学推理中的重要性，并探讨了压缩这些专家对模型性能的显著影响。

Comments Published as a conference paper at ICLR 2026

Efficient and accurate steering of Large Language Models through attention-guided feature learning

通过注意力引导的特征学习实现大语言模型的高效准确操控

Parmida Davarmanesh, Ashia Wilson, Adityanarayanan Radhakrishnan

机构 * MIT（麻省理工学院） ； Broad Institute of MIT and Harvard（麻省理工学院-哈佛大学Broad研究所） 纠错

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

AI总结 本文提出注意力引导的特征学习框架，通过解决三个核心挑战，显著提升了大语言模型的操控效率和效果，成功将可操控概念数量几乎翻倍。

A Lightweight Modular Framework for Constructing Autonomous Agents Driven by Large Language Models: Design, Implementation, and Applications in AgentForge

基于大语言模型的轻量模块化框架：用于AgentForge中的设计、实现与应用

Akbar Anbar Jafari, Cagri Ozcinar, Gholamreza Anbarjafari

机构 * University of Tartu（塔尔图大学） ； S Holding OÜ（3S控股公司） 纠错

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

AI总结 AgentForge是一种基于大语言模型的轻量模块化框架，通过可组合的技能抽象、统一的LLM后端接口和声明性配置系统，提升自主代理的开发效率和灵活性。

Comments 15 pages, 3 figures

HIPPO: Accelerating Video Large Language Models Inference via Holistic-aware Parallel Speculative Decoding

HIPPO：通过整体感知并行推测解码加速视频大语言模型推理

Qitan Lv, Tianyu Liu, Wen Wu, Xuenan Xu, Bowen Zhou, Feng Wu, Chao Zhang

机构 * University of Science and Technology of China（中国科学技术大学） ； Shanghai AI Laboratory（上海人工智能实验室） ； Department of Electronic Engineering, Tsinghua University（清华大学电子工程系） 纠错

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

AI总结 HIPPO通过整体感知并行推测解码框架，有效提升视频大语言模型推理速度，实现高达3.51倍的加速效果。

AndesVL Technical Report: An Efficient Mobile-side Multimodal Large Language Model

AndesVL 技术报告：一种高效的移动端多模态大语言模型

Zhiwei Jin, Xiaohui Song, Nan Wang, Yafei Liu, Chao Li, Xin Li, Ruichen Wang, Zhihao Li, Qi Qi, Long Cheng, Dongze Hao, Quanlong Zheng, Yanhao Zhang, Haobo Ji, Jian Ma, Zhitong Zheng, Zhenyi Lin, Haolin Deng, Xin Zou, Xiaojie Yin, Ruilin Wang, Liankai Cai, Haijing Liu, Yuqing Qiu, Ke Chen, Zixian Li, Chi Xie, Huafei Li, Chenxing Li, Chuangchuang Wang, Kai Tang, Zhiguang Zhu, Kai Tang, Wenmei Gao, Rui Wang, Jun Wu, Chao Liu, Qin Xie, Chen Chen, Haonan Lu

机构 * AndesVL Team（AndesVL团队） ； OPPO AI Center（OPPO人工智能中心） 纠错

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

AI总结 AndesVL 是一种高效的移动端多模态大语言模型，通过 1+N LoRA 架构和 QALFT 框架实现高效任务适应和模型压缩，部署在 MediaTek Dimensity 9500 芯片上，达到 6.7 倍解码加速和 30.9% 内存减少。

Comments Tech report of OPPO AndesVL Team

Adaptive Edge-Cloud Inference for Speech-to-Action Systems Using ASR and Large Language Models

基于ASR和大语言模型的自适应边缘-云推断用于语音到动作系统

Mohammad Jalili Torkamani, Israt Zarin

机构 * School of Computing, University of Nebraska--Lincoln（计算机学院，内布拉斯加大学林肯分校） 纠错

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

AI总结 本文提出ASTA系统，通过自适应边缘-云推断平衡性能与资源利用，实现语音到动作的可靠控制。

Comments preprint, 6 pages, 7 figures, 1 table

Parameter-Efficient Fine-Tuning with Differential Privacy for Robust Instruction Adaptation in Large Language Models

在大型语言模型中实现鲁棒性指令适应的差分隐私参数高效微调

Yulin Huang, Yaxuan Luan, Jinxu Guo, Xiangchen Song, Yuchen Liu

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

AI总结 本研究提出一种结合差分隐私与参数高效微调的方法，以提升大型语言模型在多任务指令场景中的鲁棒性和隐私保护能力。

DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

DeepSeek-V3.2: 推动开放大规模语言模型的前沿

DeepSeek-AI, Aixin Liu, Aoxue Mei, Bangcai Lin, Bing Xue, Bingxuan Wang, Bingzheng Xu, Bochao Wu, Bowei Zhang, Chaofan Lin, Chen Dong, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenhao Xu, Chong Ruan, Damai Dai, Daya Guo, Dejian Yang, Deli Chen, Erhang Li, Fangqi Zhou, Fangyun Lin, Fucong Dai, Guangbo Hao, Guanting Chen, Guowei Li, H. Zhang, Hanwei Xu, Hao Li, Haofen Liang, Haoran Wei, Haowei Zhang, Haowen Luo, Haozhe Ji, Honghui Ding, Hongxuan Tang, Huanqi Cao, Huazuo Gao, Hui Qu, Hui Zeng, Jialiang Huang, Jiashi Li, Jiaxin Xu, Jiewen Hu, Jingchang Chen, Jingting Xiang, Jingyang Yuan, Jingyuan Cheng, Jinhua Zhu, Jun Ran, Junguang Jiang, Junjie Qiu, Junlong Li, Junxiao Song, Kai Dong, Kaige Gao, Kang Guan, Kexin Huang, Kexing Zhou, Kezhao Huang, Kuai Yu, Lean Wang, Lecong Zhang, Lei Wang, Liang Zhao, Liangsheng Yin, Lihua Guo, Lingxiao Luo, Linwang Ma, Litong Wang, Liyue Zhang, M. S. Di, M. Y Xu, Mingchuan Zhang, Minghua Zhang, Minghui Tang, Mingxu Zhou, Panpan Huang, Peixin Cong, Peiyi Wang, Qiancheng Wang, Qihao Zhu, Qingyang Li, Qinyu Chen, Qiushi Du, Ruiling Xu, Ruiqi Ge, Ruisong Zhang, Ruizhe Pan, Runji Wang, Runqiu Yin, Runxin Xu, Ruomeng Shen, Ruoyu Zhang, S. H. Liu, Shanghao Lu, Shangyan Zhou, Shanhuang Chen, Shaofei Cai, Shaoyuan Chen, Shengding Hu, Shengyu Liu, Shiqiang Hu, Shirong Ma, Shiyu Wang, Shuiping Yu, Shunfeng Zhou, Shuting Pan, Songyang Zhou, Tao Ni, Tao Yun, Tian Pei, Tian Ye, Tianyuan Yue, Wangding Zeng, Wen Liu, Wenfeng Liang, Wenjie Pang, Wenjing Luo, Wenjun Gao, Wentao Zhang, Xi Gao, Xiangwen Wang, Xiao Bi, Xiaodong Liu, Xiaohan Wang, Xiaokang Chen, Xiaokang Zhang, Xiaotao Nie, Xin Cheng, Xin Liu, Xin Xie, Xingchao Liu, Xingkai Yu, Xingyou Li, Xinyu Yang, Xinyuan Li, Xu Chen, Xuecheng Su, Xuehai Pan, Xuheng Lin, Xuwei Fu, Y. Q. Wang, Yang Zhang, Yanhong Xu, Yanru Ma, Yao Li, Yao Li, Yao Zhao, Yaofeng Sun, Yaohui Wang, Yi Qian, Yi Yu, Yichao Zhang, Yifan Ding, Yifan Shi, Yiliang Xiong, Ying He, Ying Zhou, Yinmin Zhong, Yishi Piao, Yisong Wang, Yixiao Chen, Yixuan Tan, Yixuan Wei, Yiyang Ma, Yiyuan Liu, Yonglun Yang, Yongqiang Guo, Yongtong Wu, Yu Wu, Yuan Cheng, Yuan Ou, Yuanfan Xu, Yuduan Wang, Yue Gong, Yuhan Wu, Yuheng Zou, Yukun Li, Yunfan Xiong, Yuxiang Luo, Yuxiang You, Yuxuan Liu, Yuyang Zhou, Z. F. Wu, Z. Z. Ren, Zehua Zhao, Zehui Ren, Zhangli Sha, Zhe Fu, Zhean Xu, Zhenda Xie, Zhengyan Zhang, Zhewen Hao, Zhibin Gou, Zhicheng Ma, Zhigang Yan, Zhihong Shao, Zhixian Huang, Zhiyu Wu, Zhuoshu Li, Zhuping Zhang, Zian Xu, Zihao Wang, Zihui Gu, Zijia Zhu, Zilin Li, Zipeng Zhang, Ziwei Xie, Ziyi Gao, Zizheng Pan, Zongqing Yao, Bei Feng, Hui Li, J. L. Cai, Jiaqi Ni, Lei Xu, Meng Li, Ning Tian, R. J. Chen, R. L. Jin, S. S. Li, Shuang Zhou, Tianyu Sun, X. Q. Li, Xiangyue Jin, Xiaojin Shen, Xiaosha Chen, Xinnan Song, Xinyi Zhou, Y. X. Zhu, Yanping Huang, Yaohui Li, Yi Zheng, Yuchen Zhu, Yunxian Ma, Zhen Huang, Zhipeng Xu, Zhongyu Zhang, Dongjie Ji, Jian Liang, Jianzhong Guo, Jin Chen, Leyi Xia, Miaojun Wang, Mingming Li, Peng Zhang, Ruyi Chen, Shangmian Sun, Shaoqing Wu, Shengfeng Ye, T. Wang, W. L. Xiao, Wei An, Xianzu Wang, Xiaowen Sun, Xiaoxiang Wang, Ying Tang, Yukun Zha, Zekai Zhang, Zhe Ju, Zhen Zhang, Zihua Qu

机构 * DeepSeek-AI 纠错

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

AI总结 DeepSeek-V3.2通过高效注意力机制、强化学习框架和大规模代理任务合成流水线，在计算效率与推理能力上取得突破，超越GPT-5并获国际竞赛金牌。

Conversational SimulMT: Efficient Simultaneous Translation with Large Language Models

Minghan Wang, Thuy-Trang Vu, Yuxia Wang, Ehsan Shareghi, Gholamreza Haffari

机构 * Department of Data Science & AI, Monash University（数据科学与人工智能系，莫纳什大学） ； MBZUAI（马克斯·普朗克智能系统研究所） 纠错

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

Comments Accepted to IWSLT 2025

Data-Efficient Domain Adaptation for LLM-based MT using Contrastive Preference Optimization

Inacio Vieira, Antonio Castaldo, James O'Doherty, Sheila Castilho

机构 * Alpha CRC, Cambridge, UK（Alpha CRC（英国剑桥）） ； University of Pisa（比萨大学） ； Dublin City University, Ireland（都柏林城市大学（爱尔兰）） 纠错

专题命中 效率与部署 ：LLM(title)；preference optimization(title)；SFT(abstract)；分类 cs.CL

Contrastive Knowledge Transfer and Robust Optimization for Secure Alignment of Large Language Models

Jiasen Zheng, Huajun Zhang, Xu Yan, Ran Hao, Chong Peng

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

Adaptive Blockwise Search: Inference-Time Alignment for Large Language Models

Mohammad Atif Quamar, Mohammad Areeb, Nishant Sharma, Ananth Shreekumar, Jonathan Rosenthal, Muslum Ozgur Ozmen, Mikhail Kuznetsov, Z. Berkay Celik

机构 * Purdue University（普渡大学） ； Arizona State University（亚利桑那州立大学） ； Amazon（亚马逊） 纠错

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

Memory-based Language Models: An Efficient, Explainable, and Eco-friendly Approach to Large Language Modeling

Antal van den Bosch, Ainhoa Risco Patón, Teun Buijse, Peter Berck, Maarten van Gompel

机构 * Utrecht University（乌特勒支大学） ； Lund University（吕勒奥大学） ； Royal Netherlands Academy of Arts and Sciences（荷兰艺术与科学皇家学院） 纠错

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

Comments 15 pages, 11 figures

Advancing Symbolic Integration in Large Language Models: Beyond Conventional Neurosymbolic AI

Maneeha Rani, Bhupesh Kumar Mishra, Dhavalkumar Thakker

机构 * Data Science, AI & Modelling Centre (DAIM)（数据科学、人工智能与建模中心） ； School of Digital and Physical Sciences（数字与物理科学学院） ； University of Hull（霍尔大学） 纠错

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

Large Language Models Inference Engines based on Spiking Neural Networks

Adarsha Balaji, Sandeep Madireddy, Prasanna Balaprakash

机构 * Mathematics and Computer Science Division Argonne National Laboratory（阿贡国家实验室数学与计算机科学部） ； Computer Science and Mathematics Division Oak Ridge National Laboratory（橡树岭国家实验室计算机科学与数学部） 纠错

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

Augmenting Compliance-Guaranteed Customer Service Chatbots: Context-Aware Knowledge Expansion with Large Language Models

Mengze Hong, Chen Jason Zhang, Di Jiang, Yuanqin He

机构 * Hong Kong Polytechnic University（香港理工大学） ； AI Group, WeBank Co., Ltd（WeBank金融科技部） 纠错

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

Comments Accepted by EMNLP 2025 Industry Track

CARPAS: Towards Content-Aware Refinement of Provided Aspects for Summarization in Large Language Models

Yong-En Tian, Yu-Chien Tang, An-Zi Yen, Wen-Chih Peng

机构 * National Yang Ming Chiao Tung University（国家阳明交通大学） 纠错

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

Comments 22 pages, 17 figures

Goal-Guided Efficient Exploration via Large Language Model in Reinforcement Learning

Yajie Qi, Wei Wei, Lin Li, Lijun Zhang, Zhidong Gao, Da Wang, Huizhong Song

机构 * School of Computer and Information Technology, Shanxi University（计算机与信息技术学院，山西大学） 纠错

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

XplaiNLP at CheckThat! 2025: Multilingual Subjectivity Detection with Finetuned Transformers and Prompt-Based Inference with Large Language Models

Ariana Sahitaj, Jiaao Li, Pia Wenzel Neves, Fedor Splitt, Premtim Sahitaj, Charlott Jakob, Veronika Solopova, Vera Schmitt

机构 * Quality and Usability Lab, Technische Universität Berlin, Berlin, Germany（柏林技术大学质量与可用性实验室） ； German Research Center for Artificial Intelligence (DFKI), Berlin, Germany（德国人工智能研究中心（DFKI）） 纠错

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

Equinox: Holistic Fair Scheduling in Serving Large Language Models

Zhixiang Wei, James Yen, Jingyi Chen, Ziyang Zhang, Zhibai Huang, Chen Chen, Xingzi Yu, Yicheng Gu, Chenggang Wu, Yun Wang, Mingyuan Xia, Jie Wu, Hao Wang, Zhengwei Qi

机构 * Shanghai Jiao Tong University（上海交通大学） ； Cloud Computing Research Institute, China Telecom（云计算研究所，中国电信） ； Stevens Institute of Technology（史蒂文斯理工学院） 纠错

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

ChatGPT on the Road: Leveraging Large Language Model-Powered In-vehicle Conversational Agents for Safer and More Enjoyable Driving Experience

Yeana Lee Bond, Mungyeong Choe, Baker Kasim Hasan, Arsh Siddiqui, Myounghoon Jeon

机构 * Computer Science, Virginia Tech, Blacksburg, Virginia, USA（计算机科学，弗吉尼亚理工学院，弗吉尼亚州黑斯堡，美国；弗吉尼亚理工学院黑斯堡弗吉尼亚美国） ； Virginia Tech Blacksburg Virginia USA 纠错

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

Comments Submitted to International Journal of Human-Computer Studies. Bond and Choe: Drafting, Review, Editing, Validation, Software, Methodology, Investigation, Data Analysis, Conceptualization, Experiment training. Hasan and Siddiqui: Experimental and Data Analysis Support. Jeon: Supervision, Review, Resources, Project Admin, Methodology, Conceptualization. Total 34 pages

Contextual Morphogenesis in Large Language Models: A Novel Approach to Self-Organizing Token Representations

Alistair Dombrowski, Beatrix Engelhardt, Dimitri Fairbrother, Henry Evidail

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

Comments arXiv admin note: This paper has been withdrawn by arXiv due to disputed and unverifiable authorship

Structural Embedding Projection for Contextual Large Language Model Inference

Vincent Enoasmo, Cedric Featherstonehaugh, Xavier Konstantinopoulos, Zacharias Huntington

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

Comments arXiv admin note: This paper has been withdrawn by arXiv due to disputed and unverifiable authorship

EmbedGrad: Gradient-Based Prompt Optimization in Embedding Space for Large Language Models

Xiaoming Hou, Jiquan Zhang, Zibin Lin, DaCheng Tao, Shengli Zhang

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