arXivDaily arXiv每日学术速递 周一至周五更新

AI 大模型

语言大模型 / LLM

大语言模型、预训练、指令微调、后训练和语言模型应用。

共收录 12720 信号源:cs.CL, cs.AI, cs.LG

1. 领域大模型 12720 篇

2010.12871 2020-10-27 cs.CL cs.AI 73%

Large Scale Legal Text Classification Using Transformer Models

Zein Shaheen, Gerhard Wohlgenannt, Erwin Filtz

专题命中 领域大模型 :language model(abstract);pretraining(abstract);分类 cs.CL、cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2004.12303 2020-04-28 cs.AI cs.CL 73%

Challenge Closed-book Science Exam: A Meta-learning Based Question Answering System

Xinyue Zheng, Peng Wang, Qigang Wang, Zhongchao Shi

专题命中 领域大模型 :large language model(abstract);language model(abstract);分类 cs.CL、cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
1904.02817 2019-09-06 cs.CL cs.DL cs.LG 73%

Unsupervised Domain Adaptation of Contextualized Embeddings for Sequence Labeling

Xiaochuang Han, Jacob Eisenstein

专题命中 领域大模型 :language model(abstract);pretraining(abstract);分类 cs.CL、cs.LG

Comments EMNLP 2019

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.14667 2026-08-18 cs.AI cs.HC 新提交 72%

Position: AI Agents in Scientific Teams Should Be Studied as Human-Agent Systems

立场:科学团队中的智能体应作为人机系统(HAS)进行研究

Patrick Emami, Sameera Horawalavithana, Truc Nguyen, Gihan Panapitiya, Bruno Jacob, Siddhisanket Raskar, Saumya Sinha, Jared D. Willard, Andrew Glaws, Nithin Somasekharan, Ling Yue, Brian Lu, Shaowu Pan, Jason Eisner

专题命中 领域大模型 :language model(abstract,comments);large language model(abstract);分类 cs.AI

AI总结 针对当前AI科学家研究忽视科学团队社会层面的问题,提出将其作为人机系统(HAS)研究,分析相关风险并呼吁开发人机协同数学框架。

Comments 15 pages. Accepted at the COLM 2nd Workshop on Language Models for Scientific Discovery

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.21220 2026-08-24 cs.HC 新提交 71%

Who Trusts AI with Their Emotions? Trust Formation and Sociodemographic Variation in LLM Use for Emotional Support

谁会信任AI来处理自己的情绪?情感支持大语言模型使用中的信任形成与社会人口统计学差异

Natalia Amat-Lefort, Mert Yazan, Amanda Cercas Curry, Flor Miriam Plaza-del-Arco

专题命中 领域大模型 :LLM(title)

AI总结 本研究针对情感支持大语言模型,开发验证了心理测量量表,通过结构方程模型与多组分析发现不同社会人口群体对AI的信任影响因素及采纳逻辑存在差异,为情感支持AI的公平设计提供了理论支撑。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.22448 2026-08-21 cs.MA 版本更新 71%

Where Facts Go Missing: A Layerwise Taxonomy and Per-Layer Attribution of Information Omission in Air-Gapped LLMAgent Pipelines

事实缺失的地方:气隙式大语言模型智能体管道中信息遗漏的分层分类和逐层归因

Santhiya Rajan, Samuel Mugel, Roman Orus

专题命中 领域大模型 :LLM(title)

AI总结 研究气隙式大语言模型智能体管道中信息遗漏问题,提出九层分类法、归因方法、跨架构比较框架及运行时检测框架,经多模型多引擎试验,确定遗漏率及来源,为定位运营商干预位置提供依据。

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.09991 2026-08-12 eess.IV cs.CV 新提交 71%

Longitudinal 3D Foundation Modeling for Neoadjuvant Breast Cancer Response Prediction from Serial DCE-MRI

用于从系列动态对比增强磁共振成像(DCE-MRI)预测乳腺癌新辅助治疗反应的纵向三维基础建模

Fidel Omar Tito Cruz, Neda Ghafouri, Zengyan Wang, Pegah Khosravi, Yu Tian, Chen Chen

机构 * University of Central Florida(中佛罗里达大学)

专题命中 领域大模型 :foundation model(title)

AI总结 本研究提出结合三维基础编码器与时间动态网络的纵向框架,融合系列DCE-MRI与临床数据,在982例乳腺癌患者上实现了较好的pCR预测性能。

Comments Accepted at the Applications of Medical AI (AMAI) Workshop at MICCAI 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.23297 2026-07-29 cs.CV 版本更新 71%

PRIMA: Pre-Training with Risk-Integrated Image--Metadata Alignment for Medical Diagnosis with LLM-Based Feature Aggregation

PRIMA:通过大语言模型进行风险集成图像-元数据对齐的医学诊断预训练

Yiqing Wang, Chunming He, Ziyun Yang, Maria Woodward, Ming-Chen Lu, Mercy Pawar, Leslie Niziol, Sina Farsiu

机构 * Department of Biomedical Engineering, Duke University(杜克大学生物医学工程系) Department of Ophthalmology and Visual Sciences, University of Michigan(密歇根大学眼科与视觉科学系)

专题命中 领域大模型 :LLM(title)

AI总结 提出PRIMA框架,通过检索增强生成策展风险-疾病关联专家语料库优化文本编码器,用双编码器预训练策略及四个互补损失函数弥合模态差距,融合特征用于疾病分类,性能优于其他方法。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.24000 2026-07-28 cs.SE 新提交 71%

Industrial Practice of LLM-Based Test Case Carving and Assertion Generation (Experience Paper)

基于大语言模型的测试用例提取与断言生成的工业实践(经验论文)

Haozhen You, Zhen Dong, Jingjing Wang, Qiang Li, Xin Peng

专题命中 领域大模型 :LLM(title)

AI总结 针对微服务系统回归测试因文档问题面临的挑战,提出NL2Test工具,通过自然语言描述和流量捕获生成可执行API回归测试,经大语言模型和确定性算法完成测试用例提取与断言生成等任务,在工业场景中效果良好,减少人工并提升自动化程度。

Comments 23 pages, 6 figures, Proceedings of the 35th ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA 2026)

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.16633 2026-07-21 cs.IR 新提交 71%

Beyond Fixed Depths and Widths: Optimizing Textual Decoding Tries in LLM-based Generative Recommendation

超越固定深度和宽度:优化基于大语言模型的生成式推荐中的文本解码树

Jingzhe Liu, Hanbing Wang, Jiliang Tang, Liam Collins, Tong Zhao, Neil Shah, Mingxuan Ju

专题命中 领域大模型 :LLM(title)

AI总结 研究基于大语言模型的生成式推荐中解码树结构问题,提出BONSAI框架,从项目元数据提取信息丰富的词,用最小集覆盖公式构建满足自适应ID长度和约束分支因子属性的解码树,实验显示比基线有高达21.6%的相对改进。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.14601 2026-07-17 cs.SE 新提交 71%

SYNAPSE: A Multi-LLM Orchestrated AI Tutor for Secure Software Development Education with Neurodivergent-First Design

SYNAPSE:一个多语言大模型编排的人工智能导师,用于具有神经差异优先设计的安全软件开发教育

Giusy Ferrara, Ashkan Sami

专题命中 领域大模型 :LLM(title)

AI总结 针对安全软件开发教育中神经差异学习者的问题,SYNAPSE平台通过协调多个大模型,采用三阶段苏格拉底式提示策略,结合可访问性特征和ShopSecure应用,实现自适应辅导,提高了可用性和参与度。

Comments Accepted at the 42nd IEEE International Conference on Software Maintenance and Evolution (ICSME 2026), Tool Demonstration and Data Showcase Track. Source code archived at https://doi.org/10.5281/zenodo.20480483

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.18130 2026-05-19 cs.CV 71%

Rad-VLSM: A Cross-Modal Framework with Semantics-Assisted Prompting for Medical Segmentation and Diagnosis

Rad-VLSM:一种结合语义辅助提示的跨模态框架用于医学分割与诊断

Fengyi Zhang, Xujie Zeng, Mohan Liu, Zengyi Wang, Yalong Jiang

机构 * Student Member, IEEE(IEEE学生会员) Member, IEEE(IEEE会员)

专题命中 领域大模型 :prompting(title)

AI总结 本文提出Rad-VLSM框架,通过语义引导的提示机制,提升医学图像分割与诊断的准确性,解决现有模型易受背景组织和无关视觉相关性干扰的问题。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.18313 2026-04-21 cs.CV 71%

Denoise and Align: Diffusion-Driven Foreground Knowledge Prompting for Open-Vocabulary Temporal Action Detection

去噪与对齐:基于扩散的前景知识提示用于开放词汇时序动作检测

Sa Zhu, Wanqian Zhang, Lin Wang, Jinchao Zhang, Cong Wang, Bo Li

机构 * Institute of Information Engineering, Chinese Academy of Sciences School of Cyber Security, University of Chinese Academy of Sciences State Key Laboratory of Cyberspace Security Defense Beijing China Institute of Information Engineering, Chinese Academy of Sciences Beijing China Hangzhou Dianzi University Hangzhou China Institute of Information Engineering, Chinese Academy of Sciences\ Key Laboratory of Cyberspace Security Defense Beijing China Engineering, Zhejiang University Hangzhou China Institute of Information Engineering, Chinese Academy of Sciences State Key Laboratory of Cyberspace Security Defense Beijing China Institute of Information Engineering, Chinese Academy of Sciences School of Cyber Security, University of Chinese Academy of Sciences State Key Laboratory of Cyberspace Security Defense Institute of Information Engineering, Chinese Academy of Sciences Hangzhou Dianzi University Institute of Information Engineering, Chinese Academy of Sciences\ Key Laboratory of Cyberspace Security Defense Engineering, Zhejiang University Institute of Information Engineering, Chinese Academy of Sciences State Key Laboratory of Cyberspace Security Defense

专题命中 领域大模型 :prompting(title)

AI总结 本文提出DFAlign框架,通过扩散去噪生成前景知识,解决开放词汇时序动作检测中语义不平衡问题,提升动作相关片段的判别性。

Comments Accepted by SIGIR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.09814 2026-04-14 cs.CV 71%

RobustMedSAM: Degradation-Resilient Medical Image Segmentation via Robust Foundation Model Adaptation

RobustMedSAM: 通过鲁棒基础模型适应实现抗退化的医学图像分割

Jieru Li, Matthew Chen, Micky C. Nnamdi, J. Ben Tamo, Benoit L. Marteau, May D. Wang

机构 * Georgia Institute of Technology(佐治亚理工学院)

专题命中 领域大模型 :foundation model(title)

AI总结 本文提出RobustMedSAM,通过模块级检查点融合和参数高效变体,提升医学图像分割在退化数据下的鲁棒性,实验表明其在降质图像Dice系数上优于SAM。

Comments 14 pages, 9 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.21287 2026-03-24 cs.CV 71%

Focus on Background: Exploring SAM's Potential in Few-shot Medical Image Segmentation with Background-centric Prompting

聚焦背景:探索SAM在少样本医学图像分割中的潜力:基于背景的提示生成

Yuntian Bo, Yazhou Zhu, Piotr Koniusz, Haofeng Zhang

机构 * Nanjing University of Science and Technology(南京理工大学) University of New South Wales(新南威尔士大学) Data61 CSIRO

专题命中 领域大模型 :prompting(title)

AI总结 本文提出FoB,通过背景中心提示生成解决SAM在医学图像分割中的过度分割问题,实验表明其在少样本分割任务中表现优异,具有良好的跨领域泛化能力。

Comments Accepted by CVPR26

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.12814 2026-02-11 cs.SI cs.CY 71%

Tiered Anonymity on Social-Media Platforms as a Countermeasure against Deepfakes and LLM-Driven Mass Misinformation

社交媒体平台的分层匿名性:作为对抗深度伪造和大语言模型驱动的虚假信息的对策

David Khachaturov, Roxanne Schnyder, Robert Mullins

专题命中 领域大模型 :LLM(title)

AI总结 本文提出通过三级匿名框架应对深度伪造和大语言模型驱动的虚假信息,通过影响力评分区分用户层级并实施差异化隐私保护措施。

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.22283 2025-11-27 cs.CV 71%

Rule-Based Reinforcement Learning for Document Image Classification with Vision Language Models

基于规则的强化学习用于文档图像分类与视觉语言模型

Michael Jungo, Andreas Fischer

机构 * University of Applied Sciences and Arts Western Switzerland(西瑞士应用艺术大学) University of Fribourg(弗里堡大学)

专题命中 领域大模型 :language model(title)

AI总结 本文提出基于规则的强化学习方法,用于提升文档图像分类任务的泛化能力,通过不同场景验证其在处理超出分布数据时的优势。

Comments Code available at https://github.com/jungomi/vision-finetune

Journal ref Document Analysis and Recognition - ICDAR 2025 Workshops. pp. 292-309. Cham: Springer Nature Switzerland

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.17201 2025-11-24 cs.CV 71%

Continual Alignment for SAM: Rethinking Foundation Models for Medical Image Segmentation in Continual Learning

持续对齐用于SAM:重新思考面向持续学习的医学图像分割的基础模型

Jiayi Wang, Wei Dai, Haoyu Wang, Sihan Yang, Haixia Bi, Jian Sun

机构 * Xi’an Jiaotong University(西安交通大学) School of Information and Communications Engineering, Xi’an Jiaotong University(信息与通信工程学院) School of Mathematics and Statistics, Xi’an Jiaotong University(数学与统计学学院)

专题命中 领域大模型 :foundation model(title)

AI总结 CA-SAM通过引入对齐层,实现了在持续学习中高效适应医学图像分割,提升性能并减少计算开销。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.02113 2025-11-11 cs.IR 71%

Enhancing Multimodal Recommendations with Vision-Language Models and Information-Aware Fusion

Hai-Dang Kieu, Min Xu, Thanh Trung Huynh, Dung D. Le

专题命中 领域大模型 :language model(title)

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.01234 2025-10-21 cs.MA physics.optics 71%

First Field-Trial Demonstration of L4 Autonomous Optical Network for Distributed AI Training Communication: An LLM-Powered Multi-AI-Agent Solution

Yihao Zhang, Qizhi Qiu, Xiaomin Liu, Dianxuan Fu, Xingyu Liu, Leyan Fei, Yuming Cheng, Lilin Yi, Weisheng Hu, Qunbi Zhuge

专题命中 领域大模型 :LLM(title)

Comments Accepted by 51st European Conference on Optical Communication (ECOC 2025), paper W.02.01.177

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.20462 2025-10-01 cs.CY 71%

Automated Quality Assessment for LLM-Based Complex Qualitative Coding: A Confidence-Diversity Framework

Zhilong Zhao, Yindi Liu

专题命中 领域大模型 :LLM(title)

Comments 21 pages, 2 figures, 5 tables. v2: revised abstract and JCSS-aligned prose; unified table formatting and naming; clean compile

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.20940 2025-09-26 cs.IR 71%

Markup Language Modeling for Web Document Understanding

Su Liu, Bin Bi, Jan Bakus, Paritosh Kumar Velalam, Vijay Yella, Vinod Hegde

专题命中 领域大模型 :language model(title)

详情

展开后加载摘要…

URL PDF HTML 收藏
2501.17595 2025-09-26 cs.CV 71%

Technical report on label-informed logit redistribution for better domain generalization in low-shot classification with foundation models

Behraj Khan, Tahir Syed

机构 * School of Mathematics and Computer Science(数学与计算机科学学院) Institute of Business Administration(商学院)

专题命中 领域大模型 :foundation model(title)

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.02505 2025-09-16 cs.RO 71%

Would you let a humanoid play storytelling with your child? A usability study on LLM-powered narrative Human-Robot Interaction

Maria Lombardi, Carmela Calabrese, Davide Ghiglino, Caterina Foglino, Davide De Tommaso, Giulia Da Lisca, Lorenzo Natale, Agnieszka Wykowska

机构 * Humanoid Sensing and Perception, Italian Institute of Technology (IIT)(人形感知与感知,意大利技术研究院) Social Cognition in Human-Robot Interaction, IIT(人机交互中的社会认知,IIT)

专题命中 领域大模型 :LLM(title)

Journal ref 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems, Hangzhou, China, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.08570 2025-09-11 cs.CV 71%

Vision-Language Semantic Aggregation Leveraging Foundation Model for Generalizable Medical Image Segmentation

Wenjun Yu, Yinchen Zhou, Jia-Xuan Jiang, Shubin Zeng, Yuee Li, Zhong Wang

机构 * organization= School of Information Science \& Engineering, Lanzhou University , addressline= , city= Lanzhou , postcode= 730000 , country= China

专题命中 领域大模型 :foundation model(title)

Comments 29 pages and 8 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.24039 2025-08-19 cs.CV cs.HC 71%

Foundation Models for Zero-Shot Segmentation of Scientific Images without AI-Ready Data

Shubhabrata Mukherjee, Jack Lang, Obeen Kwon, Iryna Zenyuk, Valerie Brogden, Adam Weber, Daniela Ushizima

机构 * Lawrence Berkeley National Laboratory(伯克利国家实验室) University of California, Irvine(加州大学尔湾分校) University of California, Berkeley(加州大学伯克利分校) Covalent Metrology(协力计量)

专题命中 领域大模型 :foundation model(title)

Comments This paper has been accepted for presentation at the 59th International Conference on Parallel Processing (ICPP 2025), DRAI workshop

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.09785 2025-08-14 cs.CV 71%

DSS-Prompt: Dynamic-Static Synergistic Prompting for Few-Shot Class-Incremental Learning

Linpu He, Yanan Li, Bingze Li, Elvis Han Cui, Donghui Wang

机构 * Department of Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术系) Research Center for Frontier Fundamental Studies, Zhejiang Lab(浙江实验室前沿基础研究中心) Department of Neurology, University of California, Irvine(加州大学伊市医学院神经科)

专题命中 领域大模型 :prompting(title)

Comments Accepted to ACMMM 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.21842 2025-07-30 cs.CY 71%

Prompt template for a fictitious LLM agent in a content-flagging experiment

Marie-Therese Sekwenz, Daria Simons, Alina Wundsam

专题命中 领域大模型 :LLM(title)

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.07548 2025-07-11 cs.SE 71%

From Requirements to Code: Understanding Developer Practices in LLM-Assisted Software Engineering

Jonathan Ullrich, Matthias Koch, Andreas Vogelsang

专题命中 领域大模型 :LLM(title)

Comments This paper has been accepted for publication at the 33rd IEEE International Requirements Engineering (RE) conference

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.17645 2025-06-24 cs.CV 71%

Histopathology Image Report Generation by Vision Language Model with Multimodal In-Context Learning

Shih-Wen Liu, Hsuan-Yu Fan, Wei-Ta Chu, Fu-En Yang, Yu-Chiang Frank Wang

机构 * National Cheng Kung University, Taiwan(国立成功大学) NVIDIA Research(NVIDIA研究)

专题命中 领域大模型 :language model(title)

Comments Accepted to MIDL 2025

详情

展开后加载摘要…

URL PDF HTML 收藏