arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~

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。

2025-10-22 至 2025-10-22 共收录 233 信号源:cs.CL, cs.AI, cs.LG

1. 效率与部署 42 篇

2510.18636 2025-10-22 cs.CV cs.AI cs.LG cs.RO 62%

C-SWAP: Explainability-Aware Structured Pruning for Efficient Neural Networks Compression

Baptiste Bauvin, Loïc Baret, Ola Ahmad

机构 * Thales cortAIx Lab Montreal, QC, Canada(泰雷兹 cortAIx 实验室,加拿大魁北克省蒙特利尔)

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

Comments 10 pages, BMVC2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.18541 2025-10-22 cs.LG cs.AI cs.CR 62%

Pay Attention to the Triggers: Constructing Backdoors That Survive Distillation

Giovanni De Muri, Mark Vero, Robin Staab, Martin Vechev

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.17393 2025-10-22 cs.AI cs.CL 62%

Program Synthesis via Test-Time Transduction

Kang-il Lee, Jahyun Koo, Seunghyun Yoon, Minbeom Kim, Hyukhun Koh, Dongryeol Lee, Kyomin Jung

机构 * Dept. of ECE, Seoul National University(电子工程系,首尔国立大学) IPAI, Seoul National University(IPAI,首尔国立大学) Adobe Research(Adobe研究院)

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

Comments NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.21262 2025-10-22 cs.AI cs.LG 62%

Modeling Human Beliefs about AI Behavior for Scalable Oversight

Leon Lang, Patrick Forré

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

Comments 56 pages

Journal ref Transactions on Machine Learning Research, Aug. 2025. https://openreview.net/forum?id=gSJfsdQnex

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.18699 2025-10-22 cs.MA cs.AI 57%

Fetch.ai: An Architecture for Modern Multi-Agent Systems

Michael J. Wooldridge, Attila Bagoly, Jonathan J. Ward, Emanuele La Malfa, Gabriel Paludo Licks

机构 * University of Oxford(牛津大学)

专题命中 效率与部署 :LLM(abstract);分类 cs.AI

Comments 26 pages, figures, code examples

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.18583 2025-10-22 cs.CV cs.LG 57%

CovMatch: Cross-Covariance Guided Multimodal Dataset Distillation with Trainable Text Encoder

Yongmin Lee, Hye Won Chung

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

Comments NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.09252 2025-10-22 cs.LG stat.ML 57%

TPP-SD: Accelerating Transformer Point Process Sampling with Speculative Decoding

Shukai Gong, Yiyang Fu, Fengyuan Ran, Quyu Kong, Feng Zhou

机构 * Center for Applied Statistics and School of Statistics, Renmin University of China(应用统计中心和统计学院,中国人民大学) School of Information, Renmin University of China(信息学院,中国人民大学) School of Cyber Science and Engineering, Wuhan University(网络安全与工程学院,武汉大学) Alibaba Group(阿里巴巴集团)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.16333 2025-10-22 cs.LG 57%

Understanding Differential Transformer Unchains Pretrained Self-Attentions

Chaerin Kong, Jiho Jang, Nojun Kwak

机构 * TwelveLabs Seoul National University(首尔国立大学)

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

Comments NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.15093 2025-10-22 q-bio.BM cs.LG 57%

Steering Generative Models with Experimental Data for Protein Fitness Optimization

Jason Yang, Wenda Chu, Daniel Khalil, Raul Astudillo, Bruce J. Wittmann, Frances H. Arnold, Yisong Yue

机构 * California Institute of Technology(加州理工学院) Microsoft Corporation(微软公司)

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

Comments NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.18716 2025-10-22 cs.CV 50%

SSD: Spatial-Semantic Head Decoupling for Efficient Autoregressive Image Generation

Siyong Jian, Huan Wang

机构 * Westlake University(西湖大学)

专题命中 效率与部署 :language model(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.18213 2025-10-22 cs.CV 50%

EMA-SAM: Exponential Moving-average for SAM-based PTMC Segmentation

Maryam Dialameh, Hossein Rajabzadeh, Jung Suk Sim, Hyock Ju Kwon

机构 * Department of Mechanical and Mechatronics Engineering, University of Waterloo(滑铁卢大学机械与机电工程系) Department of Radiology, Withsim Clinic(放射科,Withsim诊所) Ewha Womans University Medical Center(成均馆大学医学院)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.15277 2025-10-22 cs.CV 50%

Foundation Cures Personalization: Improving Personalized Models' Prompt Consistency via Hidden Foundation Knowledge

Yiyang Cai, Zhengkai Jiang, Yulong Liu, Chunyang Jiang, Wei Xue, Yike Guo, Wenhan Luo

机构 * Hong Kong University of Science and Technology (HKUST)(香港科技大学) Tencent Hunyuan(腾讯文元)

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

Comments Accepted to NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏

2. 领域大模型 13 篇

2510.18674 2025-10-22 cs.CR cs.AI 88%

Exploring Membership Inference Vulnerabilities in Clinical Large Language Models

Alexander Nemecek, Zebin Yun, Zahra Rahmani, Yaniv Harel, Vipin Chaudhary, Mahmood Sharif, Erman Ayday

机构 * Case Western Reserve University(凯斯西储大学) Tel Aviv University(特拉维夫大学)

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

Comments Accepted at the 1st IEEE Workshop on Healthcare and Medical Device Security, Privacy, Resilience, and Trust (IEEE HMD-SPiRiT)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.18304 2025-10-22 cs.CV cs.CL 88%

The Impact of Image Resolution on Biomedical Multimodal Large Language Models

Liangyu Chen, James Burgess, Jeffrey J Nirschl, Orr Zohar, Serena Yeung-Levy

机构 * Stanford University(斯坦福大学) Institute for Computational and Mathematical Engineering (ICME)(计算与数学工程研究所)

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

Comments Proceedings of the 10th Machine Learning for Healthcare Conference, PMLR 298, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.18303 2025-10-22 cs.CV 88%

Proactive Reasoning-with-Retrieval Framework for Medical Multimodal Large Language Models

Lehan Wang, Yi Qin, Honglong Yang, Xiaomeng Li

机构 * The Hong Kong University of Science and Technology(香港科学与技术大学)

专题命中 领域大模型 :large language model(title,abstract);language model(title,abstract)

Comments Work in progress

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.12783 2025-10-22 cs.CV 88%

Med-2E3: A 2D-Enhanced 3D Medical Multimodal Large Language Model

Yiming Shi, Xun Zhu, Kaiwen Wang, Ying Hu, Chenyi Guo, Miao Li, Ji Wu

机构 * Department of Electronic Engineering, Tsinghua University(清华大学电子工程系) College of AI, Tsinghua University(清华大学人工智能学院) Beijing National Research Center for Information Science and Technology(北京信息科学与技术国家研究中心)

专题命中 领域大模型 :large language model(title,abstract);language model(title,abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.18806 2025-10-22 cs.CY 86%

Integrating Large Language Models and Evaluating Student Outcomes in an Introductory Computer Science Course

Annapurna Vadaparty, David H. Smith, Samvrit Srinath, Mounika Padala, Christine Alvarado, Jamie Gorson Benario, Daniel Zingaro, Leo Porter

专题命中 领域大模型 :large language model(title);language model(title);LLM(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.17892 2025-10-22 cs.CL 84%

Advances in Pre-trained Language Models for Domain-Specific Text Classification: A Systematic Review

Zhyar Rzgar K. Rostam, Gábor Kertész

机构 * Doctoral School of Applied Informatics and Applied Mathematics, Obuda University(应用信息学与应用数学博士学院,奥布达大学) John von Neumann Faculty of Informatics, Obuda University(冯·诺依曼信息学学院,奥布达大学) Laboratory of Parallel and Distributed Systems, Institute for Computer Science and Control (SZTAKI), Hungarian Research Network (HUN-REN)(并行与分布式系统实验室,计算机科学与控制研究所(SZTAKI),匈牙利研究网络(HUN-REN))

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

Comments 41 pages, 10 figures, 13 tables

Journal ref Zhyar Rzgar K. Rostam and Gábor Kertész. 2025. Advances in Pre-trained Language Models for Domain-Specific Text Classification: A Systematic Review. ACM Trans. Intell. Syst. Technol. 16, 6, Article 124 (December 2025), 41 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.18475 2025-10-22 cs.CL 77%

DART: A Structured Dataset of Regulatory Drug Documents in Italian for Clinical NLP

Mariano Barone, Antonio Laudante, Giuseppe Riccio, Antonio Romano, Marco Postiglione, Vincenzo Moscato

机构 * University of Naples Federico II, Department of Electrical Engineering(那不勒斯费德里科二世大学电气工程系) Consorzio Interuniversitario Nazionale per l'Informatica (CINI) - ITEM National Lab, Complesso Universitario Monte S.Angelo, Naples, Italy(国家信息计算联合研究所(CINI)- ITEM国家实验室,那不勒斯意大利大学综合体) Northwestern University, Department of Computer Science, McCormick School of Engineering(西北大学计算机科学系,麦科姆工程学院)

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

Journal ref ITADATA 2025: 4th Italian Conference on Big Data and Data Science, Turin, Italy, September 9-11, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.18468 2025-10-22 cs.CL 77%

IMB: An Italian Medical Benchmark for Question Answering

Antonio Romano, Giuseppe Riccio, Mariano Barone, Marco Postiglione, Vincenzo Moscato

机构 * University of Naples Federico II, Department of Electrical Engineering(那不勒斯费德里科二世大学电子工程系) Consorzio Interuniversitario Nazionale per l'Informatica (CINI) - ITEM National Lab(国家信息计算联合研究中心(CINI)- ITEM国家实验室) Northwestern University, Department of Computer Science, McCormick School of Engineering(西北大学计算机科学系,工程学院)

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

Journal ref CLIC-it 2025: Eleventh Italian Conference on Computational Linguistics, Cagliari, Italy, September 24-26, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.18297 2025-10-22 cs.CL cs.AI 73%

From Retrieval to Generation: Unifying External and Parametric Knowledge for Medical Question Answering

Lei Li, Xiao Zhou, Yingying Zhang, Xian Wu

机构 * Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学北京校区人工智能学院) Tencent Jarvis Lab(腾讯 Jarvis 实验室)

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

Comments 13 pages, 4 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.17882 2025-10-22 cs.CY cs.AI cs.CL cs.DL 73%

Does GenAI Rewrite How We Write? An Empirical Study on Two-Million Preprints

Minfeng Qi, Zhongmin Cao, Qin Wang, Ningran Li, Tianqing Zhu

机构 * City University of Macau(澳门城市大学) CSIRO Data61(CSIRO数据61) The University of Adelaide(阿德莱德大学)

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
2509.01042 2025-10-22 cs.LG cs.IR 70%

MatPROV: A Provenance Graph Dataset of Material Synthesis Extracted from Scientific Literature

Hirofumi Tsuruta, Masaya Kumagai

机构 * SAKURA internet Inc.(SAKURA互联网公司) Kyoto University(京都大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2408.10111 2025-10-22 cs.AI cs.LG 62%

LENS: Large Pre-trained Transformer for Exploring Financial Time Series Regularities

Yuanjian Xu, Anxian Liu, Jianing Hao, Zhenzhuo Li, Shichang Meng, Guang Zhang

机构 * The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州)) City University of Hong Kong(香港城市大学) Peking University(北京大学)

专题命中 领域大模型 :foundation model(abstract);分类 cs.AI、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.17839 2025-10-22 cs.SE 50%

AI Exchange Platforms

Johannes Schneider, Rene Abraham

专题命中 领域大模型 :foundation model(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏

3. 知识编辑与模型理解 17 篇

2510.18476 2025-10-22 cs.AI cs.CL 86%

Probabilistic Modeling of Intentions in Socially Intelligent LLM Agents

Feifan Xia, Yuyang Fang, Defang Li, Yantong Xie, Weikang Li, Yang Li, Deguo Xia, Jizhou Huang

机构 * Baidu Inc(百度公司) Imperial College London(伦敦帝国学院) Zhejiang University(浙江大学) Carnegie Mellon University(卡内基梅隆大学) Peking University(北京大学)

专题命中 知识编辑与模型理解 :LLM(title,abstract);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
2508.09423 2025-10-22 cs.CV cs.RO 85%

Distilling LLM Prior to Flow Model for Generalizable Agent's Imagination in Object Goal Navigation

Badi Li, Ren-jie Lu, Yu Zhou, Jingke Meng, Wei-shi Zheng

机构 * Sun Yat-sen University(中山大学) The University of Hong Kong(香港大学) Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education(教育部机器智能与高级计算重点实验室)

专题命中 知识编辑与模型理解 :LLM(title,abstract);large language model(abstract);language model(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.17148 2025-10-22 cs.SE cs.AI 83%

LLM Agents for Interactive Exploration of Historical Cadastre Data: Framework and Application to Venice

Tristan Karch, Jakhongir Saydaliev, Isabella Di Lenardo, Frédéric Kaplan

机构 * DH-Lab, EPFL, Lausanne, Switzerland(DH实验室,日内瓦联邦理工学院,洛桑,瑞士)

专题命中 知识编辑与模型理解 :LLM(title);large language model(abstract);language model(abstract);分类 cs.AI

Comments Accepted in Cambridge press - Computational Humanities Research 2025

Journal ref Comput. humanit. res. 1 (2025) e11

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.17941 2025-10-22 cs.CL cs.AI 82%

Believe It or Not: How Deeply do LLMs Believe Implanted Facts?

Stewart Slocum, Julian Minder, Clément Dumas, Henry Sleight, Ryan Greenblatt, Samuel Marks, Rowan Wang

专题命中 知识编辑与模型理解 :LLM(abstract);large language model(abstract);language model(abstract);prompting(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.24262 2025-10-22 q-bio.QM cs.AI cs.LG 81%

LAMP-PRo: Label-aware Attention for Multi-label Prediction of DNA- and RNA-binding Proteins using Protein Language Models

Nimisha Ghosh, Dheeran Sankaran, Rahul Balakrishnan Adhi, Sharath S, Amrut Anand

机构 * Department of Computer Science and Engineering, Shiv Nadar University Chennai, Tamil Nadu, India(计算机科学与工程系,Shiv Nadar大学 Chennai,印度 Tamil Nadu)

专题命中 知识编辑与模型理解 :language model(title,abstract);分类 cs.AI、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏