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。

2025-08-15 至 2025-08-15 共收录 174 信号源:cs.CL, cs.AI, cs.LG

1. 效率与部署 22 篇

2508.08895 2025-08-15 cs.CL cs.AI 79%

ASPD: Unlocking Adaptive Serial-Parallel Decoding by Exploring Intrinsic Parallelism in LLMs

Keyu Chen, Zhifeng Shen, Daohai Yu, Haoqian Wu, Wei Wen, Jianfeng He, Ruizhi Qiao, Xing Sun

机构 * Youtu Team(你Tube团队)

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

Comments 20 pages, 9 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.14976 2025-08-15 cs.CV 78%

Hierarchical Cross-modal Prompt Learning for Vision-Language Models

Hao Zheng, Shunzhi Yang, Zhuoxin He, Jinfeng Yang, Zhenhua Huang

机构 * South China Normal University(华南师范大学) Shenzhen Polytechnic University(深圳职业技术大学)

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

Comments Accepted by ICCV2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.10874 2025-08-15 cs.CL 77%

SSRL: Self-Search Reinforcement Learning

Yuchen Fan, Kaiyan Zhang, Heng Zhou, Yuxin Zuo, Yanxu Chen, Yu Fu, Xinwei Long, Xuekai Zhu, Che Jiang, Yuchen Zhang, Li Kang, Gang Chen, Cheng Huang, Zhizhou He, Bingning Wang, Lei Bai, Ning Ding, Bowen Zhou

机构 * Tsinghua University(清华大学) Shanghai Jiao Tong University(上海交通大学) Shanghai AI Laboratory(上海人工智能实验室) University College London(伦敦大学学院) CSCEC Third Bureau(中建第三工程局) WeChat AI(微信AI)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.10012 2025-08-15 cs.CL 77%

Guided Navigation in Knowledge-Dense Environments: Structured Semantic Exploration with Guidance Graphs

Dehao Tao, Guangjie Liu, Weizheng, Yongfeng Huang, Minghu jiang

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.01701 2025-08-15 cs.CV cs.AI 77%

Data Pruning by Information Maximization

Haoru Tan, Sitong Wu, Wei Huang, Shizhen Zhao, Xiaojuan Qi

机构 * The University of Hong Kong(香港大学) The Chinese University of Hong Kong(香港中文大学)

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

Comments Code is available at \url{https://github.com/hrtan/InfoMax}

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.22267 2025-08-15 cs.DC 75%

From Data Center IoT Telemetry to Data Analytics Chatbots -- Virtual Knowledge Graph is All You Need

Junaid Ahmed Khan, Hiari Pizzini Cavagna, Andrea Proia, Andrea Bartolini

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

Comments 12 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.01618 2025-08-15 cs.LG cs.AI 73%

Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods

Isha Puri, Shivchander Sudalairaj, Guangxuan Xu, Kai Xu, Akash Srivastava

机构 * MIT CSAIL(麻省理工学院计算机科学与人工智能实验室) RedHat AI Innovation(红帽人工智能创新)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.07837 2025-08-15 cs.LG 70%

FRUGAL: Memory-Efficient Optimization by Reducing State Overhead for Scalable Training

Philip Zmushko, Aleksandr Beznosikov, Martin Takáč, Samuel Horváth

机构 * Moscow Institute of Physics and Technology, Russia(莫斯科物理技术学院) Ivannikov Institute for System Programming RAS, Russia(伊万诺夫系统编程研究所) Skolkovo Institute of Science and Technology, Russia(斯克尔罗沃科学与技术研究所) Mohamed bin Zayed University of Artificial Intelligence, UAE(穆罕默德·本·扎耶德人工智能大学)

专题命中 效率与部署 :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
2508.10366 2025-08-15 cs.CL 70%

Advancing Cross-lingual Aspect-Based Sentiment Analysis with LLMs and Constrained Decoding for Sequence-to-Sequence Models

Jakub Šmíd, Pavel Přibáň, Pavel Král

机构 * Department of Computer Science and Engineering, University of West Bohemia in Pilsen(计算机科学与工程系,西波赫大学)

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

Comments Published in Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2 (ICAART 2025). Official version: https://www.scitepress.org/Link.aspx?doi=10.5220/0013349400003890

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.09626 2025-08-15 cs.CV 50%

Semantic-aware DropSplat: Adaptive Pruning of Redundant Gaussians for 3D Aerial-View Segmentation

Xu Tang, Junan Jia, Yijing Wang, Jingjing Ma, Xiangrong Zhang

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

Comments 9 pages, 4 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.06818 2025-08-15 cs.CV 50%

Stepwise Decomposition and Dual-stream Focus: A Novel Approach for Training-free Camouflaged Object Segmentation

Chao Yin, Hao Li, Kequan Yang, Jide Li, Pinpin Zhu, Xiaoqiang Li

机构 * Shanghai University(上海大学) University of the Chinese Academy of Sciences(中国科学院大学)

专题命中 效率与部署 :prompting(abstract)

Comments accepted by ACM MM2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.08561 2025-08-15 cs.CV 50%

Reinforcement Learning meets Masked Video Modeling : Trajectory-Guided Adaptive Token Selection

Ayush K. Rai, Kyle Min, Tarun Krishna, Feiyan Hu, Alan F. Smeaton, Noel E. O'Connor

机构 * Insight Research Ireland Centre for Data Analytics, Dublin City University(爱尔兰洞察研究机构数据分析中心、都柏林城市大学) Intel Labs, USA(美国英特尔实验室)

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

Comments Accepted in ICCVW 2025 - Long Multi-Scene Video Foundations Workshop

详情

展开后加载摘要…

URL PDF HTML 收藏

2. 领域大模型 16 篇

2508.10492 2025-08-15 cs.AI cs.CE cs.CL 90%

Reverse Physician-AI Relationship: Full-process Clinical Diagnosis Driven by a Large Language Model

Shicheng Xu, Xin Huang, Zihao Wei, Liang Pang, Huawei Shen, Xueqi Cheng

机构 * State Key Laboratory of AI Safety, Institute of Computing Technology, CAS(人工智能安全国家重点实验室,计算技术研究所,中国科学院) University of Chinese Academy of Sciences(中国科学院大学) Peking University Third Hospital(北京大学第三医院)

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

Comments 39 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.17402 2025-08-15 cs.AI 89%

Assessing the Capability of Large Language Models for Domain-Specific Ontology Generation

Anna Sofia Lippolis, Mohammad Javad Saeedizade, Robin Keskisarkka, Aldo Gangemi, Eva Blomqvist, Andrea Giovanni Nuzzolese

机构 * University of Bologna, Italy(博洛尼亚大学,意大利) ISTC-CNR, Italy(ISTC-意大利国家研究理事会) Linköping University, Sweden(林雪平大学,瑞典)

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

Journal ref Joint Proc. ESWC 2025 Workshops and Tutorials, CEUR-WS, Vol. 3977, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2403.18405 2025-08-15 cs.AI cs.IR 88%

Leveraging Large Language Models for Relevance Judgments in Legal Case Retrieval

Shengjie Ma, Qi Chu, Jiaxin Mao, Xuhui Jiang, Haozhe Duan, Chong Chen

机构 * Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学耿丽人工智能学院) Beijing Normal University(北京师范大学) DataArc Tech Ltd.(数据弧科技有限公司) Huawei Cloud BU(华为云业务单元)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.10010 2025-08-15 cs.CL 85%

An Audit and Analysis of LLM-Assisted Health Misinformation Jailbreaks Against LLMs

Ayana Hussain, Patrick Zhao, Nicholas Vincent

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2409.14572 2025-08-15 cs.CL cond-mat.mtrl-sci cs.AI cs.LG 80%

Evaluating the Performance and Robustness of LLMs in Materials Science Q&A and Property Predictions

Hongchen Wang, Kangming Li, Scott Ramsay, Yao Fehlis, Edward Kim, Jason Hattrick-Simpers

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.10216 2025-08-15 cs.CE 78%

CarAT: Carbon Atom Tracing across Industrial Chemical Value Chains via Chemistry Language Models

Emma Pajak, David Walz, Olga Walz, Laura Marie Helleckes, Klaus Hellgardt, Antonio del Rio Chanona

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

Comments 21 pages, 9 figures, pre-print

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.10013 2025-08-15 cs.CL 77%

Semantic Bridge: Universal Multi-Hop Question Generation via AMR-Driven Graph Synthesis

Linqing Chen, Hanmeng Zhong, Wentao Wu, Weilei Wang

机构 * Linqing Chen, Hanmeng Zhong, Wentao Wu, Weilei Wang(作者)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.09995 2025-08-15 q-bio.BM cs.ET cs.LG 77%

zERExtractor:An Automated Platform for Enzyme-Catalyzed Reaction Data Extraction from Scientific Literature

Rui Zhou, Haohui Ma, Tianle Xin, Lixin Zou, Qiuyue Hu, Hongxi Cheng, Mingzhi Lin, Jingjing Guo, Sheng Wang, Guoqing Zhang, Yanjie Wei, Liangzhen Zheng

机构 * Shenzhen Institutes of Advanced Technology(深圳先进技术研究院) Chinese Academy of Sciences(中国科学院) University of Chinese Academy of Sciences(中国科学院大学) Shanghai Zelixir Biotech Co.,Ltd.(上海泽立生物技术有限公司) Bio-Med Big Data Center, Shanghai Institute of Nutrition and Health, University of Chinese Academy of Sciences, Chinese Academy of Science(生物医学大数据中心,上海营养健康研究所,中国科学院) Shenzhen Zelixir Biotech Co., Ltd.(深圳泽立生物技术有限公司) Centre in Artificial Intelligence Driven Drug Discovery, Faculty of Applied Sciences, Macao Polytechnic University(人工智能驱动药物发现中心,应用科学学院,澳门理工大学) National Genomics Data Center, Shanghai Institute of Nutrition and Health, University of Chinese Academy of Sciences, Chinese Academy of Science(国家基因组科学数据中心,上海营养健康研究所,中国科学院)

专题命中 领域大模型 :LLM(abstract);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
2508.10455 2025-08-15 cs.LG cs.AI 73%

RealAC: A Domain-Agnostic Framework for Realistic and Actionable Counterfactual Explanations

Asiful Arefeen, Shovito Barua Soumma, Hassan Ghasemzadeh

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.14189 2025-08-15 cs.CL cs.AI 73%

DeepWriter: A Fact-Grounded Multimodal Writing Assistant Based On Offline Knowledge Base

Song Mao, Lejun Cheng, Pinlong Cai, Guohang Yan, Ding Wang, Botian Shi

机构 * Shanghai AI LAB(上海人工智能实验室)

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

Comments work in process

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.10478 2025-08-15 cs.IR 67%

Semantic IDs for Joint Generative Search and Recommendation

Gustavo Penha, Edoardo D'Amico, Marco De Nadai, Enrico Palumbo, Alexandre Tamborrino, Ali Vardasbi, Max Lefarov, Shawn Lin, Timothy Heath, Francesco Fabbri, Hugues Bouchard

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

Comments Accepted for publication in the 19th ACM Conference on Recommender Systems (RecSys 2025), Late-Breaking Results track

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.05519 2025-08-15 cs.CV 67%

Leveraging AI to Accelerate Medical Data Cleaning: A Comparative Study of AI-Assisted vs. Traditional Methods

Matthew Purri, Amit Patel, Erik Deurrell

机构 * Octozi

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.10461 2025-08-15 cs.LG cs.AI 62%

X-Node: Self-Explanation is All We Need

Prajit Sengupta, Islem Rekik

机构 * BASIRA Lab, Imperial-X (I-X)(BASIRA实验室,Imperial-X(I-X)) Department of Computing, Imperial College London, London, United Kingdom(计算系,伦敦帝国学院,伦敦,英国)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.10033 2025-08-15 cs.CR cs.AI 57%

Cognitive Cybersecurity for Artificial Intelligence: Guardrail Engineering with CCS-7

Yuksel Aydin

机构 * Independent Researcher(独立研究者)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.05977 2025-08-15 cs.LG physics.flu-dyn 57%

LinguaFluid: Language Guided Fluid Control via Semantic Rewards in Reinforcement Learning

Aoming Liang, Chi Cheng, Dashuai Chen, Boai Sun, Dixia Fan

机构 * College of Environmental and Resource Sciences, Zhejiang University, Hangzhou, China(浙江大学环境与资源学院) School of Engineering, Westlake University, Hangzhou, China(西湖大学工程学院)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.10897 2025-08-15 cs.CV 50%

Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning

Mengyuan Liu, Xinshun Wang, Zhongbin Fang, Deheng Ye, Xia Li, Tao Tang, Songtao Wu, Xiangtai Li, Ming-Hsuan Yang

机构 * National Key Laboratory of General Artificial Intelligence, Peking University, Shenzhen Graduate School(国家通用人工智能重点实验室,北京大学深圳研究生院) Tencent, China(腾讯(中国)) Department of Information Technology and Electrical Engineering, ETH Zurich(信息科技与电子工程系,苏黎世联邦理工学院) S-Lab, Nanyang Technological University, Singapore(南洋理工大学新加坡分校S实验室) Sony R&D Center, China(索尼研发中心(中国)) University of California at Merced, US(加州大学默塞德分校)

专题命中 领域大模型 :prompting(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 8 篇

2508.10192 2025-08-15 cs.CL cs.AI cs.LG q-fin.CP 90%

Prompt-Response Semantic Divergence Metrics for Faithfulness Hallucination and Misalignment Detection in Large Language Models

Igor Halperin

机构 * Fidelity Investments(fidelity投资公司)

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

Comments 24 pages, 3 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.08329 2025-08-15 cs.AI cs.CL cs.LG 88%

MedRep: Medical Concept Representation for General Electronic Health Record Foundation Models

Junmo Kim, Namkyeong Lee, Jiwon Kim, Kwangsoo Kim

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

Comments 18 pages

详情

展开后加载摘要…

URL PDF HTML 收藏