语言大模型 / LLM

2508.01541 2025-10-30 cs.CL 70%

MOPrompt: Multi-objective Semantic Evolution for Prompt Optimization

Sara Câmara, Eduardo Luz, Valéria Carvalho, Ivan Meneghini, Gladston Moreira

机构 * Computing Department, Universidade Federal de Ouro Preto（联邦大学奥鲁普里托 computing 部门）； Federal Institute of Minas Gerais（巴西矿业高等学院）； Postgraduate Program in Computer Science, Federal University of Ouro Preto（联邦大学奥鲁普里托计算科学研究生项目）

专题命中评测与基准：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments 8 pages

2505.19028 2025-10-30 cs.CV cs.AI 70%

InfoChartQA: A Benchmark for Multimodal Question Answering on Infographic Charts

Tianchi Xie, Minzhi Lin, Mengchen Liu, Yilin Ye, Changjian Chen, Shixia Liu

专题命中评测与基准：large language model(abstract)；language model(abstract)；分类 cs.AI

2505.15063 2025-10-30 cs.CL 70%

UrduFactCheck: An Agentic Fact-Checking Framework for Urdu with Evidence Boosting and Benchmarking

Sarfraz Ahmad, Hasan Iqbal, Momina Ahsan, Numaan Naeem, Muhammad Ahsan Riaz Khan, Arham Riaz, Muhammad Arslan Manzoor, Yuxia Wang, Preslav Nakov

专题命中评测与基准：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments 15 pages, 4 figures, 5 tables, 6 Listings, Published in Proceeding of The 2025 Conference on Empirical Methods in Natural Language Processing

2503.07994 2025-10-30 astro-ph.SR astro-ph.EP astro-ph.IM cs.AI physics.space-ph 70%

A Neural Symbolic Model for Space Physics

Jie Ying, Haowei Lin, Chao Yue, Yajie Chen, Chao Xiao, Quanqi Shi, Yitao Liang, Shing-Tung Yau, Yuan Zhou, Jianzhu Ma

机构 * Qiuzhen College, Tsinghua University（清华大学求真学院）； Institute for Artificial Intelligence, Peking University（北京大学人工智能研究院）； School of Earth and Space Sciences, Peking University（北京大学地球与空间科学学院）； Max-Planck Institute for Solar System Research（马克斯·普朗克太阳系研究所）； Institute of Space Sciences, Shandong University（山东大学空间科学研究院）； Yau Mathematical Sciences Center, Tsinghua University（叶中天数学科学中心）； Beijing Institute of Mathematical Sciences and Applications（北京数学科学应用研究所）； Department of Mathematical Sciences, Tsinghua University（清华大学数学科学系）； Department of Electronic Engineering, Tsinghua University（清华大学电子工程系）； Institute for AI Industry Research, Tsinghua University（人工智能产业研究院）

专题命中评测与基准：large language model(abstract)；language model(abstract)；分类 cs.AI

2510.25612 2025-10-30 cs.AI cs.MA 57%

Counterfactual-based Agent Influence Ranker for Agentic AI Workflows

Amit Giloni, Chiara Picardi, Roy Betser, Shamik Bose, Aishvariya Priya Rathina Sabapathy, Roman Vainshtein

机构 * Fujitsu Research of Europe, UK（富士通欧洲研究中心）

专题命中评测与基准：LLM(abstract)；分类 cs.AI

Comments Accepted to EMNLP 2025, 27 pages, 6 figures

2510.25039 2025-10-30 cs.SE cs.LG 57%

Automating Benchmark Design

Amanda Dsouza, Harit Vishwakarma, Zhengyang Qi, Justin Bauer, Derek Pham, Thomas Walshe, Armin Parchami, Frederic Sala, Paroma Varma

机构 * Snorkel AI ； Dept. of Computer Sciences, University of Wisconsin-Madison（计算机科学系，威斯康星大学麦迪逊分校）

专题命中评测与基准：LLM(abstract)；分类 cs.LG

2510.25347 2025-10-30 cs.CV cs.LG 57%

3D CT-Based Coronary Calcium Assessment: A Feature-Driven Machine Learning Framework

Ayman Abaid, Gianpiero Guidone, Sara Alsubai, Foziyah Alquahtani, Talha Iqbal, Ruth Sharif, Hesham Elzomor, Emiliano Bianchini, Naeif Almagal, Michael G. Madden, Faisal Sharif, Ihsan Ullah

机构 * Visual Intelligence Lab, School of Computer Science, University of Galway, Ireland（加拉维大学计算机科学学院视觉智能实验室）； Data Science Institute, University of Galway, Ireland（加拉维大学数据科学研究所）； Sharif Cardiovascular Research Group, University of Galway, Ireland（加拉维大学沙里夫心血管研究组）； Department of Cardiology, Galway University Hospital, Galway, Ireland（加拉维大学医院心内科部门）； CRFG, University of Galway, Galway, Ireland（加拉维大学CRFG研究中心）； CURAM, University of Galway, Galway, Ireland（加拉维大学CURAM研究中心）； Cardiology Department, NEOM Hospital, Saudi Arabia（沙特NEOM医院心内科部门）

专题命中评测与基准：foundation model(abstract)；分类 cs.LG

Comments 11 pages, 2 Figures, MICCAI AMAI 2025 workshop, to be published in Volume 16206 of the Lecture Notes in Computer Science series

2507.22811 2025-10-30 cs.CL 57%

DBLPLink 2.0 -- An Entity Linker for the DBLP Scholarly Knowledge Graph

Debayan Banerjee, Tilahun Abedissa Taffa, Ricardo Usbeck

机构 * Leuphana University of Lüneburg, Lüneburg, Germany（吕贝克大学）； University of Hamburg, Hamburg, Germany（汉堡大学）

专题命中评测与基准：LLM(abstract)；分类 cs.CL

2506.14866 2025-10-30 cs.SE cs.LG 57%

OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents

Thomas Kuntz, Agatha Duzan, Hao Zhao, Francesco Croce, Zico Kolter, Nicolas Flammarion, Maksym Andriushchenko

机构 * EPFL（苏黎世联邦理工学院）； Carnegie Mellon University（卡内基梅隆大学）

专题命中评测与基准：LLM(abstract)；分类 cs.LG

Comments NeurIPS 2025 Datasets & Benchmarks Track (Spotlight)

2412.15189 2025-10-30 cs.CL cs.CY 57%

Face the Facts! Evaluating RAG-based Pipelines for Professional Fact-Checking

Daniel Russo, Stefano Menini, Jacopo Staiano, Marco Guerini

机构 * Fondazione Bruno Kessler（布罗诺·凯塞勒基金会）； University of Trento（特伦托大学）

专题命中评测与基准：LLM(abstract)；分类 cs.CL

Comments Code and data at https://github.com/drusso98/face-the-facts - Accepted for publication at INLG 2025

2510.25713 2025-10-30 cs.RO 50%

Robotic Assistant: Completing Collaborative Tasks with Dexterous Vision-Language-Action Models

Boshi An, Chenyu Yang, Robert Katzschmann

机构 * Soft Robotics Lab, ETHz, Switzerland（苏黎世联邦理工学院软机器人实验室）

专题命中评测与基准：prompting(abstract)

2510.25094 2025-10-30 cs.CV 50%

Visual Diversity and Region-aware Prompt Learning for Zero-shot HOI Detection

Chanhyeong Yang, Taehoon Song, Jihwan Park, Hyunwoo J. Kim

机构 * Korea University（韩国大学）； Korea Advanced Institute of Science and Technology（韩国科学技术院）

专题命中评测与基准：language model(abstract)

Comments Accepted by NeurIPS 2025

2507.17326 2025-10-30 cs.SD eess.AS 50%

Application of Whisper in Clinical Practice: the Post-Stroke Speech Assessment during a Naming Task

Milena Davudova, Ziyuan Cai, Valentina Giunchiglia, Dragos C. Gruia, Giulia Sanguedolce, Adam Hampshire, Fatemeh Geranmayeh

机构 * Department of Neuroimaging, King’s College London, UK（伦敦国王学院神经影像部门）； Department of Brain Sciences, Imperial College London, UK（伦敦帝国学院脑科学部门）

专题命中评测与基准：foundation model(abstract)

2506.06677 2025-10-30 cs.RO cs.CV 50%

RoboCerebra: A Large-scale Benchmark for Long-horizon Robotic Manipulation Evaluation

Songhao Han, Boxiang Qiu, Yue Liao, Siyuan Huang, Chen Gao, Shuicheng Yan, Si Liu

机构 * Beihang University（北航大学）； National University of Singapore（新加坡国立大学）； Shanghai Jiao Tong University（上海交通大学）

专题命中评测与基准：language model(abstract)

Comments 25 pages, 18 figures, Accepted by NeurIPS 2025

2510.01225 2025-10-30 cs.CE cs.AI cs.CL cs.SE 92%

Utilizing Modern Large Language Models (LLM) for Financial Trend Analysis and Digest Creation

Andrei Lazarev, Dmitrii Sedov

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

Comments This is the version of the article accepted for publication in SUMMA 2024 after peer review. The final, published version is available at IEEE Xplore: 10.1109/SUMMA64428.2024.10803746

Journal ref 2024 6th International Conference on Control Systems, Mathematical Modeling, Automation and Energy Efficiency (SUMMA), Lipetsk, Russian Federation, 2024, pp. 317-321

2410.14257 2025-10-30 cs.LG cs.AI 90%

Revisiting Service Level Objectives and System Level Metrics in Large Language Model Serving

Zhibin Wang, Shipeng Li, Yuhang Zhou, Xue Li, Zhonghui Zhang, Nguyen Cam-Tu, Rong Gu, Chen Tian, Guihai Chen, Sheng Zhong

机构 * State Key Laboratory for Novel Software Technology, Nanjing University（新型软件技术国家重点实验室，南京大学）； Alibaba Group（阿里巴巴集团）

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

2504.14872 2025-10-30 cs.SE 88%

Efficient Function Orchestration for Large Language Models

Xiaoxia Liu, Peng Di, Cong Li, Jun Sun, Jingyi Wang

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

Comments Accepted for publication in IEEE Transactions on Software Engineering (TSE), 2025

2509.19902 2025-10-30 cs.CL 85%

WEST: LLM based Speech Toolkit for Speech Understanding, Generation, and Interaction

Binbin Zhang, Chengdong Liang, Shuai Wang, Xuelong Geng, Zhao Guo, Haoyu Li, Hao Yin, Xipeng Yang, Pengshen Zhang, Changwei Ma, Lei Xie

机构 * Northwestern Polytechnical University（西北工业大学）； Nanjing University（南京大学）； Shanghai Jiao Tong University（上海交通大学）； GuaSemi Speech A Team（GuaSemi语音团队）； WeNet Community（WeNet社区）

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

2506.15721 2025-10-30 cs.LG 85%

Bohdi: Heterogeneous LLM Fusion with Automatic Data Exploration

Junqi Gao, Zhichang Guo, Dazhi Zhang, Dong Li, Runze Liu, Pengfei Li, Kai Tian, Biqing Qi

机构 * School of Mathematics, Harbin Institute of Technology（哈尔滨工业大学数学学院）； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）； Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）； Department of Electronic Engineering, Tsinghua University（清华大学电子工程系）； Shanghai Innovation Institute（上海创新研究院）

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

Comments Accepted by NeurIPS2025

2510.25297 2025-10-30 cs.SE 85%

Understanding the Characteristics of LLM-Generated Property-Based Tests in Exploring Edge Cases

Hidetake Tanaka, Haruto Tanaka, Kazumasa Shimari, Kenichi Matsumoto

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

Comments Accepted for publication in 2nd IEEE/ACM international conference on AI-powered Software (AIware 2025) : 8 pages, 1 table, 8 figures

2510.25017 2025-10-30 cs.DB cs.AI cs.CL 81%

StorageXTuner: An LLM Agent-Driven Automatic Tuning Framework for Heterogeneous Storage Systems

Qi Lin, Zhenyu Zhang, Viraj Thakkar, Zhenjie Sun, Mai Zheng, Zhichao Cao

机构 * Arizona State University（亚利桑那州立大学）； Iowa State University（爱荷华州立大学）

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

Comments ArXiv version; Affiliations: Arizona State University (Lin, Zhang, Thakkar, Sun, Cao) and Iowa State University (Zheng)

2510.25257 2025-10-30 cs.CV 78%

RT-DETRv4: Painlessly Furthering Real-Time Object Detection with Vision Foundation Models

Zijun Liao, Yian Zhao, Xin Shan, Yu Yan, Chang Liu, Lei Lu, Xiangyang Ji, Jie Chen

机构 * School of Electronic and Computer Engineering, Peking University, Shenzhen, China（北京大学电子与计算机工程学院，深圳，中国）； Department of Automation and BNRist, Tsinghua University, Beijing, China（清华大学自动化系及BNRist，北京，中国）

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

2510.25412 2025-10-30 cs.CL 77%

Serve Programs, Not Prompts

In Gim, Lin Zhong

机构 * Yale University（耶鲁大学）

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

Comments HotOS 2025. Follow-up implementation work (SOSP 2025) is available at arXiv:2510.24051

2507.00418 2025-10-30 cs.DC cs.AI 77%

Serving LLMs in HPC Clusters: A Comparative Study of Qualcomm Cloud AI 100 Ultra and NVIDIA Data Center GPUs

Mohammad Firas Sada, John J. Graham, Elham E Khoda, Mahidhar Tatineni, Dmitry Mishin, Rajesh K. Gupta, Rick Wagner, Larry Smarr, Thomas A. DeFanti, Frank Würthwein

机构 * University of California, San Diego（加州大学圣地亚哥分校）

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

Comments 8 pages, 3 tables

2510.24999 2025-10-30 cs.CR 75%

SLIP-SEC: Formalizing Secure Protocols for Model IP Protection

Racchit Jain, Satya Lokam, Yehonathan Refael, Adam Hakim, Lev Greenberg, Jay Tenenbaum

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

2507.06204 2025-10-30 cs.LG cs.AI cs.CL 75%

Differential Mamba

Nadav Schneider, Itamar Zimerman, Eliya Nachmani

机构 * School of Electrical and Computer Engineering, Ben-Gurion University of the Negev（电气与计算机工程学院，内盖夫本· Gurion大学）； IAEC ； Tel-Aviv University（特拉维夫大学）； IBM Research（IBM研究院）

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

Comments AACL 2025. We provide the code at https://github.com/NadavSc/Diff-Mamba

2510.25602 2025-10-30 cs.LG cs.AI 73%

INT v.s. FP: A Comprehensive Study of Fine-Grained Low-bit Quantization Formats

Mengzhao Chen, Meng Wu, Hui Jin, Zhihang Yuan, Jing Liu, Chaoyi Zhang, Yunshui Li, Jie Huang, Jin Ma, Zeyue Xue, Zhiheng Liu, Xingyan Bin, Ping Luo

机构 * The University of Hong Kong（香港大学）

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

2402.16714 2025-10-30 quant-ph cs.AI cs.CL 73%

Quantum Transformer: Accelerating model inference via quantum linear algebra

Naixu Guo, Zhan Yu, Matthew Choi, Yizhan Han, Aman Agrawal, Kouhei Nakaji, Alán Aspuru-Guzik, Patrick Rebentrost

机构 * Centre for Quantum Technologies, National University of Singapore（新加坡国立大学量子技术中心）； Department of Computer Science, University of Toronto（多伦多大学计算机科学系）； Vector Institute for Artificial Intelligence（人工智能向量研究所）； School of Computing, National University of Singapore（新加坡国立大学计算机学院）； Department of Mathematics, National University of Singapore（新加坡国立大学数学系）； NVIDIA Corporation（NVIDIA公司）； Department of Chemistry, University of Toronto（多伦多大学化学系）； Research Center for Emerging Computing Technologies, National Institute of Advanced Industrial Science and Technology (AIST)（新兴计算技术研究中心，日本国家先进工业科学与技术研究院）； Quantum Computing Center, Keio University（Keio大学量子计算中心）； Department of Materials Science & Engineering, University of Toronto（多伦多大学材料科学与工程系）； Department of Chemical Engineering & Applied Chemistry, University of Toronto（多伦多大学化学工程与应用化学系）； Lebovic Fellow, Canadian Institute for Advanced Research（加拿大高级研究研究院Lebovic研究员）

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

Comments 45 pages

2510.23323 2025-10-30 cs.LG cs.NE 70%

Towards Scaling Deep Neural Networks with Predictive Coding: Theory and Practice

Francesco Innocenti

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

Comments PhD thesis

2510.25150 2025-10-30 cs.CL 70%

Explainable Disentanglement on Discrete Speech Representations for Noise-Robust ASR

Shreyas Gopal, Ashutosh Anshul, Haoyang Li, Yue Heng Yeo, Hexin Liu, Eng Siong Chng

机构 * College of Computing and Data Science, Nanyang Technological University（计算与数据科学学院，南洋理工大学）

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

Comments Awarded Best Student Paper at APSIPA ASC 2025

1. 评测与基准 43 篇