语言大模型 / LLM

2508.13180 2025-08-20 cs.AI cs.LG 62%

Search-Time Data Contamination

Ziwen Han, Meher Mankikar, Julian Michael, Zifan Wang

机构 * Scale AI

专题命中评测与基准：LLM(abstract)；分类 cs.AI、cs.LG

2508.13428 2025-08-20 cs.CV cs.AI cs.MM 57%

Mitigating Easy Option Bias in Multiple-Choice Question Answering

Hao Zhang, Chen Li, Basura Fernando

机构 * Institute of High-Performance Computing, Agency for Science, Technology and Research, Singapore（高性能计算研究所，科学、技术及研究局，新加坡）； Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore（前沿人工智能研究中心，科学、技术及研究局，新加坡）； College of Computing and Data Science, Nanyang Technological University, Singapore（计算与数据科学学院，南洋理工大学，新加坡）

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

Comments Under review

2506.20988 2025-08-20 cs.CV cs.AI 57%

Segment Anything in Pathology Images with Natural Language

Zhixuan Chen, Junlin Hou, Liqi Lin, Yihui Wang, Yequan Bie, Xi Wang, Yanning Zhou, Ronald Cheong Kin Chan, Hao Chen

机构 * Department of Computer Science and Engineering（计算机科学与工程系）； The Hong Kong University of Science and Technology（香港科学与技术大学）； School of Electronic Engineering and Information Science（电子工程与信息科学学院）； University of Science and Technology of China（中国科学技术大学）； The Chinese University of Hong Kong（香港中文大学）； Tencent AI Platform Department（腾讯人工智能平台部门）； Department of Anatomical and Cellular Pathology（解剖与细胞病理学部）； Department of Chemical and Biological Engineering（化学与生物工程系）； Division of Life Science（生命科学系）； HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute（香港科技大学深圳-香港协同创新研究院）； State Key Laboratory of Nervous System Disorders（神经系统疾病国家重点实验室）

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

2310.01642 2025-08-20 cs.SE cs.AI 57%

"I see models being a whole other thing": An Empirical Study of Pre-Trained Model Naming Conventions and A Tool for Enhancing Naming Consistency

Wenxin Jiang, Mingyu Kim, Chingwo Cheung, Heesoo Kim, George K. Thiruvathukal, James C. Davis

机构 * Purdue University（普渡大学）； Loyola University Chicago（芝加哥洛约拉大学）

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

Comments Published at EMSE'25

Journal ref Empirical Software Engineering 30, 155 (2025)

2210.12958 2025-08-20 cs.CL 57%

Composition, Attention, or Both?

Ryo Yoshida, Yohei Oseki

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

Comments Accepted by Findings of EMNLP 2022

2508.13223 2025-08-20 cs.CV cs.AI 57%

MIRAGE: Towards AI-Generated Image Detection in the Wild

Cheng Xia, Manxi Lin, Jiexiang Tan, Xiaoxiong Du, Yang Qiu, Junjun Zheng, Xiangheng Kong, Yuning Jiang, Bo Zheng

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

2508.13936 2025-08-20 eess.IV cs.CV 50%

MMIS-Net for Retinal Fluid Segmentation and Detection

Nchongmaje Ndipenocha, Alina Mirona, Kezhi Wanga, Yongmin Li

机构 * Brunel University London（布鲁内尔大学伦敦分校）

专题命中评测与基准：foundation model(abstract)

2508.13713 2025-08-20 cs.CV 50%

Hierarchical Vision-Language Retrieval of Educational Metaverse Content in Agriculture

Ali Abdari, Alex Falcon, Giuseppe Serra

机构 * University of Udine（乌迪大学）； University of Naples Federico II（那不勒斯费德里科二世大学）

专题命中评测与基准：language model(abstract)

Comments Accepted for publication at the 23rd International Conference on Image Analysis and Processing (ICIAP 2025)

2507.14647 2025-08-20 cs.SD eess.AS 50%

Multi-Sampling-Frequency Naturalness MOS Prediction Using Self-Supervised Learning Model with Sampling-Frequency-Independent Layer

Go Nishikawa, Wataru Nakata, Yuki Saito, Kanami Imamura, Hiroshi Saruwatari, Tomohiko Nakamura

机构 * The University of Tokyo, Japan（东京大学）； National Institute of Advanced Industrial Science（国家工业科学与技术研究院）

专题命中评测与基准：pretraining(abstract)

Comments 4 pages, 2 figures; Accepted to ASRU 2025 Challenge track

2501.05985 2025-08-20 cs.HC cs.CY 50%

Exploring LLMs for Automated Generation and Adaptation of Questionnaires

Divya Mani Adhikari, Alexander Hartland, Ingmar Weber, Vikram Kamath Cannanure

专题命中评测与基准：LLM(abstract)

Comments Published in the Proceedings of the 7th ACM Conference on Conversational User Interfaces (CUI '25)

2501.04678 2025-08-20 eess.IV cs.CV 50%

RadGPT: Constructing 3D Image-Text Tumor Datasets

Pedro R. A. S. Bassi, Mehmet Can Yavuz, Kang Wang, Xiaoxi Chen, Wenxuan Li, Sergio Decherchi, Andrea Cavalli, Yang Yang, Alan Yuille, Zongwei Zhou

机构 * Johns Hopkins University（约翰霍普金斯大学）； University of Bologna（博洛尼亚大学）； Italian Institute of Technology（意大利理工学院）； University of California, San Francisco（加州大学旧金山分校）； Istanbul Medipol University（伊斯坦布尔Medipol大学）； University of Zurich（苏黎世大学）； ETH AI Center（ETH人工智能中心）； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）； École Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）

专题命中评测与基准：language model(abstract)

2508.13881 2025-08-20 cs.RO 89%

Driving Style Recognition Like an Expert Using Semantic Privileged Information from Large Language Models

Zhaokun Chen, Chaopeng Zhang, Xiaohan Li, Wenshuo Wang, Gentiane Venture, Junqiang Xi

机构 * School of Mechanical Engineering, Beijing Institute of Technology（北京理工大学机械工程学院）； Division of Energy-Mobility Convergence, Beijing Institute of Technology（北京理工大学能源-移动融合 division）； Department of Mechanical Engineering, The University of Tokyo（东京大学机械工程系）

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

2508.14025 2025-08-20 cs.CL cs.AI 88%

Ask Good Questions for Large Language Models

Qi Wu, Zhongqi Lu

机构 * College of Artificial Intelligence, China University of Petroleum-Beijing, China（人工智能学院，中国石油大学（北京））； Hainan Institute of China University of Petroleum (Beijing), Sanya, Hainan, China（海南中国石油大学（北京）研究院，三亚，海南）

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

2508.13167 2025-08-20 cs.AI cs.CL 88%

Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL

Weizhen Li, Jianbo Lin, Zhuosong Jiang, Jingyi Cao, Xinpeng Liu, Jiayu Zhang, Zhenqiang Huang, Qianben Chen, Weichen Sun, Qiexiang Wang, Hongxuan Lu, Tianrui Qin, Chenghao Zhu, Yi Yao, Shuying Fan, Xiaowan Li, Tiannan Wang, Pai Liu, King Zhu, He Zhu, Dingfeng Shi, Piaohong Wang, Yeyi Guan, Xiangru Tang, Minghao Liu, Yuchen Eleanor Jiang, Jian Yang, Jiaheng Liu, Ge Zhang, Wangchunshu Zhou

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

Comments 51 pages

2508.13439 2025-08-20 cs.CV cs.AI cs.CL eess.IV 84%

Structured Prompting and Multi-Agent Knowledge Distillation for Traffic Video Interpretation and Risk Inference

Yunxiang Yang, Ningning Xu, Jidong J. Yang

机构 * Smart Mobility and Infrastructure Lab（智能移动与基础设施实验室）； College of Engineering, University of Georgia（工程学院，佐治亚大学）

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

Comments 16 pages, 10 figures, 1 table

2508.13470 2025-08-20 cs.CV cs.AI 79%

STER-VLM: Spatio-Temporal With Enhanced Reference Vision-Language Models

Tinh-Anh Nguyen-Nhu, Triet Dao Hoang Minh, Dat To-Thanh, Phuc Le-Gia, Tuan Vo-Lan, Tien-Huy Nguyen

机构 * Ho Chi Minh University of Technology（胡志明理工大学）； Vietnamese-German University（越德大学）； Ho Chi Minh University of Science（胡志明理工大学）； University of Information Technology（信息科技大学）； Vietnam National University, Ho Chi Minh city（越南国家大学，胡志明市）

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

Comments ICCV Workshop 2025

2402.12691 2025-08-20 cs.CL 79%

Tree-Planted Transformers: Unidirectional Transformer Language Models with Implicit Syntactic Supervision

Ryo Yoshida, Taiga Someya, Yohei Oseki

机构 * The University of Tokyo（东京大学）

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

Comments Accepted by ACL 2024 (Findings)

2508.09288 2025-08-20 cs.CR cs.AI cs.CL 79%

Can AI Keep a Secret? Contextual Integrity Verification: A Provable Security Architecture for LLMs

Aayush Gupta

机构 * Aayush Gupta（独立研究者）

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 2 figures, 3 tables; code and certification harness: https://github.com/ayushgupta4897/Contextual-Integrity-Verification ; Elite-Attack dataset: https://huggingface.co/datasets/zyushg/elite-attack

2508.13191 2025-08-20 q-bio.GN 75%

NucEL: Single-Nucleotide ELECTRA-Style Genomic Pre-training for Efficient and Interpretable Representations

Ke Ding, Brian Parker, Jiayu Wen

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

2503.08549 2025-08-20 cs.AI cs.CL 73%

GoAI: Enhancing AI Students' Learning Paths and Idea Generation via Graph of AI Ideas

Xian Gao, Zongyun Zhang, Ting Liu, Yuzhuo Fu

机构 * Shanghai Jiao Tong University（上海交通大学）

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

Comments Work in progress

2505.09902 2025-08-20 cs.CL 70%

Crossing Borders Without Crossing Boundaries: How Sociolinguistic Awareness Can Optimize User Engagement with Localized Spanish AI Models Across Hispanophone Countries

Martin Capdevila, Esteban Villa Turek, Ellen Karina Chumbe Fernandez, Luis Felipe Polo Galvez, Andrea Marroquin, Rebeca Vargas Quesada, Johanna Crew, Nicole Vallejo Galarraga, Christopher Rodriguez, Diego Gutierrez, Radhi Datla

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

2508.13460 2025-08-20 cs.CV 67%

Revisiting MLLM Token Technology through the Lens of Classical Visual Coding

Jinming Liu, Junyan Lin, Yuntao Wei, Kele Shao, Keda Tao, Jianguo Huang, Xudong Yang, Zhibo Chen, Huan Wang, Xin Jin

机构 * Eastern Institute of Technology, Ningbo, China（东部技术研究所）； Westlake University（西湖大学）； USTC（中国科学技术大学）

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

2508.13390 2025-08-20 cs.IR 67%

FLAIR: Feedback Learning for Adaptive Information Retrieval

William Zhang, Yiwen Zhu, Yunlei Lu, Mathieu Demarne, Wenjing Wang, Kai Deng, Nutan Sahoo, Katherine Lin, Miso Cilimdzic, Subru Krishnan

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

Comments Accepted to CIKM2025

2508.07571 2025-08-20 cs.LG cs.AI 62%

Towards Theoretical Understanding of Transformer Test-Time Computing: Investigation on In-Context Linear Regression

Xingwu Chen, Miao Lu, Beining Wu, Difan Zou

机构 * Department of XXX, University of YYY, Location, Country（XXX系，YYY大学，地点，国家）； School of ZZZ, Institute of WWW, Location, Country（ZZZ学院，WWW研究所，地点，国家）

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

2507.04680 2025-08-20 cs.LG cs.AI cs.CV 62%

Identify, Isolate, and Purge: Mitigating Hallucinations in LVLMs via Self-Evolving Distillation

Wenhao Li, Xiu Su, Jingyi Wu, Feng Yang, Yang Liu, Yi Chen, Shan You, Chang Xu

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

Comments In Figure 2, the correlation coefficient and the scatter plot do not match. I calculated this correlation using two sets of settings. I used the scatter plot from setting A, but accidentally wrote the correlation coefficient, r, from setting B

2501.00051 2025-08-20 cs.LG cs.AI cs.SY eess.SY 62%

DDD-GenDT: Dynamic Data-driven Generative Digital Twin Framework

Yu-Zheng Lin, Qinxuan Shi, Zhanglong Yang, Banafsheh Saber Latibari, Shalaka Satam, Sicong Shao, Soheil Salehi, Pratik Satam

机构 * Department of Electrical and Computer Engineering, University of Arizona（电气与计算机工程系，亚利桑那大学）； Department of Systems and Industrial Engineering, University of Arizona（系统与工业工程系，亚利桑那大学）； School of Electrical Engineering and Computer Science, University of North Dakota（电气工程与计算机科学学院，北达科他大学）

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

2505.23509 2025-08-20 cs.SD cs.LG eess.AS 57%

Spectrotemporal Modulation: Efficient and Interpretable Feature Representation for Classifying Speech, Music, and Environmental Sounds

Andrew Chang, Yike Li, Iran R. Roman, David Poeppel

机构 * New York University（纽约大学）； Queen Mary University of London（伦敦大学女王学院）； Max Planck Society（马克斯·普朗克协会）

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

Comments Interspeech 2025

2508.13547 2025-08-20 cs.CV eess.IV 50%

A Lightweight Dual-Mode Optimization for Generative Face Video Coding

Zihan Zhang, Shanzhi Yin, Bolin Chen, Ru-Ling Liao, Shiqi Wang, Yan Ye

机构 * Department of Computer Science, City University of Hong Kong（香港城市大学计算机科学系）； DAMO Academy, Alibaba Group（阿里巴巴集团达摩院）； Fudan University（复旦大学）； Hupan Lab（虎扑实验室）

专题命中效率与部署：post-training(abstract)

2508.14032 2025-08-20 cs.CL 90%

The Promise of Large Language Models in Digital Health: Evidence from Sentiment Analysis in Online Health Communities

Xiancheng Li, Georgios D. Karampatakis, Helen E. Wood, Chris J. Griffiths, Borislava Mihaylova, Neil S. Coulson, Alessio Pasinato, Pietro Panzarasa, Marco Viviani, Anna De Simoni

机构 * School of Business and Management, Queen Mary University of London（女王玛丽大学商学院）； Wolfson Institute of Population Health (WIPH), Queen Mary University of London（人口健康沃尔夫森研究所）； Department of Medicine, University of Nottingham（诺丁汉大学医学部）； Department of Informatics, Systems, and Communication, University of Milano-Bicocca（米兰-比科卡大学信息学、系统与通信系）

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

2410.02458 2025-08-20 eess.IV cs.CL cs.CV 89%

MedVisionLlama: Leveraging Pre-Trained Large Language Model Layers to Enhance Medical Image Segmentation

Gurucharan Marthi Krishna Kumar, Aman Chadha, Janine Mendola, Amir Shmuel

机构 * Montreal Neurological Institute, McGill University（蒙特利尔神经科学研究所，麦吉尔大学）

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

Comments Accepted to the CVAMD Workshop (Computer Vision for Automated Medical Diagnosis) at the 2025 IEEE/CVF International Conference on Computer Vision (ICCVW 2025)

1. 评测与基准 30 篇