语言大模型 / LLM - arXivDaily 专题

2510.22829 2025-10-28 cs.CV cs.AI cs.MM 79%

LLM-based Fusion of Multi-modal Features for Commercial Memorability Prediction

Aleksandar Pramov

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

专题命中指令微调：LLM(title,abstract)；分类 cs.AI

2510.21722 2025-10-28 cs.HC cs.AI 79%

AquaVLM: Improving Underwater Situation Awareness with Mobile Vision Language Models

Beitong Tian, Lingzhi Zhao, Bo Chen, Haozhen Zheng, Jingcheng Yang, Mingyuan Wu, Deepak Vasisht, Klara Nahrstedt

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）

专题命中指令微调：language model(title,abstract)；分类 cs.AI

Comments 12 pages, 10 figures, under review

2505.21732 2025-10-28 cs.LG 79%

LaX: Boosting Low-Rank Training of Foundation Models via Latent Crossing

Ruijie Zhang, Ziyue Liu, Zhengyang Wang, Zheng Zhang

机构 * University of California at Santa Barbara（加州大学圣芭芭拉分校）

专题命中指令微调：foundation model(title,abstract)；分类 cs.LG

2502.14828 2025-10-27 cs.LG cs.CR 79%

Fundamental Limitations in Pointwise Defences of LLM Finetuning APIs

Xander Davies, Eric Winsor, Alexandra Souly, Tomek Korbak, Robert Kirk, Christian Schroeder de Witt, Yarin Gal

机构 * DSIT（数据与信息技术局）

专题命中指令微调：LLM(title,abstract)；分类 cs.LG

2507.19271 2025-10-24 cs.SE cs.AI cs.PL 79%

Fine-Tuning Multilingual Language Models for Code Review: An Empirical Study on Industrial C# Projects

Igli Begolli, Meltem Aksoy, Daniel Neider

机构 * Technical University Dortmund, Lovion GmbH（图鲁尼大学，洛维昂公司）； Security\ Alliance Ruhr, Technical University Dortmund（安全联盟鲁尔，图鲁尼大学）

专题命中指令微调：language model(title,abstract)；分类 cs.AI

2510.19160 2025-10-23 cs.LG 79%

Preliminary Use of Vision Language Model Driven Extraction of Mouse Behavior Towards Understanding Fear Expression

Paimon Goulart, Jordan Steinhauser, Kylene Shuler, Edward Korzus, Jia Chen, Evangelos E. Papalexakis

机构 * University of California, Riverside（加州大学河滨分校）

专题命中指令微调：language model(title,abstract)；分类 cs.LG

2510.16014 2025-10-21 cs.LG 79%

STAR: Boosting Time Series Foundation Models for Anomaly Detection through State-aware Adapter

Hanyin Cheng, Ruitong Zhang, Yuning Lu, Peng Chen, Meng Wang, Yang Shu, Bin Yang, Chenjuan Guo

机构 * East China Normal University（华东师范大学）； APPLab, Huawei（2012 APPLab，华为）

专题命中指令微调：foundation model(title,abstract)；分类 cs.LG

2510.15200 2025-10-20 econ.TH cs.AI 79%

The Economics of AI Foundation Models: Openness, Competition, and Governance

Fasheng Xu, Xiaoyu Wang, Wei Chen, Karen Xie

机构 * School of Business, University of Connecticut（康奈尔大学商学院）； Faculty of Business, The Hong Kong Polytechnic University（香港理工大学商学院）

专题命中指令微调：foundation model(title,abstract)；分类 cs.AI

2510.09473 2025-10-20 cs.CV cs.LG 79%

D-TPT: Dimensional Entropy Maximization for Calibrating Test-Time Prompt Tuning in Vision-Language Models

Jisu Han, Wonjun Hwang

专题命中指令微调：language model(title,abstract)；分类 cs.LG

Comments Corrected typos

2510.10366 2025-10-14 cs.CV cs.LG 79%

Vision4PPG: Emergent PPG Analysis Capability of Vision Foundation Models for Vital Signs like Blood Pressure

Saurabh Kataria, Ayca Ermis, Lovely Yeswanth Panchumarthi, Minxiao Wang, Xiao Hu

机构 * Nell Hodgson Woodruff School of Nursing, Emory University, Atlanta, USA, 30322（埃默里大学护理学院）

专题命中指令微调：foundation model(title,abstract)；分类 cs.LG

Comments BHI abstract extended

2510.04966 2025-10-07 cs.CV cs.AI 79%

ActiveMark: on watermarking of visual foundation models via massive activations

Anna Chistyakova, Mikhail Pautov

专题命中指令微调：foundation model(title,abstract)；分类 cs.AI

2508.00924 2025-10-07 cs.CL 79%

XAutoLM: Efficient Fine-Tuning of Language Models via Meta-Learning and AutoML

Ernesto L. Estevanell-Valladares, Suilan Estevez-Velarde, Yoan Gutiérrez, Andrés Montoyo, Ruslan Mitkov

机构 * University of Alicante（阿利坎特大学）； University of Havana（哈瓦那大学）； University of Lancaster（兰卡斯特大学）

专题命中指令微调：language model(title,abstract)；分类 cs.CL

Comments 18 pages, 10 figures, 7 tables. Preprint. Accepted at EMNLP 2025

2501.05482 2025-10-07 cs.CL cs.SI 79%

HP-BERT: A framework for longitudinal study of Hinduphobia on social media via language models

Ashutosh Singh, Rohitash Chandra

机构 * Transitional Artificial Intelligence Research Group, School of Mathematics and Statistics, UNSW Sydney（过渡人工智能研究组，数学与统计学学院，UNSW悉尼）； Centre for Artificial Intelligence and Innovation, Pingla Institute, Sydney, Australia（人工智能与创新中心，Pingla研究所，悉尼，澳大利亚）； Department of Data Science and Artificial Intelligence, IIIT Naya Raipur（数据科学与人工智能系，IIIT奈亚拉普尔）

专题命中指令微调：language model(title,abstract)；分类 cs.CL

2509.23653 2025-09-30 cs.CL 79%

Don't Settle Too Early: Self-Reflective Remasking for Diffusion Language Models

Zemin Huang, Yuhang Wang, Zhiyang Chen, Guo-Jun Qi

机构 * Westlake University（西湖大学）

专题命中指令微调：language model(title,abstract)；分类 cs.CL

Comments 24 pages,11 figures

2505.15130 2025-09-29 cs.LG 79%

Few-Shot Adversarial Low-Rank Fine-Tuning of Vision-Language Models

Sajjad Ghiasvand, Haniyeh Ehsani Oskouie, Mahnoosh Alizadeh, Ramtin Pedarsani

专题命中指令微调：language model(title,abstract)；分类 cs.LG

2509.19595 2025-09-25 cs.CL cs.CV 79%

Anatomy of a Feeling: Narrating Embodied Emotions via Large Vision-Language Models

Mohammad Saim, Phan Anh Duong, Cat Luong, Aniket Bhanderi, Tianyu Jiang

机构 * University of Cincinnati（辛辛那提大学）

专题命中指令微调：language model(title,abstract)；分类 cs.CL

2509.19306 2025-09-25 eess.SP cs.AI cs.IT cs.NI math.IT 79%

A Federated Fine-Tuning Paradigm of Foundation Models in Heterogenous Wireless Networks

Jingyi Wang, Zhongyuan Zhao, Qingtian Wang, Zexu Li, Yue Wang, Tony Q. S. Quek

机构 * Wireless AI System Research Team, China Telecom Research Institute（中国电信研究院无线AI系统研究团队）； The State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications（北京邮电大学网络与交换技术国家重点实验室）； Singapore University of Technology and Design（新加坡科技设计大学）

专题命中指令微调：foundation model(title,abstract)；分类 cs.AI

2505.22157 2025-09-25 cs.CL 79%

LASER: Stratified Selective Sampling for Instruction Tuning with Dedicated Scoring Strategy

Paramita Mirza, Lucas Weber, Fabian Küch

机构 * ScaDS.AI & TU Dresden（ScaDS.AI与德累斯顿技术大学）； Fraunhofer IIS（弗劳恩霍夫研究所）

专题命中指令微调：instruction tuning(title)；post-training(abstract)；分类 cs.CL

Comments Accepted at Findings of the Association for Computational Linguistics: EMNLP 2025

2509.18529 2025-09-24 cs.LG q-bio.GN 79%

Reverse-Complement Consistency for DNA Language Models

Mingqian Ma

机构 * Carnegie Mellon University（卡内基梅隆大学）

专题命中指令微调：language model(title,abstract)；分类 cs.LG

2509.17167 2025-09-23 cs.CL 79%

SFT-TA: Supervised Fine-Tuned Agents in Multi-Agent LLMs for Automated Inductive Thematic Analysis

Seungjun Yi, Joakim Nguyen, Huimin Xu, Terence Lim, Joseph Skrovan, Mehak Beri, Hitakshi Modi, Andrew Well, Liu Leqi, Mia Markey, Ying Ding

机构 * University of Texas at Austin（德克萨斯大学）； Vanderbilt University School of Medicine（范德比大学医学院）； McCombs School of Business University of Texas at Austin（德克萨斯大学麦康姆商学院）

专题命中指令微调：SFT(title,abstract)；分类 cs.CL

2509.16617 2025-09-23 cs.CV cs.AI 79%

Detection and Simulation of Urban Heat Islands Using a Fine-Tuned Geospatial Foundation Model

David Kreismann

机构 * Baden-Wuerttemberg Cooperative State University（巴登-符腾堡州立大学）

专题命中指令微调：foundation model(title,abstract)；分类 cs.AI

Comments 12 pages, 4 figures, to appear in GI LNI (SKILL 2025)

2409.13366 2025-09-17 cs.CV cs.AI 79%

RingMo-Aerial: An Aerial Remote Sensing Foundation Model With Affine Transformation Contrastive Learning

Wenhui Diao, Haichen Yu, Kaiyue Kang, Tong Ling, Di Liu, Yingchao Feng, Hanbo Bi, Libo Ren, Xuexue Li, Yongqiang Mao, Xian Sun

机构 * Aerospace Information Research Institute, Chinese Academy of Sciences（中国科学院航空信息研究所）； University of Chinese Academy of Sciences（中国科学院大学）； Key Laboratory of Target Cognition and Application Technology (TCAT), Aerospace Information Research Institute, Chinese Academy of Sciences（目标认知与应用技术重点实验室（TCAT））； Department of Electronic Engineering, Tsinghua University（清华大学电子工程系）

专题命中指令微调：foundation model(title,abstract)；分类 cs.AI

2509.12724 2025-09-17 cs.CV cs.AI 79%

Defense-to-Attack: Bypassing Weak Defenses Enables Stronger Jailbreaks in Vision-Language Models

Yunhan Zhao, Xiang Zheng, Xingjun Ma

机构 * Fudan University（复旦大学）； City University of Hong Kong（香港城市大学）

专题命中指令微调：language model(title,abstract)；分类 cs.AI

Comments This work has been submitted to the IEEE for possible publication

2509.12697 2025-09-17 cs.LG 79%

Bi-level Personalization for Federated Foundation Models: A Task-vector Aggregation Approach

Yiyuan Yang, Guodong Long, Qinghua Lu, Liming Zhu, Jing Jiang

专题命中指令微调：foundation model(title,abstract)；分类 cs.LG

2406.15007 2025-09-16 cs.AI 79%

RouteFinder: Towards Foundation Models for Vehicle Routing Problems

Federico Berto, Chuanbo Hua, Nayeli Gast Zepeda, André Hottung, Niels Wouda, Leon Lan, Junyoung Park, Kevin Tierney, Jinkyoo Park

机构 * KAIST（韩国科学技术院）； Bielefeld University（比勒菲尔德大学）； Rotterdam School of Management（鹿特丹管理学院）； VU Amsterdam（阿姆斯特丹自由大学）； Omelet AI4CO

专题命中指令微调：foundation model(title,abstract)；分类 cs.AI

Comments TMLR 2025. A previous version of this work was presented as Oral at the ICML 2024 FM-Wild Workshop

2509.10513 2025-09-16 cs.LG 79%

Mixture-of-Clustered-Experts: Advancing Expert Specialization and Generalization in Instruction Tuning

Sugyeong Eo, Jungjun Lee, Chanjun Park, Heuiseok Lim

机构 * Department of Computer Science and Engineering, Korea University, Republic of Korea（韩国大学计算机科学与工程系）； KT, Republic of Korea（韩国KT）； School of Software, Soongsil University, Republic of Korea（顺天大学软件学院）

专题命中指令微调：instruction tuning(title,abstract)；分类 cs.LG

2506.05394 2025-09-15 cs.CR cs.LG 79%

Attacking Attention of Foundation Models Disrupts Downstream Tasks

Hondamunige Prasanna Silva, Federico Becattini, Lorenzo Seidenari

机构 * University of Florence（佛罗伦萨大学）； University of Siena（锡耶纳大学）

专题命中指令微调：foundation model(title,abstract)；分类 cs.LG

Comments Paper published at CVPR 2025 Workshop Advml

2509.08903 2025-09-12 cs.CL 79%

Noise or Nuance: An Investigation Into Useful Information and Filtering For LLM Driven AKBC

Alex Clay, Ernesto Jiménez-Ruiz, Pranava Madhyastha

机构 * City St George's, University of London（伦敦城市圣乔治大学）； The Alan Turing Institute, British Library（艾伦·图灵研究所，大英图书馆）

专题命中指令微调：LLM(title,abstract)；分类 cs.CL

Comments 8 pages, 1 figure, accepted to the ISWC 2025 LM-KBC Workshop

2405.10160 2025-09-11 cs.CV cs.AI 79%

PriorCLIP: Visual Prior Guided Vision-Language Model for Remote Sensing Image-Text Retrieval

Jiancheng Pan, Muyuan Ma, Qing Ma, Cong Bai, Shengyong Chen

机构 * IEEE Publication Technology Department（IEEE出版技术部）

专题命中指令微调：language model(title,abstract)；分类 cs.AI

Comments 14 pages, 7 figures

2509.07488 2025-09-10 cs.CV cs.AI 79%

Fine-Tuning Vision-Language Models for Visual Navigation Assistance

Xiao Li, Bharat Gandhi, Ming Zhan, Mohit Nehra, Zhicheng Zhang, Yuchen Sun, Meijia Song, Naisheng Zhang, Xi Wang

机构 * University of Florida, Gainesville, FL, USA（佛罗里达大学）； University of Minnesota, Minneapolis, MN, USA（明尼苏达大学）； New York University, New York, NY, USA（纽约大学）

专题命中指令微调：language model(title,abstract)；分类 cs.AI

1. 指令微调 11653 篇

LLM-based Fusion of Multi-modal Features for Commercial Memorability Prediction

AquaVLM: Improving Underwater Situation Awareness with Mobile Vision Language Models

LaX: Boosting Low-Rank Training of Foundation Models via Latent Crossing

Fundamental Limitations in Pointwise Defences of LLM Finetuning APIs

Fine-Tuning Multilingual Language Models for Code Review: An Empirical Study on Industrial C# Projects

Preliminary Use of Vision Language Model Driven Extraction of Mouse Behavior Towards Understanding Fear Expression

STAR: Boosting Time Series Foundation Models for Anomaly Detection through State-aware Adapter

The Economics of AI Foundation Models: Openness, Competition, and Governance

D-TPT: Dimensional Entropy Maximization for Calibrating Test-Time Prompt Tuning in Vision-Language Models

Vision4PPG: Emergent PPG Analysis Capability of Vision Foundation Models for Vital Signs like Blood Pressure

ActiveMark: on watermarking of visual foundation models via massive activations

XAutoLM: Efficient Fine-Tuning of Language Models via Meta-Learning and AutoML

HP-BERT: A framework for longitudinal study of Hinduphobia on social media via language models

Don't Settle Too Early: Self-Reflective Remasking for Diffusion Language Models

Few-Shot Adversarial Low-Rank Fine-Tuning of Vision-Language Models

Anatomy of a Feeling: Narrating Embodied Emotions via Large Vision-Language Models

A Federated Fine-Tuning Paradigm of Foundation Models in Heterogenous Wireless Networks

LASER: Stratified Selective Sampling for Instruction Tuning with Dedicated Scoring Strategy

Reverse-Complement Consistency for DNA Language Models

SFT-TA: Supervised Fine-Tuned Agents in Multi-Agent LLMs for Automated Inductive Thematic Analysis

Detection and Simulation of Urban Heat Islands Using a Fine-Tuned Geospatial Foundation Model

RingMo-Aerial: An Aerial Remote Sensing Foundation Model With Affine Transformation Contrastive Learning

Defense-to-Attack: Bypassing Weak Defenses Enables Stronger Jailbreaks in Vision-Language Models

Bi-level Personalization for Federated Foundation Models: A Task-vector Aggregation Approach

RouteFinder: Towards Foundation Models for Vehicle Routing Problems

Mixture-of-Clustered-Experts: Advancing Expert Specialization and Generalization in Instruction Tuning

Attacking Attention of Foundation Models Disrupts Downstream Tasks

Noise or Nuance: An Investigation Into Useful Information and Filtering For LLM Driven AKBC

PriorCLIP: Visual Prior Guided Vision-Language Model for Remote Sensing Image-Text Retrieval

Fine-Tuning Vision-Language Models for Visual Navigation Assistance