语言大模型 / LLM - arXivDaily 专题

2507.15480 2025-07-29 cs.CV 78%

One Last Attention for Your Vision-Language Model

Liang Chen, Ghazi Shazan Ahmad, Tianjun Yao, Lingqiao Liu, Zhiqiang Shen

专题命中指令微调：language model(title,abstract)

Comments Accepted by ICCV 2025

2507.14898 2025-07-22 eess.AS eess.SP 78%

Parameter-Efficient Fine-Tuning of Foundation Models for CLP Speech Classification

Susmita Bhattacharjee, Jagabandhu Mishra, H. S. Shekhawat, S. R. Mahadeva Prasanna

专题命中指令微调：foundation model(title,abstract)

Comments 6 pages, 5 figures, conference

2507.13089 2025-07-18 cs.CV 78%

GLAD: Generalizable Tuning for Vision-Language Models

Yuqi Peng, Pengfei Wang, Jianzhuang Liu, Shifeng Chen

机构 * Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（深圳先进技术研究院，中国科学院）； Northeastern University（东北大学）； The Hong Kong Polytechnic University（香港理工大学）； Shenzhen University of Advanced Technology（深圳先进技术大学）

专题命中指令微调：language model(title,abstract)

Comments ICCV 2025 workshop

2507.12807 2025-07-18 cs.CV 78%

Semantic-guided Fine-tuning of Foundation Model for Long-tailed Visual Recognition

Yufei Peng, Yonggang Zhang, Yiu-ming Cheung

专题命中指令微调：foundation model(title,abstract)

2104.00505 2025-07-16 math.SG math.GT 78%

Simplified SFT moduli spaces for Legendrian links

Russell Avdek

专题命中指令微调：SFT(title,abstract)

Comments 42 pages. V4: Updates based on referee feedback

Journal ref J. Symplectic Geom. 21, No. 2, 265-329 (2023)

2507.07013 2025-07-10 cs.CV 78%

Integrating Pathology Foundation Models and Spatial Transcriptomics for Cellular Decomposition from Histology Images

Yutong Sun, Sichen Zhu, Peng Qiu

机构 * School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA（电气与计算机工程学院，佐治亚理工学院）； Department of Biomedical Engineering, Georgia Institute of Technology（生物医学工程系，佐治亚理工学院）； Emory University, Atlanta, GA, USA（埃默里大学）

专题命中指令微调：foundation model(title,abstract)

2507.05668 2025-07-09 cs.CV 78%

Dynamic Rank Adaptation for Vision-Language Models

Jiahui Wang, Qin Xu, Bo Jiang, Bin Luo

机构 * Anhui University（安徽大学）

专题命中指令微调：language model(title,abstract)

2412.01145 2025-07-08 eess.AS 78%

AlignFormer: Modality Matching Can Achieve Better Zero-shot Instruction-Following Speech-LLM

Ruchao Fan, Bo Ren, Yuxuan Hu, Rui Zhao, Shujie Liu, Jinyu Li

专题命中指令微调：LLM(title,abstract)

Comments To be published in the Journal of Selected Topics in Signal Processing (JSTSP)

2506.23283 2025-07-01 cs.CV 78%

MoMa: Modulating Mamba for Adapting Image Foundation Models to Video Recognition

Yuhuan Yang, Chaofan Ma, Zhenjie Mao, Jiangchao Yao, Ya Zhang, Yanfeng Wang

机构 * Cooperative Medianet Innovation Center, Shanghai Jiao Tong University（上海交通大学协同中位创新中心）； School of Artificial Intelligence, Shanghai Jiao Tong University（上海交通大学人工智能学院）； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）

专题命中指令微调：foundation model(title,abstract)

Comments ICML 2025 paper

2506.22395 2025-06-30 cs.CV 78%

Test-Time Consistency in Vision Language Models

Shih-Han Chou, Shivam Chandhok, James J. Little, Leonid Sigal

机构 * Department of Computer Science, University of British Columbia（不列颠哥伦比亚大学计算机科学系）； Vector Institute for AI（人工智能矢量研究所）； Canada CIFAR AI Chair（加拿大CIFAR人工智能主席）

专题命中指令微调：language model(title,abstract)

2506.22149 2025-06-30 cs.CV 78%

RetFiner: A Vision-Language Refinement Scheme for Retinal Foundation Models

Ronald Fecso, José Morano, Ursula Schmidt-Erfurth, Hrvoje Bogunović

机构 * Institute of Artificial Intelligence, Center for Medical Data Science, Medical University of Vienna（人工智能研究所、医学数据科学中心、维也纳医科大学）； Christian Doppler Lab for Artificial Intelligence in Retina, Center for Medical Data Science, Medical University of Vienna（视网膜人工智能基督教多普勒实验室、医学数据科学中心、维也纳医科大学）； Comprehensive Center for AI in Medicine, Medical University of Vienna（医学人工智能综合中心、维也纳医科大学）； OPTIMA Lab, Dept. of Ophthalmology, Medical University of Vienna（OPTIMA实验室、眼科部门、维也纳医科大学）

专题命中指令微调：foundation model(title,abstract)

Comments Accepted for presentation at MICCAI 2025

2506.21975 2025-06-30 cs.CV 78%

TASeg: Text-aware RGB-T Semantic Segmentation based on Fine-tuning Vision Foundation Models

Meng Yu, Te Cui, Qitong Chu, Wenjie Song, Yi Yang, Yufeng Yue

机构 * School of Automation, Beijing Institute of Technology（自动化学院，北京理工大学）

专题命中指令微调：foundation model(title,abstract)

Comments 6 pages, accepted for publication in lEEE/RSJ international Conference on Intelligent Robots and Systems (lROS 2025)

2410.04778 2025-06-30 cs.CV 78%

MM-R$^3$: On (In-)Consistency of Vision-Language Models (VLMs)

Shih-Han Chou, Shivam Chandhok, James J. Little, Leonid Sigal

专题命中指令微调：language model(title,abstract)

2506.21317 2025-06-27 cs.CV 78%

LLaVA-Pose: Enhancing Human Pose and Action Understanding via Keypoint-Integrated Instruction Tuning

Dewen Zhang, Tahir Hussain, Wangpeng An, Hayaru Shouno

机构 * Department of Informatics, Graduate School of Informatics and Engineering, The University of Electro-Communications（信息学院、信息工程研究生院、东京电波通信大学）

专题命中指令微调：instruction tuning(title)；language model(abstract)

Comments arXiv admin note: substantial text overlap with arXiv:2409.09306

2506.13073 2025-06-17 cs.CV 78%

SuperPlace: The Renaissance of Classical Feature Aggregation for Visual Place Recognition in the Era of Foundation Models

Bingxi Liu, Pengju Zhang, Li He, Hao Chen, Shiyi Guo, Yihong Wu, Jinqiang Cui, Hong Zhang

机构 * Southern University of Science and Technology（南方科技大学）； Peng Cheng Laboratory（鹏城实验室）； Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）； Cambridge University（剑桥大学）

专题命中指令微调：foundation model(title,abstract)

Comments 11 pages

2503.00513 2025-06-17 cs.CV 78%

Inst3D-LMM: Instance-Aware 3D Scene Understanding with Multi-modal Instruction Tuning

Hanxun Yu, Wentong Li, Song Wang, Junbo Chen, Jianke Zhu

机构 * Zhejiang University（浙江大学）； Nanjing University of Aeronautics and Astronautics（南京航空航天大学）

专题命中指令微调：instruction tuning(title,abstract)

Comments CVPR2025, Code Link: https://github.com/hanxunyu/Inst3D-LMM

2504.17397 2025-06-16 cs.CV 78%

Fine-tune Smarter, Not Harder: Parameter-Efficient Fine-Tuning for Geospatial Foundation Models

Francesc Marti-Escofet, Benedikt Blumenstiel, Linus Scheibenreif, Paolo Fraccaro, Konrad Schindler

机构 * IBM Research Europe（IBM欧洲研究院）； ETH Zurich（苏黎世联邦理工学院）

专题命中指令微调：foundation model(title,abstract)

Comments Code available at https://github.com/IBM/peft-geofm

2506.07214 2025-06-10 cs.CV cs.CR 78%

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation

Zhiyuan Zhong, Zhen Sun, Yepang Liu, Xinlei He, Guanhong Tao

专题命中指令微调：language model(title,abstract)

2506.05318 2025-06-09 cs.CV 78%

Does Your 3D Encoder Really Work? When Pretrain-SFT from 2D VLMs Meets 3D VLMs

Haoyuan Li, Yanpeng Zhou, Yufei Gao, Tao Tang, Jianhua Han, Yujie Yuan, Dave Zhenyu Chen, Jiawang Bian, Hang Xu, Xiaodan Liang

机构 * Shenzhen campus of Sun Yat-sen University（中山大学深圳校区）； Huawei Noah’s Ark Lab（华为诺亚实验室）； MBZUAI ； Peng Cheng Laboratory（鹏城实验室）； Guangdong Key Laboratory of Big Data Analysis and Processing（广东省大数据分析与处理重点实验室）

专题命中指令微调：SFT(title)；language model(abstract)

2502.19958 2025-06-03 cs.CV 78%

ChatReID: Open-ended Interactive Person Retrieval via Hierarchical Progressive Tuning for Vision Language Models

Ke Niu, Haiyang Yu, Mengyang Zhao, Teng Fu, Siyang Yi, Wei Lu, Bin Li, Xuelin Qian, Xiangyang Xue

机构 * Fudan University（复旦大学）； Northwestern Polytechnical University（西北工业大学）

专题命中指令微调：language model(title,abstract)

2505.23236 2025-05-30 cs.SD cs.HC eess.AS 78%

Towards LLM-Empowered Fine-Grained Speech Descriptors for Explainable Emotion Recognition

Youjun Chen, Xurong Xie, Haoning Xu, Mengzhe Geng, Guinan Li, Chengxi Deng, Huimeng Wang, Shujie Hu, Xunying Liu

机构 * The Chinese University of Hong Kong（香港中文大学）； Chinese Academy of Sciences（中国科学院）； National Research Council Canada（加拿大国家研究理事会）； Institute of Software（软件研究所）

专题命中指令微调：LLM(title,abstract)

Comments Accepted by INTERSPEECH2025

2410.10919 2025-05-30 q-bio.QM q-bio.GN 78%

Fine-tuning the ESM2 protein language model to understand the functional impact of missense variants

Ali Saadat, Jacques Fellay

专题命中指令微调：language model(title,abstract)

2505.05130 2025-05-27 cs.DC 78%

CacheFL: Privacy-Preserving and Efficient Federated Cache Model Fine-Tuning for Vision-Language Models

Mengjun Yi, Hanwen Zhang, Hui Dou, Jian Zhao, Furao Shen

专题命中指令微调：language model(title,abstract)

2505.18115 2025-05-26 cs.CV 78%

Instructify: Demystifying Metadata to Visual Instruction Tuning Data Conversion

Jacob Hansen, Wei Lin, Junmo Kang, Muhammad Jehanzeb Mirza, Hongyin Luo, Rogerio Feris, Alan Ritter, James Glass, Leonid Karlinsky

专题命中指令微调：instruction tuning(title,abstract)

2505.15334 2025-05-22 cs.CV 78%

Parameter-Efficient Fine-Tuning of Multispectral Foundation Models for Hyperspectral Image Classification

Bernardin Ligan, Khalide Jbilou, Fahd Kalloubi, Ahmed Ratnani

机构 * University Mohammed VI Polytechnic (UM6P)（摩洛哥穆莱·伊沙克·费萨尔大学）

专题命中指令微调：foundation model(title,abstract)

Comments 33 pages, 14 figures

2505.12991 2025-05-20 cs.SD eess.AS 78%

Personalized Fine-Tuning with Controllable Synthetic Speech from LLM-Generated Transcripts for Dysarthric Speech Recognition

Dominik Wagner, Ilja Baumann, Natalie Engert, Seanie Lee, Elmar Nöth, Korbinian Riedhammer, Tobias Bocklet

机构 * Technische Hochschule Nürnberg（纽伦堡技术大学）； Korea Advanced Institute of Science & Technology（韩国科学技术院）； Friedrich-Alexander-Universität Erlangen-Nürnberg（埃尔兰根-纽伦堡 Friedrich-Alexander 大学）

专题命中指令微调：LLM(title,abstract)

Comments Accepted at Interspeech 2025

2505.12912 2025-05-20 cs.CV 78%

Uniformity First: Uniformity-aware Test-time Adaptation of Vision-language Models against Image Corruption

Kazuki Adachi, Shin'ya Yamaguchi, Tomoki Hamagami

机构 * NTT, Inc.（NTT公司）； Kyoto University（京都大学）； Yokohama National University（横滨国立大学）

专题命中指令微调：language model(title,abstract)

Comments Code is available at https://github.com/kzkadc/uninfo

2505.10219 2025-05-16 cs.RO 78%

Towards Safe Robot Foundation Models Using Inductive Biases

Maximilian Tölle, Theo Gruner, Daniel Palenicek, Tim Schneider, Jonas Günster, Joe Watson, Davide Tateo, Puze Liu, Jan Peters

机构 * Technical University of Darmstadt（德累斯顿技术大学）； German Research Center for AI ( dfki )（人工智能研究中心）； University of Oxford（牛津大学）； Robotics Institute Germany ( rig )（德国机器人研究所）； Centre for Cognitive Science（认知科学中心）

专题命中指令微调：foundation model(title,abstract)

Comments 14 pages, 5 figures

2412.03587 2025-05-16 cs.CL cs.AI cs.LG 78%

Not All Adapters Matter: Selective Adapter Freezing for Memory-Efficient Fine-Tuning of Language Models

Hyegang Son, Yonglak Son, Changhoon Kim, Young Geun Kim

机构 * Korea University（韩国大学）； Arizona State University（亚利桑那州立大学）； Soongsil University（顺天大学）

专题命中指令微调：language model(title)；分类 cs.CL、cs.AI、cs.LG

Comments URL: https://aclanthology.org/2025.naacl-long.480/ Volume: Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) Year: 2025 Address: Albuquerque, New Mexico

2505.07690 2025-05-13 cs.CV 78%

Beyond CLIP Generalization: Against Forward&Backward Forgetting Adapter for Continual Learning of Vision-Language Models

Songlin Dong, Chenhao Ding, Jiangyang Li, Jizhou Han, Qiang Wang, Yuhang He, Yihong Gong

机构 * College of Artificial Intelligence, Xi’an Jiaotong University（人工智能学院，西安交通大学）； School of Software Engineering, Xi’an Jiaotong University（软件工程学院，西安交通大学）

专题命中指令微调：language model(title,abstract)

1. 指令微调 11714 篇

One Last Attention for Your Vision-Language Model

Parameter-Efficient Fine-Tuning of Foundation Models for CLP Speech Classification

GLAD: Generalizable Tuning for Vision-Language Models

Semantic-guided Fine-tuning of Foundation Model for Long-tailed Visual Recognition

Simplified SFT moduli spaces for Legendrian links

Integrating Pathology Foundation Models and Spatial Transcriptomics for Cellular Decomposition from Histology Images

Dynamic Rank Adaptation for Vision-Language Models

AlignFormer: Modality Matching Can Achieve Better Zero-shot Instruction-Following Speech-LLM

MoMa: Modulating Mamba for Adapting Image Foundation Models to Video Recognition

Test-Time Consistency in Vision Language Models

RetFiner: A Vision-Language Refinement Scheme for Retinal Foundation Models

TASeg: Text-aware RGB-T Semantic Segmentation based on Fine-tuning Vision Foundation Models

MM-R$^3$: On (In-)Consistency of Vision-Language Models (VLMs)

LLaVA-Pose: Enhancing Human Pose and Action Understanding via Keypoint-Integrated Instruction Tuning

SuperPlace: The Renaissance of Classical Feature Aggregation for Visual Place Recognition in the Era of Foundation Models

Inst3D-LMM: Instance-Aware 3D Scene Understanding with Multi-modal Instruction Tuning

Fine-tune Smarter, Not Harder: Parameter-Efficient Fine-Tuning for Geospatial Foundation Models

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation

Does Your 3D Encoder Really Work? When Pretrain-SFT from 2D VLMs Meets 3D VLMs

ChatReID: Open-ended Interactive Person Retrieval via Hierarchical Progressive Tuning for Vision Language Models

Towards LLM-Empowered Fine-Grained Speech Descriptors for Explainable Emotion Recognition

Fine-tuning the ESM2 protein language model to understand the functional impact of missense variants

CacheFL: Privacy-Preserving and Efficient Federated Cache Model Fine-Tuning for Vision-Language Models

Instructify: Demystifying Metadata to Visual Instruction Tuning Data Conversion

Parameter-Efficient Fine-Tuning of Multispectral Foundation Models for Hyperspectral Image Classification

Personalized Fine-Tuning with Controllable Synthetic Speech from LLM-Generated Transcripts for Dysarthric Speech Recognition

Uniformity First: Uniformity-aware Test-time Adaptation of Vision-language Models against Image Corruption

Towards Safe Robot Foundation Models Using Inductive Biases

Not All Adapters Matter: Selective Adapter Freezing for Memory-Efficient Fine-Tuning of Language Models

Beyond CLIP Generalization: Against Forward&Backward Forgetting Adapter for Continual Learning of Vision-Language Models