语言大模型 / LLM - arXivDaily 专题

2406.06620 2025-09-09 cs.LG cs.AI cs.CL 82%

MedualTime: A Dual-Adapter Language Model for Medical Time Series-Text Multimodal Learning

Jiexia Ye, Weiqi Zhang, Ziyue Li, Jia Li, Meng Zhao, Fugee Tsung

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））； The Hong Kong University of Science and Technology（香港科技大学）； Technical University of Munich（慕尼黑技术大学）； Columbia University（哥伦比亚大学）

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

Comments 9 pages, 6 figure, 3 tables

Journal ref IJCAI 2025 main conference

2508.15903 2025-08-25 cs.CV 82%

VT-LVLM-AR: A Video-Temporal Large Vision-Language Model Adapter for Fine-Grained Action Recognition in Long-Term Videos

Kaining Li, Shuwei He, Zihan Xu

机构 * Xidian University（西电大学）

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

2508.11196 2025-08-18 cs.CV 82%

UAV-VL-R1: Generalizing Vision-Language Models via Supervised Fine-Tuning and Multi-Stage GRPO for UAV Visual Reasoning

Jiajin Guan, Haibo Mei, Bonan Zhang, Dan Liu, Yuanshuang Fu, Yue Zhang

机构 * Research Institute of Electronic Science and Technology, University of Electronic Science and Technology of China（电子科学与技术研究院，电子科技大学）； School of Aeronautics and Astronautics, University of Electronic Science and Technology of China（航空航天学院，电子科技大学）

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

2301.12429 2025-08-14 cs.CV 82%

Debiased Fine-Tuning for Vision-language Models by Prompt Regularization

Beier Zhu, Yulei Niu, Saeil Lee, Minhoe Hur, Hanwang Zhang

机构 * NTU（国立新加坡大学）

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

Comments AAAI2023 accepted

2503.09994 2025-08-08 cs.CV 82%

TIME: Temporal-Sensitive Multi-Dimensional Instruction Tuning and Robust Benchmarking for Video-LLMs

Yunxiao Wang, Meng Liu, Wenqi Liu, Xuemeng Song, Bin Wen, Fan Yang, Tingting Gao, Di Zhang, Guorui Zhou, Liqiang Nie

机构 * Shandong University（山东大学）； Shandong Jianzhu University（山东建筑大学）； City University of Hong Kong（香港城市大学）； Kuaishou Technology（快手科技）

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

2504.01308 2025-08-05 cs.CV 82%

Safeguarding Vision-Language Models: Mitigating Vulnerabilities to Gaussian Noise in Perturbation-based Attacks

Jiawei Wang, Yushen Zuo, Yuanjun Chai, Zhendong Liu, Yicheng Fu, Yichun Feng, Kin-Man Lam

机构 * University of Science and Technology of China（中国科学技术大学）； The Hong Kong Polytechnic University（香港理工大学）； University of Washington（华盛顿大学）； Nanjing University（南京大学）； Stanford University（斯坦福大学）； University of Chinese Academy of Sciences（中国科学院大学）

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

Comments ICCV 2025

2407.15731 2025-08-05 cs.CV 82%

The Inter-Intra Modal Measure: A Predictive Lens on Fine-Tuning Outcomes in Vision-Language Models

Laura Niss, Kevin Vogt-Lowell, Theodoros Tsiligkaridis

机构 * MIT Lincoln Laboratory（麻省理工学院林肯实验室）

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

Comments Accepted to ICCV 2025

2507.04569 2025-07-08 cs.CL cs.AI cs.LG 82%

Nile-Chat: Egyptian Language Models for Arabic and Latin Scripts

Guokan Shang, Hadi Abdine, Ahmad Chamma, Amr Mohamed, Mohamed Anwar, Abdelaziz Bounhar, Omar El Herraoui, Preslav Nakov, Michalis Vazirgiannis, Eric Xing

机构 * MBZUAI（穆罕默德·本·拉希德智能研究院）； Ecole Polytechnique（巴黎高等理工学院）

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

2507.03283 2025-07-08 cs.CV 82%

MolVision: Molecular Property Prediction with Vision Language Models

Deepan Adak, Yogesh Singh Rawat, Shruti Vyas

机构 * NIT Kurukshetra（尼特学院）； University of Central Florida（中央佛罗里达大学）

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

2502.15895 2025-06-24 cs.LG cs.AI cs.CL cs.CV 82%

Directional Gradient Projection for Robust Fine-Tuning of Foundation Models

Chengyue Huang, Junjiao Tian, Brisa Maneechotesuwan, Shivang Chopra, Zsolt Kira

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

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

Comments Accepted to ICLR 2025

2506.08666 2025-06-16 cs.CV 82%

LLaVA-c: Continual Improved Visual Instruction Tuning

Wenzhuo Liu, Fei Zhu, Haiyang Guo, Longhui Wei, Cheng-Lin Liu

机构 * School of Artificial Intelligence, UCAS（人工智能学院，UCAS）； State Key Laboratory of Multimodal Artificial Intelligence Systems, CASIA（多模态人工智能系统国家重点实验室，CASIA）； Centre for Artificial Intelligence and Robotics, HKISI-CAS（人工智能与机器人中心，HKISI-CAS）； Huawei Inc（华为公司）

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

2504.04178 2025-06-10 cs.IR 82%

MSL: Not All Tokens Are What You Need for Tuning LLM as a Recommender

Bohao Wang, Feng Liu, Jiawei Chen, Xingyu Lou, Changwang Zhang, Jun Wang, Yuegang Sun, Yan Feng, Chun Chen, Can Wang

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

Comments Accepted by SIGIR2025

2504.05632 2025-06-09 cs.CL cs.AI cs.LG 82%

Reasoning Towards Fairness: Mitigating Bias in Language Models through Reasoning-Guided Fine-Tuning

Sanchit Kabra, Akshita Jha, Chandan K. Reddy

机构 * Virginia Tech（弗吉尼亚理工大学）

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

Comments 17 pages

2506.00359 2025-06-03 cs.CR 82%

Keeping an Eye on LLM Unlearning: The Hidden Risk and Remedy

Jie Ren, Zhenwei Dai, Xianfeng Tang, Yue Xing, Shenglai Zeng, Hui Liu, Jingying Zeng, Qiankun Peng, Samarth Varshney, Suhang Wang, Qi He, Charu C. Aggarwal, Hui Liu

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

2505.08932 2025-05-15 cs.RO cs.CV 82%

Parameter-Efficient Fine-Tuning of Vision Foundation Model for Forest Floor Segmentation from UAV Imagery

Mohammad Wasil, Ahmad Drak, Brennan Penfold, Ludovico Scarton, Maximilian Johenneken, Alexander Asteroth, Sebastian Houben

机构 * Bonn-Rhein-Sieg University of Applied Sciences（博恩-莱茵-锡格应用科学大学）； Department of Computer Science（计算机科学系）； Institute for Artificial Intelligence and Autonomous Systems (A2S)（人工智能与自主系统研究所）； Institute of Technology, Resource and Energy-efficient Engineering (TREE)（技术与资源节能工程研究所）

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

Comments Accepted to the Novel Approaches for Precision Agriculture and Forestry with Autonomous Robots IEEE ICRA Workshop - 2025

2505.07172 2025-05-13 cs.CV 82%

Critique Before Thinking: Mitigating Hallucination through Rationale-Augmented Instruction Tuning

Zexian Yang, Dian Li, Dayan Wu, Gang Liu, Weiping Wang

机构 * Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）； Foundation Technology Center, Tencent PCG（腾讯PCG基础技术中心）

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

2505.01851 2025-05-06 cs.CV 82%

Mitigating Group-Level Fairness Disparities in Federated Visual Language Models

Chaomeng Chen, Zitong Yu, Junhao Dong, Sen Su, Linlin Shen, Shutao Xia, Xiaochun Cao

机构 * Great Bay University（大湾大学）； Tsinghua Shenzhen International Graduate School（清华大学深圳国际研究生院）； Nanyang Technological University（南洋理工大学）； Beijing University of Posts and Telecommunications（北京邮电大学）； Shenzhen University（深圳大学）； Pengcheng Laboratory（鹏城实验室）； Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区）

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

2505.00156 2025-05-02 cs.CV 82%

V3LMA: Visual 3D-enhanced Language Model for Autonomous Driving

Jannik Lübberstedt, Esteban Rivera, Nico Uhlemann, Markus Lienkamp

机构 * Technical University of Munich (TUM)（慕尼黑技术大学）； Munich Institute of Robotics and Machine Intelligence (MIRMI)（慕尼黑机器人与智能机械研究所）

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

2504.18349 2025-04-28 cs.CV cs.CR 82%

Revisiting Data Auditing in Large Vision-Language Models

Hongyu Zhu, Sichu Liang, Wenwen Wang, Boheng Li, Tongxin Yuan, Fangqi Li, ShiLin Wang, Zhuosheng Zhang

机构 * Shanghai Jiao Tong University（上海交通大学）； Southeast University（东南大学）； Carnegie Mellon University（卡内基梅隆大学）； Nanyang Technological University（南洋理工大学）

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

2504.14638 2025-04-22 cs.CV 82%

NVSMask3D: Hard Visual Prompting with Camera Pose Interpolation for 3D Open Vocabulary Instance Segmentation

Junyuan Fang, Zihan Wang, Yejun Zhang, Shuzhe Wang, Iaroslav Melekhov, Juho Kannala

机构 * Aalto University（阿莱大学）； University of Helsinki（赫尔辛基大学）； University of Oulu（奥卢大学）

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

Comments 15 pages, 4 figures, Scandinavian Conference on Image Analysis 2025

2504.07519 2025-04-11 cs.CV 82%

VideoExpert: Augmented LLM for Temporal-Sensitive Video Understanding

Henghao Zhao, Ge-Peng Ji, Rui Yan, Huan Xiong, Zechao Li

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

2406.11721 2025-04-08 cs.CL cs.AI cs.LG 82%

The Right Time Matters: Data Arrangement Affects Zero-Shot Generalization in Instruction Tuning

Bingxiang He, Ning Ding, Cheng Qian, Jia Deng, Ganqu Cui, Lifan Yuan, Haiwen Hong, Huan-ang Gao, Longtao Huang, Hui Xue, Huimin Chen, Zhiyuan Liu, Maosong Sun

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

Comments 22 pages, 16 figures

2504.01655 2025-04-03 cs.CV cs.MM 82%

Q-Adapt: Adapting LMM for Visual Quality Assessment with Progressive Instruction Tuning

Yiting Lu, Xin Li, Haoning Wu, Bingchen Li, Weisi Lin, Zhibo Chen

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

2502.14050 2025-04-02 cs.CL cs.AI cs.LG 82%

Diversity-driven Data Selection for Language Model Tuning through Sparse Autoencoder

Xianjun Yang, Shaoliang Nie, Lijuan Liu, Suchin Gururangan, Ujjwal Karn, Rui Hou, Madian Khabsa, Yuning Mao

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

Comments fix typos

2502.19777 2025-04-01 cs.CV 82%

InPK: Infusing Prior Knowledge into Prompt for Vision-Language Models

Shuchang Zhou, Jiwei Wei, Shiyuan He, Yuyang Zhou, Chaoning Zhang, Jie Zou, Ning Xie, Yang Yang

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

2503.15885 2025-03-21 cs.SE 82%

Human or LLM? A Comparative Study on Accessible Code Generation Capability

Hyunjae Suh, Mahan Tafreshipour, Sam Malek, Iftekhar Ahmed

专题命中指令微调：LLM(title,abstract)；prompting(abstract)

2410.06846 2025-03-14 cs.CL cs.AI cs.LG cs.SD eess.AS 82%

Joint Fine-tuning and Conversion of Pretrained Speech and Language Models towards Linear Complexity

Mutian He, Philip N. Garner

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

Comments 18 pages, 5 figures; ICLR 2025 camera ready. Code: https://github.com/idiap/linearize-distill-pretrained-transformers

2503.02199 2025-03-05 cs.CV cs.AI cs.CL cs.LG cs.MM 82%

Words or Vision: Do Vision-Language Models Have Blind Faith in Text?

Ailin Deng, Tri Cao, Zhirui Chen, Bryan Hooi

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

Comments Accepted to CVPR 2025

2410.11087 2025-03-05 cs.CV 82%

Locality Alignment Improves Vision-Language Models

Ian Covert, Tony Sun, James Zou, Tatsunori Hashimoto

专题命中指令微调：language model(title,abstract)；post-training(abstract)

Comments ICLR 2025 Camera-Ready

2502.12563 2025-02-19 cs.CL cs.AI cs.LG 82%

Evaluating Language Models on Grooming Risk Estimation Using Fuzzy Theory

Geetanjali Bihani, Tatiana Ringenberg, Julia Rayz

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

Comments 9 pages, 2 figures. Accepted for publication in the Proceedings of the NAFIPS International Conference on Fuzzy Systems, Soft Computing, and Explainable AI. NAFIPS'2024

1. 指令微调 11619 篇

MedualTime: A Dual-Adapter Language Model for Medical Time Series-Text Multimodal Learning

VT-LVLM-AR: A Video-Temporal Large Vision-Language Model Adapter for Fine-Grained Action Recognition in Long-Term Videos

UAV-VL-R1: Generalizing Vision-Language Models via Supervised Fine-Tuning and Multi-Stage GRPO for UAV Visual Reasoning

Debiased Fine-Tuning for Vision-language Models by Prompt Regularization

TIME: Temporal-Sensitive Multi-Dimensional Instruction Tuning and Robust Benchmarking for Video-LLMs

Safeguarding Vision-Language Models: Mitigating Vulnerabilities to Gaussian Noise in Perturbation-based Attacks

The Inter-Intra Modal Measure: A Predictive Lens on Fine-Tuning Outcomes in Vision-Language Models

Nile-Chat: Egyptian Language Models for Arabic and Latin Scripts

MolVision: Molecular Property Prediction with Vision Language Models

Directional Gradient Projection for Robust Fine-Tuning of Foundation Models

LLaVA-c: Continual Improved Visual Instruction Tuning

MSL: Not All Tokens Are What You Need for Tuning LLM as a Recommender

Reasoning Towards Fairness: Mitigating Bias in Language Models through Reasoning-Guided Fine-Tuning

Keeping an Eye on LLM Unlearning: The Hidden Risk and Remedy

Parameter-Efficient Fine-Tuning of Vision Foundation Model for Forest Floor Segmentation from UAV Imagery

Critique Before Thinking: Mitigating Hallucination through Rationale-Augmented Instruction Tuning

Mitigating Group-Level Fairness Disparities in Federated Visual Language Models

V3LMA: Visual 3D-enhanced Language Model for Autonomous Driving

Revisiting Data Auditing in Large Vision-Language Models

NVSMask3D: Hard Visual Prompting with Camera Pose Interpolation for 3D Open Vocabulary Instance Segmentation

VideoExpert: Augmented LLM for Temporal-Sensitive Video Understanding

The Right Time Matters: Data Arrangement Affects Zero-Shot Generalization in Instruction Tuning

Q-Adapt: Adapting LMM for Visual Quality Assessment with Progressive Instruction Tuning

Diversity-driven Data Selection for Language Model Tuning through Sparse Autoencoder

InPK: Infusing Prior Knowledge into Prompt for Vision-Language Models

Human or LLM? A Comparative Study on Accessible Code Generation Capability

Joint Fine-tuning and Conversion of Pretrained Speech and Language Models towards Linear Complexity

Words or Vision: Do Vision-Language Models Have Blind Faith in Text?

Locality Alignment Improves Vision-Language Models

Evaluating Language Models on Grooming Risk Estimation Using Fuzzy Theory