arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~

AI 大模型

语言大模型 / LLM

大语言模型、预训练、指令微调、后训练和语言模型应用。

2025-09-18 至 2025-09-18 共收录 12 信号源:cs.CL, cs.AI, cs.LG

1. 指令微调 12 篇

2410.08299 2025-09-18 cs.LG cs.CL cs.CR 88%

Privately Learning from Graphs with Applications in Fine-tuning Large Language Models

Haoteng Yin, Rongzhe Wei, Eli Chien, Pan Li

机构 * Purdue University(普渡大学) Georgia Institute of Technology(佐治亚理工学院)

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

Comments Accepted by COLM 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.13906 2025-09-18 cs.LG 83%

TFMAdapter: Lightweight Instance-Level Adaptation of Foundation Models for Forecasting with Covariates

Afrin Dange, Sunita Sarawagi

机构 * Indian Institute of Technology Bombay Centre for Machine Intelligence(印度理工学院班加罗尔中心人工智能与数据科学中心) Indian Institute of Technology Bombay Department of Computer Science(印度理工学院班加罗尔计算机科学与工程系)

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

Comments Accepted at CIKM 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.12129 2025-09-18 cs.RO 82%

Embodied Navigation Foundation Model

Jiazhao Zhang, Anqi Li, Yunpeng Qi, Minghan Li, Jiahang Liu, Shaoan Wang, Haoran Liu, Gengze Zhou, Yuze Wu, Xingxing Li, Yuxin Fan, Wenjun Li, Zhibo Chen, Fei Gao, Qi Wu, Zhizheng Zhang, He Wang

机构 * Peking University(北京大学) Galbot USTC(中国科学技术大学) BAAI(百度人工智能研究院) University of Adelaide(阿德莱德大学) Zhejiang University(浙江大学) Differential Robotics Project(差分机器人项目)

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

Comments Project Page: https://pku-epic.github.io/NavFoM-Web/

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.01658 2025-09-18 cs.LG cs.AI cs.IR 79%

CoPL: Collaborative Preference Learning for Personalizing LLMs

Youngbin Choi, Seunghyuk Cho, Minjong Lee, MoonJeong Park, Yesong Ko, Jungseul Ok, Dongwoo Kim

机构 * Graduate School of Artificial Intelligence, POSTECH(POSTECH人工智能研究生院) Department of Computer Science and Engineering, POSTECH(POSTECH计算机科学与工程系)

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

Comments 19pages, 13 figures, 11 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.09974 2025-09-18 cs.CR cs.AI 77%

Analysing Safety Risks in LLMs Fine-Tuned with Pseudo-Malicious Cyber Security Data

Adel ElZemity, Budi Arief, Shujun Li

机构 * University of Kent(肯特大学)

专题命中 指令微调 :LLM(abstract);large language model(abstract);language model(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.13760 2025-09-18 cs.CV 75%

Iterative Prompt Refinement for Safer Text-to-Image Generation

Jinwoo Jeon, JunHyeok Oh, Hayeong Lee, Byung-Jun Lee

机构 * Korea University(韩国大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.13395 2025-09-18 eess.AS cs.AI cs.CL cs.LG cs.MM 67%

TICL: Text-Embedding KNN For Speech In-Context Learning Unlocks Speech Recognition Abilities of Large Multimodal Models

Haolong Zheng, Yekaterina Yegorova, Mark Hasegawa-Johnson

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.08531 2025-09-18 cs.CV cs.RO 67%

Embodied Image Captioning: Self-supervised Learning Agents for Spatially Coherent Image Descriptions

Tommaso Galliena, Tommaso Apicella, Stefano Rosa, Pietro Morerio, Alessio Del Bue, Lorenzo Natale

机构 * Istituto Italiano di Tecnologia(意大利技术研究院) University of Genoa(热那亚大学)

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

Comments 11 pages, 8 figures, 6 tables, code and test set annotations available at https://hsp-iit.github.io/embodied-captioning/

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.13878 2025-09-18 eess.AS cs.LG cs.SD 57%

Mixture of Low-Rank Adapter Experts in Generalizable Audio Deepfake Detection

Janne Laakkonen, Ivan Kukanov, Ville Hautamäki

机构 * University of Eastern Finland(东芬兰大学)

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

Comments 6 pages, 3 figures, 1 table

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.04975 2025-09-18 cs.CL 57%

PETapter: Leveraging PET-style classification heads for modular few-shot parameter-efficient fine-tuning

Jonas Rieger, Mattes Ruckdeschel, Gregor Wiedemann

机构 * Leibniz Institute for Media Research | Hans-Bredow-Institut (HBI)(莱比锡媒体研究所 | 哈恩-布雷多研究所)

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

Journal ref https://aclanthology.org/2025.konvens-1.29/

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.14060 2025-09-18 cs.CV 50%

VSE-MOT: Multi-Object Tracking in Low-Quality Video Scenes Guided by Visual Semantic Enhancement

Jun Du, Weiwei Xing, Ming Li, Fei Richard Yu

机构 * School of Software Engineering(软件工程学院) Guangdong Laboratory of Artificial Intelligence and Digital Economy(人工智能与数字经济广东实验室)

专题命中 指令微调 :language model(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.13919 2025-09-18 cs.CV 50%

Towards Rationale-Answer Alignment of LVLMs via Self-Rationale Calibration

Yuanchen Wu, Ke Yan, Shouhong Ding, Ziyin Zhou, Xiaoqiang Li

机构 * School of Computer Engineering(计算机工程学院) Key Laboratory of Multimedia Trusted Perception(多媒体可信感知关键实验室) Efficient Computing, Xiamen University(高效计算,厦门大学) Tencent Youtu Lab(腾讯优图实验室)

专题命中 指令微调 :language model(abstract)

Comments Accepted by ICML 2025

详情

展开后加载摘要…

URL PDF HTML 收藏