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。

2025-10-15 至 2025-10-15 共收录 18 信号源:cs.CL, cs.AI, cs.LG

1. 指令微调 18 篇

2510.12178 2025-10-15 cs.AI cs.CL 91%

Evolution of meta's llama models and parameter-efficient fine-tuning of large language models: a survey

Abdulhady Abas Abdullah, Arkaitz Zubiaga, Seyedali Mirjalili, Amir H. Gandomi, Fatemeh Daneshfar, Mohammadsadra Amini, Alan Salam Mohammed, Hadi Veisi

机构 * University of Kurdistan(库尔德斯坦大学) Queen Mary University(女王玛丽大学) Torrens University Australia(澳大利亚托伦斯大学) University of Technology Sydney(悉尼技术大学) University of Kurdistan Sanandaj, Iran(伊朗桑和杰德大学) TU Dortmund University(多特蒙德技术大学) University of Kurdistan Hewler(库尔德斯坦大学海勒) Tehran University(德黑兰大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.12044 2025-10-15 cs.CL cs.AI 91%

Hierarchical Alignment: Surgical Fine-Tuning via Functional Layer Specialization in Large Language Models

Yukun Zhang, Qi Dong

机构 * The Chinese University of Hong Kong(香港中文大学) Fudan University(复旦大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.12004 2025-10-15 cs.CL cs.LG 91%

The Open Source Advantage in Large Language Models (LLMs)

Jiya Manchanda, Laura Boettcher, Matheus Westphalen, Jasser Jasser

机构 * Department of Philosophy and Religion(哲学与宗教系) Rollins College(罗林斯学院) Department of Mathematics and Computer Science(数学与计算机科学系)

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

Comments 9 pages, 1 figure

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.12245 2025-10-15 cs.LG cs.AI 86%

MoRA: On-the-fly Molecule-aware Low-Rank Adaptation Framework for LLM-based Multi-Modal Molecular Assistant

Tao Yin, Xiaohong Zhang, Jiacheng Zhang, Li Huang, Zhibin Zhang, Yuansong Zeng, Jin Xie, Meng Yan

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.07447 2025-10-15 cs.CV 85%

In the Eye of MLLM: Benchmarking Egocentric Video Intent Understanding with Gaze-Guided Prompting

Taiying Peng, Jiacheng Hua, Miao Liu, Feng Lu

机构 * State Key Laboratory of VR Technology and Systems, School of CSE, Beihang University(虚拟现实技术与系统国家重点实验室,北京航空航天大学计算机科学与工程学院) College of AI, Tsinghua University(清华大学人工智能学院)

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

Comments Accepted to NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.07146 2025-10-15 cs.LG cs.CL 84%

Attention-Aware GNN-based Input Defense against Multi-Turn LLM Jailbreak

Zixuan Huang, Kecheng Huang, Lihao Yin, Bowei He, Huiling Zhen, Mingxuan Yuan, Zili Shao

机构 * The Chinese University of Hong Kong(香港中文大学) Noah’s Ark Lab, Huawei(华为诺亚实验室) City University of Hong Kong(香港城市大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.12434 2025-10-15 cs.CV 83%

VideoRFT: Incentivizing Video Reasoning Capability in MLLMs via Reinforced Fine-Tuning

Qi Wang, Yanrui Yu, Ye Yuan, Rui Mao, Tianfei Zhou

机构 * Beijing Institute of Technology(北京理工大学) Shenzhen University(深圳大学)

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

Comments Accepted by NeurIPS 2025. Code: https://github.com/QiWang98/VideoRFT

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.02575 2025-10-15 cs.CL cs.CR cs.LG 82%

Cross-Modal Safety Alignment: Is textual unlearning all you need?

Trishna Chakraborty, Erfan Shayegani, Zikui Cai, Nael Abu-Ghazaleh, M. Salman Asif, Yue Dong, Amit K. Roy-Chowdhury, Chengyu Song

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

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

Comments Accepted by EMNLP 2024 Findings

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.11926 2025-10-15 cs.LG cs.AI 79%

Indoor Localization using Compact, Telemetry-Agnostic, Transfer-Learning Enabled Decoder-Only Transformer

Nayan Sanjay Bhatia, Pranay Kocheta, Russell Elliott, Harikrishna S. Kuttivelil, Katia Obraczka

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

Comments 11 pages, 12 Figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.12741 2025-10-15 cs.CV cs.DC 78%

Personalized Federated Fine-Tuning of Vision Foundation Models for Healthcare

Adam Tupper, Christian Gagné

机构 * Institut intelligence et données (IID)(智能与数据研究所) Université Laval(拉瓦尔大学) Mila - Quebec AI Institute(魁北克人工智能研究所)

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

Comments Accepted to the Symposium on Model Accountability, Sustainability and Healthcare (SMASH) 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.12798 2025-10-15 cs.CV 75%

Detect Anything via Next Point Prediction

Qing Jiang, Junan Huo, Xingyu Chen, Yuda Xiong, Zhaoyang Zeng, Yihao Chen, Tianhe Ren, Junzhi Yu, Lei Zhang

机构 * International Digital Economy Academy (IDEA)(国际数字经济学院(IDEA))

专题命中 指令微调 :post-training(abstract);SFT(abstract);prompting(abstract)

Comments homepage: https://rex-omni.github.io/

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.12266 2025-10-15 cs.LG cs.AI 73%

HiLoRA: Adaptive Hierarchical LoRA Routing for Training-Free Domain Generalization

Ziyi Han, Huanyu Wang, Zeyu Zhang, Xiangxiang Dai, Xutong Liu, John C. S. Lui

机构 * The Chinese University of Hong Kong, Hong Kong(香港中文大学) FSI Lab, Huawei Technologies Co., Ltd.(华为技术有限公司FSI实验室) Carnegie Mellon University, Pittsburgh, PA, USA(卡内基梅隆大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.11978 2025-10-15 cs.LG cs.AI 73%

Learning Dynamics of VLM Finetuning

Jusheng Zhang, Kaitong Cai, Jing Yang, Keze Wang

机构 * Sun Yat-sen University(中山大学) X-Era AI Lab(X-Era人工智能实验室)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2012.04182 2025-10-15 math.SG 71%

A landscape of contact manifolds via rational SFT

Agustin Moreno, Zhengyi Zhou

专题命中 指令微调 :SFT(title)

Comments Accepted version, to appear in G&T

Journal ref Geom. Topol. 29 (2025) 3465-3565

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.12251 2025-10-15 cs.CL 70%

DSAS: A Universal Plug-and-Play Framework for Attention Optimization in Multi-Document Question Answering

Jiakai Li, Rongzheng Wang, Yizhuo Ma, Shuang Liang, Guangchun Luo, Ke Qin

机构 * Institute of Intelligent Computing, University of Electronic Science and Technology of China(电子科技大学智能计算研究院) School of Information and Software Engineering, University of Electronic Science and Technology of China(电子科技大学信息与软件工程学院)

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

Comments 27 pages, has been accepted by NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.10666 2025-10-15 cs.CL cs.AI 62%

BrowserAgent: Building Web Agents with Human-Inspired Web Browsing Actions

Tao Yu, Zhengbo Zhang, Zhiheng Lyu, Junhao Gong, Hongzhu Yi, Xinming Wang, Yuxuan Zhou, Jiabing Yang, Ping Nie, Yan Huang, Wenhu Chen

机构 * CASIA UCAS University of Waterloo(大学水力研究所) Peking University(北京大学) Tsinghua University(清华大学)

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

Comments 10 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.16463 2025-10-15 cs.AI cs.CV 57%

Modular Embedding Recomposition for Incremental Learning

Aniello Panariello, Emanuele Frascaroli, Pietro Buzzega, Lorenzo Bonicelli, Angelo Porrello, Simone Calderara

机构 * AImageLab University of Modena and Reggio Emilia Italy(AImageLab 罗马那瓦尔大学)

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

Comments Accepted to the 36th British Machine Vision Conference (BMVC 2025), Sheffield, UK

详情

展开后加载摘要…

URL PDF HTML 收藏
2501.06031 2025-10-15 cs.CV 50%

Generate, Transduct, Adapt: Iterative Transduction with VLMs

Oindrila Saha, Logan Lawrence, Grant Van Horn, Subhransu Maji

机构 * University of Massachusetts, Amherst(马萨诸塞大学阿默斯特分校)

专题命中 指令微调 :language model(abstract)

Comments Code is released at https://github.com/cvl-umass/GTA-CLIP

详情

展开后加载摘要…

URL PDF HTML 收藏