arXivDaily arXiv每日学术速递 周一至周五更新

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。

共收录 7596 信号源:cs.CL, cs.AI, cs.LG

1. 知识编辑与模型理解 7596 篇

2506.07239 2025-07-01 cs.AR cs.AI 57%

VeriLoC: Line-of-Code Level Prediction of Hardware Design Quality from Verilog Code

Raghu Vamshi Hemadri, Jitendra Bhandari, Andre Nakkab, Johann Knechtel, Badri P Gopalan, Ramesh Narayanaswamy, Ramesh Karri, Siddharth Garg

机构 * New York University Tandon School of Engineering(纽约大学Tandon工程学院) New York University Abu Dhabi(纽约大学阿布扎克分校) Synopsys(Synopsys公司)

专题命中 知识编辑与模型理解 :LLM(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2501.10316 2025-07-01 cs.CL 57%

Know Your Mistakes: Towards Preventing Overreliance on Task-Oriented Conversational AI Through Accountability Modeling

Suvodip Dey, Yi-Jyun Sun, Gokhan Tur, Dilek Hakkani-Tur

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

专题命中 知识编辑与模型理解 :LLM(abstract);分类 cs.CL

Comments Accepted at ACL 2025 Main Conference

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.09338 2025-06-30 cs.CL 57%

Llama See, Llama Do: A Mechanistic Perspective on Contextual Entrainment and Distraction in LLMs

Jingcheng Niu, Xingdi Yuan, Tong Wang, Hamidreza Saghir, Amir H. Abdi

机构 * University of Toronto(多伦多大学) Technical University of Darmstadt(达姆施塔特技术大学) Microsoft(微软公司)

专题命中 知识编辑与模型理解 :language model(abstract);分类 cs.CL

Comments ACL 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.12374 2025-06-25 cs.RO cs.AI 57%

AntiGrounding: Lifting Robotic Actions into VLM Representation Space for Decision Making

Wenbo Li, Shiyi Wang, Yiteng Chen, Huiping Zhuang, Qingyao Wu

机构 * School of Software Engineering, South China University of Technology(软件工程学院,华南理工大学) School of Future Technology, South China University of Technology(未来技术学院,华南理工大学) Shien-Ming Wu School of Intelligent Engineering, South China University of Technology(智能工程学院,华南理工大学)

专题命中 知识编辑与模型理解 :language model(abstract);分类 cs.AI

Comments submitted to NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.13816 2025-06-25 cs.CL 57%

Analyzing LLMs' Knowledge Boundary Cognition Across Languages Through the Lens of Internal Representations

Chenghao Xiao, Hou Pong Chan, Hao Zhang, Mahani Aljunied, Lidong Bing, Noura Al Moubayed, Yu Rong

机构 * DAMO Academy, Alibaba Group(阿里巴巴集团达摩院) Department of Computer Science, Durham University(杜伦大学计算机科学系) Hupan Lab, Hangzhou, China(杭州实验室)

专题命中 知识编辑与模型理解 :LLM(abstract);分类 cs.CL

Comments ACL 2025 main; camera ready

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.18053 2025-06-24 cs.CR cs.AI 57%

Mechanistic Interpretability in the Presence of Architectural Obfuscation

Marcos Florencio, Thomas Barton

机构 * INTELI – Institute of Technology and Leadership(INTELI — 技术与领导力研究所)

专题命中 知识编辑与模型理解 :LLM(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.18369 2025-06-24 cs.RO cs.AI cs.CV cs.SY eess.SY 57%

G3Flow: Generative 3D Semantic Flow for Pose-aware and Generalizable Object Manipulation

Tianxing Chen, Yao Mu, Zhixuan Liang, Zanxin Chen, Shijia Peng, Qiangyu Chen, Mingkun Xu, Ruizhen Hu, Hongyuan Zhang, Xuelong Li, Ping Luo

机构 * The University of Hong Kong(香港大学) Institute of Artificial Intelligence (TeleAI), China Telecom(人工智能研究所(TeleAI),中国电信) Shenzhen University(深圳大学) AgileX Robotics(AgileX机器人) GDIIST HKU Shanghai Intelligent Computing Research Center(香港大学上海智能计算研究中心)

专题命中 知识编辑与模型理解 :foundation model(abstract);分类 cs.AI

Comments Webpage: https://tianxingchen.github.io/G3Flow/, accepted to CVPR 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.16652 2025-06-23 cs.RO cs.CV cs.LG cs.SE 57%

CodeDiffuser: Attention-Enhanced Diffusion Policy via VLM-Generated Code for Instruction Ambiguity

Guang Yin, Yitong Li, Yixuan Wang, Dale McConachie, Paarth Shah, Kunimatsu Hashimoto, Huan Zhang, Katherine Liu, Yunzhu Li

机构 * Columbia University(哥伦比亚大学) Toyota Research Institute(丰田研究院) University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校) Tsinghua University(清华大学)

专题命中 知识编辑与模型理解 :language model(abstract);分类 cs.LG

Comments Accepted to Robotics: Science and Systems (RSS) 2025. The first three authors contributed equally. Project Page: https://robopil.github.io/code-diffuser/

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.15156 2025-06-19 cs.CL 57%

Emergence of Primacy and Recency Effect in Mamba: A Mechanistic Point of View

Muhammad Cendekia Airlangga, Hilal AlQuabeh, Munachiso S Nwadike, Kentaro Inui

机构 * MBZUAI RIKEN(日本研究机构) Tohoku University(东北大学)

专题命中 知识编辑与模型理解 :language model(abstract);分类 cs.CL

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.06761 2025-06-19 cs.LG cs.CV 57%

The OCR Quest for Generalization: Learning to recognize low-resource alphabets with model editing

Adrià Molina Rodríguez, Oriol Ramos Terrades, Josep Lladós

机构 * Centre de Visió per Computador (CVC)(计算机视觉中心) Computer Science Department, Universitat Autònoma de Barcelona(计算机科学系,巴塞罗那自治大学)

专题命中 知识编辑与模型理解 :pretraining(abstract);分类 cs.LG

Comments Preprint (under review) For Journal

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.09813 2025-06-17 cs.LG cs.GT 57%

Metritocracy: Representative Metrics for Lite Benchmarks

Ariel Procaccia, Benjamin Schiffer, Serena Wang, Shirley Zhang

机构 * Paulson School of Engineering and Applied Sciences, Harvard University(哈佛大学工程与应用科学学院)

专题命中 知识编辑与模型理解 :LLM(abstract);分类 cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.07086 2025-06-10 cs.CL 57%

Representation Decomposition for Learning Similarity and Contrastness Across Modalities for Affective Computing

Yuanhe Tian, Pengsen Cheng, Guoqing Jin, Lei Zhang, Yan Song

机构 * University of Washington(华盛顿大学) Sichuan University(四川大学) People’s Daily Online(人民日报网络) University of Science and Technology of China(中国科学技术大学)

专题命中 知识编辑与模型理解 :LLM(abstract);分类 cs.CL

Comments 13 pages, 4 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.04047 2025-06-10 cs.CL 57%

On Support Samples of Next Word Prediction

Yuqian Li, Yupei Du, Yufang Liu, Feifei Feng, Mou Xiao Feng, Yuanbin Wu

机构 * School of Computer Science and Technology, East China Normal University(东华大学计算机科学与技术学院) Utrecht University(乌特勒支大学) Midea Group(美的集团)

专题命中 知识编辑与模型理解 :language model(abstract);分类 cs.CL

Comments Accepted to ACL2025(Main Conference)

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.16201 2025-06-10 stat.ML cs.LG 57%

Theoretical Limitations of Ensembles in the Age of Overparameterization

Niclas Dern, John P. Cunningham, Geoff Pleiss

专题命中 知识编辑与模型理解 :prompting(abstract);分类 cs.LG

Comments Accepted for publication at ICML 2025. 33 pages, 17 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.06822 2025-06-10 cs.CV cs.AI 57%

Hi-LSplat: Hierarchical 3D Language Gaussian Splatting

Chenlu Zhan, Yufei Zhang, Gaoang Wang, Hongwei Wang

机构 * College of Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术学院) College of Biomedical Engineering and Instrument Science, Zhejiang University(浙江大学生物医学工程与仪器科学学院) Zhejiang University-University of Illinois Urbana-Champaign Institute, Zhejiang University(浙江大学-伊利诺伊大学厄巴纳-香槟分校联合研究所)

专题命中 知识编辑与模型理解 :foundation model(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.05597 2025-06-09 cs.LG 57%

FaCTR: Factorized Channel-Temporal Representation Transformers for Efficient Time Series Forecasting

Yash Vijay, Harini Subramanyan

专题命中 知识编辑与模型理解 :pretraining(abstract);分类 cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.04627 2025-06-05 physics.comp-ph cs.LG physics.data-an 57%

Is the end of Insight in Sight ?

Jean-Michel Tucny, Mihir Durve, Sauro Succi

机构 * Department of Civil, Computer Science, and Aeronautical Technologies Engineering, Università degli Studi Roma Tre(罗马三大学土木、计算机科学与航空技术工程系) Center for Life Nano- & Neuro-Science, Italian Institute of Technology (IIT)(生命纳米与神经科学中心,意大利理工学院)

专题命中 知识编辑与模型理解 :prompting(abstract);分类 cs.LG

Comments 15 pages, 2 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.02744 2025-06-04 cs.CE cs.AI 57%

Enriching Location Representation with Detailed Semantic Information

Junyuan Liu, Xinglei Wang, Tao Cheng

机构 * SpaceTimeLab, University College London, UK(SpaceTimeLab,伦敦大学学院,英国)

专题命中 知识编辑与模型理解 :foundation model(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.02138 2025-06-04 cs.LG 57%

Revisiting LRP: Positional Attribution as the Missing Ingredient for Transformer Explainability

Yarden Bakish, Itamar Zimerman, Hila Chefer, Lior Wolf

机构 * Tel-Aviv University(特拉维夫大学)

专题命中 知识编辑与模型理解 :foundation model(abstract);分类 cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.01902 2025-06-03 cs.CV cs.CL 57%

Enhancing Biomedical Multi-modal Representation Learning with Multi-scale Pre-training and Perturbed Report Discrimination

Xinliu Zhong, Kayhan Batmanghelich, Li Sun

专题命中 知识编辑与模型理解 :language model(abstract);分类 cs.CL

Comments 6 pages, 1 figure, accepted by 2024 IEEE Conference on Artificial Intelligence (CAI)

Journal ref 2024 IEEE Conference on Artificial Intelligence (CAI), 2024, 480-485

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.22506 2025-05-29 cs.LG 57%

Sparsification and Reconstruction from the Perspective of Representation Geometry

Wenjie Sun, Bingzhe Wu, Zhile Yang, Chengke Wu

机构 * Shenzhen Institute of Advanced Technology, CAS(深圳先进技术研究院, 中国科学院)

专题命中 知识编辑与模型理解 :language model(abstract);分类 cs.LG

Comments 24 pages, 5 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.19472 2025-05-29 cs.CL 57%

Balancing Computation Load and Representation Expressivity in Parallel Hybrid Neural Networks

Mohammad Mahdi Moradi, Walid Ahmed, Shuangyue Wen, Sudhir Mudur, Weiwei Zhang, Yang Liu

机构 * Department of Computer Science, Concordia University(康科德大学计算机科学系) Ascend Team, Huawei Technologies(华为技术有限公司Ascend团队)

专题命中 知识编辑与模型理解 :language model(abstract);分类 cs.CL

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.20199 2025-05-27 cs.CL 57%

Adaptive Classifier-Free Guidance via Dynamic Low-Confidence Masking

Pengxiang Li, Shilin Yan, Joey Tsai, Renrui Zhang, Ruichuan An, Ziyu Guo, Xiaowei Gao

机构 * PolyU FDU THU CUHK PKU ICL

专题命中 知识编辑与模型理解 :language model(abstract);分类 cs.CL

Comments Project page: https://github.com/pixeli99/A-CFG

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.17812 2025-05-26 cs.CV cs.AI 57%

Seeing It or Not? Interpretable Vision-aware Latent Steering to Mitigate Object Hallucinations

Boxu Chen, Ziwei Zheng, Le Yang, Zeyu Geng, Zhengyu Zhao, Chenhao Lin, Chao Shen

专题命中 知识编辑与模型理解 :language model(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.17529 2025-05-26 cs.CV cs.AI 57%

Do You Keep an Eye on What I Ask? Mitigating Multimodal Hallucination via Attention-Guided Ensemble Decoding

Yeongjae Cho, Keonwoo Kim, Taebaek Hwang, Sungzoon Cho

机构 * Seoul National University(首尔国立大学) Kim & Chang AI&IT System Center(金·昌AI&IT系统中心) Waddle Corporation(Waddle公司)

专题命中 知识编辑与模型理解 :language model(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.16386 2025-05-23 cs.LG 57%

Omni TM-AE: A Scalable and Interpretable Embedding Model Using the Full Tsetlin Machine State Space

Ahmed K. Kadhim, Lei Jiao, Rishad Shafik, Ole-Christoffer Granmo

机构 * Department of ICT University of Agder(信息与通信技术系阿格德大学) School of Engineering Newcastle University(工程学院新castle大学)

专题命中 知识编辑与模型理解 :language model(abstract);分类 cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2501.17822 2025-05-22 eess.IV cs.AI cs.CV cs.IR q-bio.QM 57%

Aggregation Schemes for Single-Vector WSI Representation Learning in Digital Pathology

Sobhan Hemati, Ghazal Alabtah, Saghir Alfasly, H. R. Tizhoosh

机构 * KIMIA Lab, Department of Artificial Intelligence and Informatics, Mayo Clinic(KIMIA实验室,人工智能与信息学系, Mayo诊所)

专题命中 知识编辑与模型理解 :foundation model(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.14352 2025-05-21 cs.LG 57%

Towards eliciting latent knowledge from LLMs with mechanistic interpretability

Bartosz Cywiński, Emil Ryd, Senthooran Rajamanoharan, Neel Nanda

专题命中 知识编辑与模型理解 :language model(abstract);分类 cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.14341 2025-05-21 cs.CV cs.AI 57%

Replace in Translation: Boost Concept Alignment in Counterfactual Text-to-Image

Sifan Li, Ming Tao, Hao Zhao, Ling Shao, Hao Tang

机构 * Liaoning University(辽宁大学) Nanjing University of Posts and Telecommunications(南京邮电大学) Tsinghua University(清华大学) University of Chinese Academy of Sciences(中国科学院大学) Peking University(北京大学)

专题命中 知识编辑与模型理解 :language model(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.10081 2025-05-21 cs.CL 57%

Designing and Contextualising Probes for African Languages

Wisdom Aduah, Francois Meyer

机构 * African Institute for Mathematical Sciences South Africa(非洲数学科学研究所南非分所) Department of Computer Science(计算机科学系) University of Cape Town(开普敦大学)

专题命中 知识编辑与模型理解 :language model(abstract);分类 cs.CL

详情

展开后加载摘要…

URL PDF HTML 收藏