语言大模型 / LLM

Understanding Down Syndrome Stereotypes in LLM-Based Personas

理解基于大语言模型的虚拟人物中唐氏综合征刻板印象

Chantelle Wu, Peinan Wang, Nafi Nibras, Meida Li, Dajun Yuan, Zhixiao Wang, Jiahuan He, Mona Ali, Mirjana Prpa

专题命中 预训练与数据 ：LLM(title,abstract)；large language model(abstract)；language model(abstract)

AI总结 本文研究了基于大语言模型的虚拟人物中唐氏综合征刻板印象的形成与检测，通过访谈揭示训练数据和界面设计对刻板印象的影响，并强调了参与式方法的重要性。

Small Vocabularies, Big Gains: Pretraining and Tokenization in Time Series Models

Alexis Roger, Gwen Legate, Kashif Rasul, Yuriy Nevmyvaka, Irina Rish

专题命中 预训练与数据 ：pretraining(title,abstract)；foundation model(abstract)；分类 cs.CL、cs.AI、cs.LG

MTAttack: Multi-Target Backdoor Attacks against Large Vision-Language Models

Zihan Wang, Guansong Pang, Wenjun Miao, Jin Zheng, Xiao Bai

专题命中 预训练与数据 ：language model(title,abstract)；instruction tuning(abstract)；pretraining(abstract)

Comments AAAI2026, with supplementary material

An LLM-powered MILP modelling engine for workforce scheduling guided by expert knowledge

Qingyang Li, Lele Zhang, Vicky Mak-Hau

专题命中 预训练与数据 ：LLM(title,abstract)；large language model(abstract)；language model(abstract)

A Vision-Language Foundation Model for Leaf Disease Identification

Khang Nguyen Quoc, Lan Le Thi Thu, Luyl-Da Quach

专题命中 预训练与数据 ：foundation model(title,abstract)；language model(abstract)；pretraining(abstract)

Relative-Based Scaling Law for Neural Language Models

Baoqing Yue, Jinyuan Zhou, Zixi Wei, Jingtao Zhan, Qingyao Ai, Yiqun Liu

机构 * Tsinghua University（清华大学） 纠错

专题命中 预训练与数据 ：language model(title,abstract)；large language model(abstract)；分类 cs.CL、cs.AI、cs.LG

VideoAgentTrek: Computer Use Pretraining from Unlabeled Videos

Dunjie Lu, Yiheng Xu, Junli Wang, Haoyuan Wu, Xinyuan Wang, Zekun Wang, Junlin Yang, Hongjin Su, Jixuan Chen, Junda Chen, Yuchen Mao, Jingren Zhou, Junyang Lin, Binyuan Hui, Tao Yu

机构 * The University of Hong Kong（香港大学） ； Qwen Team, Alibaba Group（阿里巴巴集团Qwen团队） 纠错

专题命中 预训练与数据 ：pretraining(title,abstract)；SFT(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 8 pages, 6 figures

Exploring Influence Factors on LLM Suitability for No-Code Development of End User IoT Applications

Minghe Wang, Alexandra Kapp, Trever Schirmer, Tobias Pfandzelter, David Bermbach

专题命中 预训练与数据 ：LLM(title,abstract)；large language model(abstract)；language model(abstract)

Contrastive Decoding for Synthetic Data Generation in Low-Resource Language Modeling

Jannek Ulm, Kevin Du, Vésteinn Snæbjarnarson

机构 * ETH Zürich（苏黎世联邦理工学院） ； University of Copenhagen（哥本哈根大学） 纠错

专题命中 预训练与数据 ：language model(title,abstract)；large language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 13 pages, 3 figures

Self-Improving LLM Agents at Test-Time

Emre Can Acikgoz, Cheng Qian, Heng Ji, Dilek Hakkani-Tür, Gokhan Tur

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

专题命中 预训练与数据 ：LLM(title)；language model(abstract)；post-training(abstract)；分类 cs.CL、cs.AI、cs.LG

Unlocking In-Context Learning for Natural Datasets Beyond Language Modelling

Jelena Bratulić, Sudhanshu Mittal, David T. Hoffmann, Samuel Böhm, Robin Tibor Schirrmeister, Tonio Ball, Christian Rupprecht, Thomas Brox

机构 * Computer Vision Group, University of Freiburg（弗赖堡大学计算机视觉组） ； Neuromedical A.I. Lab, Medical Center -- University of Freiburg（弗赖堡大学医学神经AI实验室） ； Medical Physics, Medical Center -- University of Freiburg（弗赖堡大学医学物理） ； Visual Geometry Group, University of Oxford（牛津大学视觉几何组） 纠错

专题命中 预训练与数据 ：language model(title,abstract)；large language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Best Paper Honorable Mention at GCPR 2025 (German Conference on Pattern Recognition). This is the updated version submitted to the conference, not the official conference proceedings

VideoPASTA: 7K Preference Pairs That Matter for Video-LLM Alignment

Yogesh Kulkarni, Pooyan Fazli

机构 * Arizona State University（亚利桑那州立大学） 纠错

专题命中 预训练与数据 ：LLM(title)；language model(abstract)；pretraining(abstract)；preference optimization(abstract)

Comments EMNLP 2025 (Main)

Hopscotch: Discovering and Skipping Redundancies in Language Models

Mustafa Eyceoz, Nikhil Shivakumar Nayak, Hao Wang, Ligong Han, Akash Srivastava

机构 * Red Hat AI Innovation（红帽AI创新） 纠错

专题命中 预训练与数据 ：language model(title,abstract)；pretraining(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 10 pages, 4 figures, 9 tables

Recycling the Web: A Method to Enhance Pre-training Data Quality and Quantity for Language Models

Thao Nguyen, Yang Li, Olga Golovneva, Luke Zettlemoyer, Sewoong Oh, Ludwig Schmidt, Xian Li

机构 * FAIR at Meta（Meta 的 FAIR 研究所） ； University of Washington（华盛顿大学） ； Stanford University（斯坦福大学） 纠错

专题命中 预训练与数据 ：language model(title,abstract)；large language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted to COLM 2025

AutoVeriFix: Automatically Correcting Errors and Enhancing Functional Correctness in LLM-Generated Verilog Code

Yan Tan, Xiangchen Meng, Zijun Jiang, Yangdi Lyu

专题命中 预训练与数据 ：LLM(title,abstract)；large language model(abstract)；language model(abstract)

Synthetic vs. Gold: The Role of LLM Generated Labels and Data in Cyberbullying Detection

Arefeh Kazemi, Sri Balaaji Natarajan Kalaivendan, Joachim Wagner, Hamza Qadeer, Kanishk Verma, Brian Davis

机构 * School of Computing, ADAPT Centre, Dublin City University, Dublin, Ireland（计算学院、ADAPT中心、都柏林城市大学、都柏林、爱尔兰） 纠错

专题命中 预训练与数据 ：LLM(title)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI、cs.LG

ToolACE: Winning the Points of LLM Function Calling

Weiwen Liu, Xu Huang, Xingshan Zeng, Xinlong Hao, Shuai Yu, Dexun Li, Shuai Wang, Weinan Gan, Zhengying Liu, Yuanqing Yu, Zezhong Wang, Yuxian Wang, Wu Ning, Yutai Hou, Bin Wang, Chuhan Wu, Xinzhi Wang, Yong Liu, Yasheng Wang, Duyu Tang, Dandan Tu, Lifeng Shang, Xin Jiang, Ruiming Tang, Defu Lian, Qun Liu, Enhong Chen

机构 * Shanghai Jiao Tong University（上海交通大学） ； University of Science and Technology of China（中国科学技术大学） ； Huawei Noah’s Ark Lab（华为诺亚实验室） ； Huawei Technologies Co., Ltd（华为技术有限公司） ； Tsinghua University（清华大学） ； The Chinese University of Hong Kong（香港中文大学） 纠错

专题命中 预训练与数据 ：LLM(title)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 21 pages, 22 figures

TR-LLM: Integrating Trajectory Data for Scene-Aware LLM-Based Human Action Prediction

Kojiro Takeyama, Yimeng Liu, Misha Sra

专题命中 预训练与数据 ：LLM(title,abstract)；large language model(abstract)；language model(abstract)

Comments Accepted to IROS 2025

Random Initialization Can't Catch Up: The Advantage of Language Model Transfer for Time Series Forecasting

Roland Riachi, Kashif Rasul, Arjun Ashok, Prateek Humane, Alexis Roger, Andrew R. Williams, Yuriy Nevmyvaka, Irina Rish

机构 * University of Montreal（蒙特利尔大学） ； Mila - Québec AI Institute（魁北克人工智能研究所） ； McGill University（麦吉尔大学） 纠错

专题命中 预训练与数据 ：language model(title,abstract)；post-training(abstract)；分类 cs.CL、cs.AI、cs.LG

Assembly of Experts: Linear-time construction of the Chimera LLM variants with emergent and adaptable behaviors

Henrik Klagges, Robert Dahlke, Fabian Klemm, Benjamin Merkel, Daniel Klingmann, David A. Reiss, Dan Zecha

机构 * TNG Technology Consulting GmbH（TNG技术咨询公司） 纠错

专题命中 预训练与数据 ：LLM(title,abstract)；pretraining(abstract)；分类 cs.CL、cs.AI、cs.LG

Between Circuits and Chomsky: Pre-pretraining on Formal Languages Imparts Linguistic Biases

Michael Y. Hu, Jackson Petty, Chuan Shi, William Merrill, Tal Linzen

机构 * Center for Data Science（数据科学中心） ； Department of Linguistics（语言学系） 纠错

专题命中 预训练与数据 ：pretraining(title,abstract)；language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments ACL 2025 Camera Ready

Physics of Language Models: Part 1, Learning Hierarchical Language Structures

Zeyuan Allen-Zhu, Yuanzhi Li

专题命中 预训练与数据 ：language model(title,abstract)；pretraining(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments V2 polishes writing and adds Appendix G; V3 polishes writing and changes the title; V4 improves writing and adds Appendix H (more uniform attention results)

MAKE: Multi-Aspect Knowledge-Enhanced Vision-Language Pretraining for Zero-shot Dermatological Assessment

Siyuan Yan, Xieji Li, Ming Hu, Yiwen Jiang, Zhen Yu, Zongyuan Ge

机构 * Faculty of Engineering, Monash University, Melbourne, Australia（墨尔本大学工程学院） ； AIM for Health Lab, Monash University, Victoria, Australia（墨尔本大学健康人工智能实验室） 纠错

专题命中 预训练与数据 ：pretraining(title,abstract)；large language model(abstract)；language model(abstract)

Comments MICCAI2025 early acceptance; First two authors contribute equally

Impact of Noisy Supervision in Foundation Model Learning

Hao Chen, Zihan Wang, Ran Tao, Hongxin Wei, Xing Xie, Masashi Sugiyama, Bhiksha Raj, Jindong Wang

专题命中 预训练与数据 ：foundation model(title,abstract)；language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 18 pages, 10 figures, 6 tables, preprint. arXiv admin note: substantial text overlap with arXiv:2309.17002

Enhancing Leakage Attacks on Searchable Symmetric Encryption Using LLM-Based Synthetic Data Generation

Joshua Chiu, Partha Protim Paul, Zahin Wahab

专题命中 预训练与数据 ：LLM(title,abstract)；large language model(abstract)；language model(abstract)

Generative Multimodal Pretraining with Discrete Diffusion Timestep Tokens

Kaihang Pan, Wang Lin, Zhongqi Yue, Tenglong Ao, Liyu Jia, Wei Zhao, Juncheng Li, Siliang Tang, Hanwang Zhang

机构 * Zhejiang University（浙江大学） ； Nanyang Technological University（新加坡国立大学） ； Peking University（北京大学） ； Huawei Singapore Research Center（华为新加坡研究中心） 纠错

专题命中 预训练与数据 ：pretraining(title)；LLM(abstract)；large language model(abstract)；language model(abstract)

Comments Accepted by CVPR 2025 (Oral)

Investigating Vision-Language Model for Point Cloud-based Vehicle Classification

Yiqiao Li, Jie Wei, Camille Kamga

专题命中 预训练与数据 ：language model(title,abstract)；large language model(abstract)；prompting(abstract)

Comments 5 pages,3 figures, 1 table, CVPR DriveX workshop

Liquid: Language Models are Scalable and Unified Multi-modal Generators

Junfeng Wu, Yi Jiang, Chuofan Ma, Yuliang Liu, Hengshuang Zhao, Zehuan Yuan, Song Bai, Xiang Bai

专题命中 预训练与数据 ：language model(title,abstract)；LLM(abstract)；large language model(abstract)

Comments Technical report. Project page: https://foundationvision.github.io/Liquid/

Is Temporal Prompting All We Need For Limited Labeled Action Recognition?

Shreyank N Gowda, Boyan Gao, Xiao Gu, Xiaobo Jin

专题命中 预训练与数据 ：prompting(title,abstract)；language model(abstract)；pretraining(abstract)

Comments Accepted in CVPR-W 2025

LaMP: Language-Motion Pretraining for Motion Generation, Retrieval, and Captioning

Zhe Li, Weihao Yuan, Yisheng He, Lingteng Qiu, Shenhao Zhu, Xiaodong Gu, Weichao Shen, Yuan Dong, Zilong Dong, Laurence T. Yang

专题命中 预训练与数据 ：pretraining(title,abstract)；large language model(abstract)；language model(abstract)