语言大模型 / LLM

Scaling Dense Event-Stream Pretraining from Visual Foundation Models

从视觉基础模型扩展密集事件流预训练

Zhiwen Chen, Junhui Hou, Zhiyu Zhu, Jinjian Wu, Guangming Shi

机构 * City University of Hong Kong（香港城市大学） ； Xidian University（西安电子科技大学） 纠错

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

AI总结 本文提出一种基于视觉基础模型的自监督预训练方法，通过结构感知的蒸馏损失优化密集事件表示，显著提升下游任务性能。

Beyond Language Modeling: An Exploration of Multimodal Pretraining

超越语言模型：多模态预训练的探索

Shengbang Tong, David Fan, John Nguyen, Ellis Brown, Gaoyue Zhou, Shengyi Qian, Boyang Zheng, Théophane Vallaeys, Junlin Han, Rob Fergus, Naila Murray, Marjan Ghazvininejad, Mike Lewis, Nicolas Ballas, Amir Bar, Michael Rabbat, Jakob Verbeek, Luke Zettlemoyer, Koustuv Sinha, Yann LeCun, Saining Xie

机构 * FAIR, Meta（FAIR、Meta） ； New York University（纽约大学） 纠错

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

AI总结 本文通过多模态预训练探索，揭示了视觉与语言数据的互补性及统一预训练对世界建模的促进作用，并提出MoE架构解决多模态扩展的不对称性问题。

Comments Project website at https://beyond-llms.github.io/

SLM-S2ST: A multimodal language model for direct speech-to-speech translation

SLM-S2ST: 一种用于直接语音到语音翻译的多模态语言模型

Yuxuan Hu, Haibin Wu, Ruchao Fan, Xiaofei Wang, Heng Lu, Yao Qian, Jinyu Li

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

AI总结 SLM-S2ST是一种多模态语言模型，通过音频转换器头和流式 vocoder 实现高效的语音到语音翻译，实验表明其性能优于现有模型。

Comments Accepted by ASRU 2025

Chain-of-Caption: Training-free improvement of multimodal large language model on referring expression comprehension

Chain-of-Caption: 无需训练提升多模态大语言模型的指称表达理解

Yik Lung Pang, Changjae Oh

机构 * Queen Mary University of London（伦敦女王学院） 纠错

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

AI总结 本文提出无需训练的Chain-of-Caption框架，通过结合多种上下文提升多模态大语言模型在指称表达理解任务中的性能。

Comments 4 pages, 5 figures, 2 tables

Detecting Training Data of Large Language Models via Expectation Maximization

通过期望最大化检测大型语言模型的训练数据

Gyuwan Kim, Yang Li, Evangelia Spiliopoulou, Jie Ma, William Yang Wang

机构 * University of California, Santa Barbara（加州大学圣巴巴拉分校） ； AWS AI Lab（AWS人工智能实验室） 纠错

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

AI总结 本文提出EM-MIA方法，通过期望最大化策略检测大型语言模型的训练数据，实验表明其在分布重叠明显时表现优异，揭示了当前方法的局限性。

Comments EACL 2026

Ethical AI prompt recommendations in large language models using collaborative filtering

在大型语言模型中使用协同过滤进行伦理AI提示推荐

Jordan Nelson, Almas Baimagambetov, Konstantinos Avgerinakis, Nikolaos Polatidis

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

AI总结 本文提出利用协同过滤技术在大型语言模型中提升伦理提示推荐，通过合成数据集和用户互动减少偏见，解决伦理AI中的透明度和公平性问题。

Comments This paper has been accepted to by the International Journal of Parallel, Emergent & Distributed Systems (Taylor and Francis) and has an assigned DOI. We have already chose to make this open access using CC BY. The article is not yet available online on the publisher's website. The DOI is: doi.org/10.1080/17445760.2025.2573086

KinGuard: Hierarchical Kinship-Aware Fingerprinting to Defend Against Large Language Model Stealing

KinGuard：分层的亲属意识指纹法用于防御大语言模型窃取

Zhenhua Xu, Xiaoning Tian, Wenjun Zeng, Wenpeng Xing, Tianliang Lu, Gaolei Li, Chaochao Chen, Meng Han

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

AI总结 KinGuard通过构建基于亲属叙述的知识库，利用增量预训练内化知识，实现对大语言模型的高效且安全的指纹保护。

Comments Accepted by ICASSP2026

Are Large Language Models able to Predict Highly Cited Papers? Evidence from Statistical Publications

大语言模型能否预测高被引论文？来自统计出版物的证据

Zhanshuo Ye, Yiming Hou, Rui Pan, Tianchen Gao, Hansheng Wang

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

AI总结 本文通过大语言模型预测高被引论文，利用文本信息和结构化提示设计，展示了其在预测长期引用影响方面的有效性及局限性。

From Hype to Insight: Rethinking Large Language Model Integration in Visual Speech Recognition

从 hype 到 insight：重新思考大型语言模型在视觉语音识别中的整合

Rishabh Jain, Naomi Harte

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

AI总结 本研究通过系统评估发现，LLM解码器通过优化上下文推理提升性能，而非依赖视觉特征，强调需强化视觉编码器以推动VSR进展。

Comments Accepted for publication in ICASSP 2026

Large Language Models to Enhance Multi-task Drone Operations in Simulated Environments

大语言模型提升模拟环境中的多任务无人机操作

Yizhan Feng, Hichem Snoussi, Jing Teng, Abel Cherouat, Tian Wang

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

AI总结 本文提出利用大语言模型提升模拟环境中的无人机多任务操作效率，通过微调CodeT5模型实现自然语言到可执行代码的自动化翻译。

Comments 1st International Conference on Drones and Unmanned Systems (DAUS' 2025)

KidVis: Do Multimodal Large Language Models Possess the Visual Perceptual Capabilities of a 6-Year-Old?

KidVis: 多模态大语言模型是否具备六岁儿童的视觉感知能力？

Xianfeng Wang, Kaiwei Zhang, Qi Jia, Zijian Chen, Guangtao Zhai, Xiongkuo Min

机构 * Shanghai Jiao Tong University（上海交通大学） ； Shanghai AI Laboratory（上海人工智能实验室） 纠错

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

AI总结 KidVis研究通过对比人类儿童与多模态大语言模型在视觉能力上的表现，揭示了当前模型在基础视觉感知上的不足。

MoFa: A Unified Performance Modeling Framework for LLM Pretraining

MoFa: 一种统一的LLM预训练性能建模框架

Lu Zhao, Rong Shi, Shaoqing Zhang, Shangchao Su, Ziqing Yin, Zhiyan Cui, Hongfeng Sun, Baoguo He, Yueqiang Chen, Liang Dong, Xiyuan Li, Lingbin Wang, Lijun Ma, Qiang Huang, Ting Liu, Chong Wang, Can Wei

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

AI总结 MoFa提出一种统一的LLM预训练性能建模框架，整合多维优化特征和容错机制，通过增强的成本模型和调优系统，提升预训练性能预测精度并提供系统设计指导。

Part-X-MLLM: Part-aware 3D Multimodal Large Language Model

Chunshi Wang, Junliang Ye, Yunhan Yang, Yang Li, Zizhuo Lin, Jun Zhu, Zhuo Chen, Yawei Luo, Chunchao Guo

机构 * Zhejiang University（浙江大学） ； Tencent Hunyuan（腾讯文言） ； Tsinghua University（清华大学） ； The University of Hong Kong（香港大学） 纠错

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

DualSpeechLM: Towards Unified Speech Understanding and Generation via Dual Speech Token Modeling with Large Language Models

Yuanyuan Wang, Dongchao Yang, Yiwen Shao, Hangting Chen, Jiankun Zhao, Zhiyong Wu, Helen Meng, Xixin Wu

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

Comments Accepted by AAAI 2026

LongCat-Audio-Codec: An Audio Tokenizer and Detokenizer Solution Designed for Speech Large Language Models

Xiaohan Zhao, Hongyu Xiang, Shengze Ye, Song Li, Zhengkun Tian, Guanyu Chen, Ke Ding, Guanglu Wan

机构 * LongCat Team（LongCat团队） ； Meituan（美团） 纠错

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

Diversity-oriented Data Augmentation with Large Language Models

Zaitian Wang, Jinghan Zhang, Xinhao Zhang, Kunpeng Liu, Pengfei Wang, Yuanchun Zhou

机构 * Computer Network Information Center, CAS（中国科学院计算机网络信息中心） ； University of Chinese Academy of Sciences（中国科学院大学） ； Portland State University（波特兰州立大学） 纠错

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

Comments Accepted to ACL 2025

How human is the machine? Evidence from 66,000 Conversations with Large Language Models

Antonios Stamatogiannakis, Arsham Ghodsinia, Sepehr Etminanrad, Dilney Gonçalves, David Santos

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

DermINO: Hybrid Pretraining for a Versatile Dermatology Foundation Model

Jingkai Xu, De Cheng, Xiangqian Zhao, Jungang Yang, Zilong Wang, Xinyang Jiang, Xufang Luo, Lili Chen, Xiaoli Ning, Chengxu Li, Xinzhu Zhou, Xuejiao Song, Ang Li, Qingyue Xia, Zhou Zhuang, Hongfei Ouyang, Ke Xue, Yujun Sheng, Rusong Meng, Feng Xu, Xi Yang, Weimin Ma, Yusheng Lee, Dongsheng Li, Xinbo Gao, Jianming Liang, Lili Qiu, Nannan Wang, Xianbo Zuo, Cui Yong

机构 * Microsoft Research Asia（微软亚洲研究院） ； Peking University China-Japan Friendship School of Clinical Medicine（北京大学中国日友好临床医学学院） ； Scientific-skincare Innovation Alliance (SIA)（科学护肤创新联盟（SIA）） 纠错

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

Benchmarking Vision-Language and Multimodal Large Language Models in Zero-shot and Few-shot Scenarios: A study on Christian Iconography

Gianmarco Spinaci, Lukas Klic, Giovanni Colavizza

机构 * Gianmarco Spinaci Department of Classical Philology and Italian Studies, University of Bologna, Italy Villa i Tatti, The Harvard University Center for Italian Renaissance Studies, Florence, Italy（Gianmarco Spinaci 文艺复兴研究系，博洛尼亚大学，意大利 塔蒂别墅，哈佛大学意大利文艺复兴研究中心，佛罗伦萨，意大利） ； Lukas Klic Villa i Tatti, The Harvard University Center for Italian Renaissance Studies, Florence, Italy（Lukas Klic 塔蒂别墅，哈佛大学意大利文艺复兴研究中心，佛罗伦萨，意大利） ； Giovanni Colavizza Department of Classical Philology and Italian Studies, University of Bologna, Italy Department of Communication, University of Copenhagen, Denmark（Giovanni Colavizza 文艺复兴研究系，博洛尼亚大学，意大利 传播系，哥本哈根大学，丹麦） 纠错

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

Comments 11 pages, 2 figures

Predicting memorization within Large Language Models fine-tuned for classification

Jérémie Dentan, Davide Buscaldi, Aymen Shabou, Sonia Vanier

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

Comments This paper has been accepted for publication at ECAI 2025

Large Language Models Predict Human Well-being -- But Not Equally Everywhere

Pat Pataranutaporn, Nattavudh Powdthavee, Chayapatr Archiwaranguprok, Pattie Maes

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

Benchmarking Large Language Models for Handwritten Text Recognition

Giorgia Crosilla, Lukas Klic, Giovanni Colavizza

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

GenFair: Systematic Test Generation for Fairness Fault Detection in Large Language Models

Madhusudan Srinivasan, Jubril Abdel

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

Creative Writers' Attitudes on Writing as Training Data for Large Language Models

Katy Ilonka Gero, Meera Desai, Carly Schnitzler, Nayun Eom, Jack Cushman, Elena L. Glassman

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

Comments CHI 25

SPARC: Score Prompting and Adaptive Fusion for Zero-Shot Multi-Label Recognition in Vision-Language Models

Kevin Miller, Samarth Mishra, Aditya Gangrade, Kate Saenko, Venkatesh Saligrama

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

Stealing Training Data from Large Language Models in Decentralized Training through Activation Inversion Attack

Chenxi Dai, Lin Lu, Pan Zhou

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

Comments 12 pages, 5 figures

Bursting Filter Bubble: Enhancing Serendipity Recommendations with Aligned Large Language Models

Yunjia Xi, Muyan Weng, Wen Chen, Chao Yi, Dian Chen, Gaoyang Guo, Mao Zhang, Jian Wu, Yuning Jiang, Qingwen Liu, Yong Yu, Weinan Zhang

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

Comments 15 pages

Find Central Dogma Again: Leveraging Multilingual Transfer in Large Language Models

Wang Liang

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

Comments 31 pages,8 figures

Understanding and Evaluating Trust in Generative AI and Large Language Models for Spreadsheets

Simon Thorne

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

Journal ref Proceedings of the EuSpRIG 2024 Conference "Spreadsheet Productivity & Risks" ISBN : 978-1-905404-59-9

A Prompt-Engineered Large Language Model, Deep Learning Workflow for Materials Classification

Siyu Liu, Tongqi Wen, A. S. L. Subrahmanyam Pattamatta, David J. Srolovitz

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