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。

共收录 12393 信号源:cs.CL, cs.AI, cs.LG

1. 预训练与数据 12393 篇

2607.07001 2026-07-09 cs.CV 新提交 82%

Ego-Human Motion Prediction with 3D-Aware LLM

基于3D感知语言模型的自我-人类运动预测

Yujin Bae, Jaewoo Jeong, Hyeonseong Kim, Kuk-Jin Yoon

机构 * Visual Intelligence Lab., KAIST(视觉智能实验室,韩国科学技术院)

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

AI总结 研究从自我中心视角预测人类运动问题,提出Ego3DLM模型,基于准确运动预测需3D环境理解及姿势语言整体预测原则,通过三阶段训练,在相关任务中取得领先性能,实现跨模态和时间一致的运动预测。

Comments Accepted to ECCV 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.17390 2026-07-09 cs.CV 版本更新 82%

FMMC: Harnessing the Power of Foundation Models for Accurate Material Classification

利用基础模型提升材料分类的准确性

Qingran Lin, Fengwei Yang, Chaolun Zhu

机构 * Georgia Institute of Technology(佐治亚理工学院) Duke University(杜克大学) Waseda University(早稻田大学)

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

AI总结 本文提出一种利用基础模型克服数据限制并提升分类准确性的新框架,通过生成高质量数据集和融合视觉语言模型先验知识,有效提高材料分类性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.10547 2026-07-08 cs.SD 版本更新 82%

HeartMuLa: A Family of Open Sourced Music Foundation Models

HeartMuLa:一个开源音乐基础模型家族

Dongchao Yang, Yuxin Xie, Yuguo Yin, Zheyu Wang, Xiaoyu Yi, Gongxi Zhu, Xiaolong Weng, Zihan Xiong, Yingzhe Ma, Dading Cong, Jingliang Liu, Zihang Huang, Jinghan Ru, Rongjie Huang, Haoran Wan, Peixu Wang, Kuoxi Yu, Helin Wang, Liming Liang, Xianwei Zhuang, Yuanyuan Wang, Dingdong Wang, Haohan Guo, Junjie Cao, Zeqian Ju, Songxiang Liu, Yuewen Cao, Heming Weng, Yuexian Zou

机构 * HeartMuLa Teams(HeartMuLa团队)

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

AI总结 介绍开源音乐基础模型家族HeartMuLa,含四个组件及两种特殊模式,能跨任务和模态推动音乐理解与生成,扩展到7B参数时有显著改进,可重现商业级系统,为未来研究提供基线并促进多模态应用。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.05247 2026-07-07 cs.CV 新提交 82%

Vision Pretraining for Dense Spatial Perception

面向稠密空间感知的视觉预训练

Zelin Fu, Bin Tan, Changjiang Sun, Shaohui Liu, Kecheng Zheng, Yinghao Xu, Xing Zhu, Yujun Shen, Nan Xue

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

AI总结 针对现有视觉基础模型牺牲空间细节理解的问题,提出以边界为中心的掩码边界建模自监督预训练范式,提升稠密空间感知能力与下游任务性能。

Comments Tech report, 31 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.02513 2026-07-03 cs.CL cs.AI cs.LG 新提交 82%

LACUNA: A Testbed for Evaluating Localization Precision for LLM Unlearning

LACUNA: 评估大语言模型遗忘定位精度的测试平台

Matteo Boglioni, Thibault Rousset, Siva Reddy, Marius Mosbach, Verna Dankers

机构 * Mila – Quebec Artificial Intelligence Institute(米拉-魁北克人工智能研究所) McGill University(麦吉尔大学)

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

AI总结 提出LACUNA测试平台,通过注入合成个人身份信息到模型参数,评估遗忘方法是否真正擦除知识,发现现有方法定位不精确且易受重现攻击,而精确定位可实现强擦除。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.30457 2026-06-30 cs.RO 82%

Behavior Prompting Policy: Demonstrations as Prompts for Manipulation

行为提示策略:将演示作为操作提示

Austin Patel, Ben Pekarek, Joel Enrique Castro Hernandez, Shuran Song

机构 * Stanford University(斯坦福大学) University of California, Berkeley(加州大学伯克利分校)

专题命中 预训练与数据 :prompting(title,abstract)

AI总结 提出行为提示策略(BPP),通过单次人类演示(行为提示)使机器人推理时执行新任务,结合手持操作接口iPhUMI收集多样化数据,在DrawAnything和LIBERO-Gen基准上验证零样本适应能力。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.28103 2026-06-29 cond-mat.dis-nn cond-mat.stat-mech 新提交 82%

Phase structure of the Random Language Model

随机语言模型的相结构

Alessio Giorlandino, Eric De Giuli, Sebastian Goldt

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

AI总结 通过双标度极限分析,揭示随机语言模型存在一系列相变,包括符号关联涌现、单符号边缘分布非均匀化以及规则使用的玻璃态冻结,并导出与大型语言模型一致的标度律。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.27100 2026-06-26 q-fin.MF 新提交 82%

Pretrained Time-Series Foundation Models for Financial Return Forecasting

用于金融收益预测的预训练时间序列基础模型

Miquel Noguer I Alonso, Rodolfo Pereira Franklin

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

AI总结 本文在保守的金融设置下,基准测试预训练时间序列基础模型(TSFMs)与从头训练的神经基线,发现TSFMs在排名上占优,但相对于随机游走基准的预测提升微弱且稀疏,表明TSFMs作为实用先验可降低模型开发成本,但并非统计可靠的alpha生成引擎。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.22660 2026-06-23 cs.CV 新提交 82%

Prompting Diffusion Models for Zero-Shot Instance Segmentation

提示扩散模型用于零样本实例分割

Irem Zeynep Alagöz, Nils Morbitzer, Andrea Ramazzina, Nassir Navab, Federico Tombari, Stefano Gasperini

机构 * Technical University of Munich (TUM)(慕尼黑工业大学) Munich Center of Machine Learning (MCML)(慕尼黑机器学习中心) Mercedes-Benz AG(梅赛德斯-奔驰集团) Visualais

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

AI总结 提出Prompt2Seg框架,通过空间条件化增强扩散模型,利用2D高斯或置信度图作为提示,实现零样本实例分割,在多个数据集上优于基线。

Comments Under review

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.27465 2026-06-18 q-bio.GN 版本更新 82%

Poisoning the Genome: Targeted Backdoor Attacks on DNA Foundation Models

基因组投毒:针对DNA基础模型的目标后门攻击

Charalampos Koilakos, Ioannis Mouratidis, Ilias Georgakopoulos-Soares

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

AI总结 本研究首次系统研究基因组语言模型的训练数据投毒,通过在预训练和微调阶段注入少于1%的对抗序列,可选择性破坏目标基因组上下文的生成性能,并实现条件后门攻击和下游任务分类破坏。

Comments 23 pages, double column format

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.12678 2026-06-16 cs.CV cs.CY 版本更新 82%

No One Knows the State of the Art in Geospatial Foundation Models

没有人知道地理空间基础模型的现状

Isaac Corley, Nils Lehmann, Caleb Robinson, Gabriel Tseng, Anthony Fuller, Hamed Alemohammad, Evan Shelhamer, Jennifer Marcus, Hannah Kerner

机构 * Taylor Geospatial(泰勒地理空间公司) Technical University of Munich(慕尼黑技术大学) Microsoft AI for Good Research Lab(微软AI for Good研究实验室) Allen Institute for AI(艾伦人工智能研究所) Vector Institute(向量研究所) Carleton University(卡尔顿大学) Clark University(克拉克大学) University of British Columbia(不列颠哥伦比亚大学) Arizona State University(亚利桑那州立大学)

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

AI总结 本文指出地理空间基础模型缺乏标准化评估和训练协议,提出六项具体期望以促进社区共识。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.04061 2026-06-16 cs.RO cs.CV 版本更新 82%

CLAP: Contrastive Latent Action Pretraining for Learning Vision-Language-Action Models from Human Videos

CLAP: 从人类视频中学习视觉-语言-动作模型的对比潜在动作预训练

Chubin Zhang, Jianan Wang, Zifeng Gao, Yue Su, Tianru Dai, Cai Zhou, Jiwen Lu, Yansong Tang

机构 * Tsinghua University(清华大学) Astribot University of Hong Kong(香港大学) Massachusetts Institute of Technology(麻省理工学院)

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

AI总结 提出CLAP框架,通过对比学习将人类视频与机器人动作词汇对齐,利用伪标签训练VLA模型,实现从人类视频到机器人执行的有效技能迁移。

Comments The code is available at: https://github.com/LinShan-Bin/OpenCLAP

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.12366 2026-06-11 cs.RO 新提交 82%

APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies

APT: 动作专家预训练提升视觉-语言-动作策略的指令泛化能力

Kechun Xu, Zhenjie Zhu, Anzhe Chen, Rong Xiong, Yue Wang

机构 * Zhejiang University(浙江大学) Zhejiang Humanoid Robot Innovation Center(浙江人形机器人创新中心)

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

AI总结 针对连续动作专家模型对分布外语言指令泛化差的问题,提出APT两阶段训练方法,先预训练动作专家作为视觉-动作先验,再通过门控融合注入语言,显著提升泛化性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.01747 2026-06-11 eess.SP 版本更新 82%

AnyPPG: An ECG-Guided PPG Foundation Model Trained on Over 100,000 Hours of Recordings for Holistic Health Profiling

AnyPPG:基于心电引导的PPG基础模型,在超过10万小时记录上训练,用于全面健康分析

Guangkun Nie, Xiaocheng Fang, Gongzheng Tang, Yujie Xiao, Jun Li, Bo Liu, Hongyan Li, Shenda Hong

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

AI总结 提出AnyPPG,一种基于心电引导预训练的光电容积描记(PPG)基础模型,在超10万小时数据上训练,首次开展覆盖1468种疾病表型的全表型关联研究,证明PPG可超越传统心血管应用,对307种表型(含230种非循环系统疾病)实现有效判别。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.10846 2026-06-10 cs.CR cs.SE 新提交 82%

Securing Code Understanding: Detecting Natural Backdoor Vulnerability in Code Language Models

保障代码理解安全:检测代码语言模型中的自然后门漏洞

Yuchen Chen, Weisong Sun, Haocheng Huang, Yuan Xiao, Chunrong Fang, Yiran Zhang, Tingting Xu, Zhenpeng Chen, An Guo, Peizhuo Lv, Xiaofang Zhang, Zhenyu Chen, Yang Liu, Baowen Xu

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

AI总结 本研究系统探究代码语言模型中的自然后门漏洞,通过44种场景证明其普遍性,分析其与注入后门的差异及迁移性,并提出检测方法ScanNBT。

Comments Accepted to IEEE Transactions on Software Engineering (TSE)

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.14028 2026-06-05 cs.CV 82%

Unified Pix Token And Word Token Generative Language Model

统一像素标记与词标记的生成语言模型

Haun Leung, ZiNan Wang

机构 * Buaa.edu.cn(北京航空航天大学)

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

AI总结 本文提出一种统一像素标记和词标记的生成语言模型,通过引入图像无监督预训练、颜色折叠、全局条件注意力近似等方法,提升模型在图像细节识别上的能力,实验表明该模型在小模型和有限数据下仍表现优异。

Comments 13 pages, 6 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.22841 2026-06-03 cs.CV 82%

How Much of a Model Do We Need? Redundancy and Slimmability in Remote Sensing Foundation Models

我们需要多少模型?遥感基础模型中的冗余与可瘦身性

Leonard Hackel, Tom Burgert, Begüm Demir

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

AI总结 通过后验瘦身(均匀减少编码器Transformer块宽度)评估8个遥感基础模型的表示冗余,发现遥感模型在激进宽度缩减下仍保持69%-109%相对精度,而自然图像预训练模型性能急剧下降,表明遥感模型存在冗余编码且可有效瘦身。

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.07617 2026-06-02 cs.CV 82%

Scaling Pre-training to One Hundred Billion Data for Vision Language Models

将视觉语言模型的预训练扩展到一千亿数据

Xiao Wang, Ibrahim Alabdulmohsin, Daniel Salz, Zhe Li, Keran Rong, Xiaohua Zhai

机构 * Google DeepMind(谷歌DeepMind)

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

AI总结 本文通过实验探究将视觉语言模型预训练数据扩展到一千亿规模的效果,发现传统基准性能饱和,但文化多样性任务和低资源语言受益显著,并指出质量过滤可能减少文化多样性。

Comments v2: CVPR Findings'26

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.26992 2026-05-27 cs.CV 82%

On the Robustness of Machine Unlearning for Vision-Language Models

机器遗忘在视觉-语言模型中的鲁棒性研究

Yujie Lin, Kaidi Jia, Jiayao Ma, Chengyi Yang, Jinsong Su

机构 * Xiamen University(厦门大学)

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

AI总结 本文首次系统调查了视觉-语言模型机器遗忘的鲁棒性,通过提出三种攻击范式揭示现有方法往往隐藏而非彻底移除目标知识。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.19673 2026-05-27 cs.CV 82%

InHabit: Leveraging Image Foundation Models for Scalable 3D Human Placement

InHabit: 利用图像基础模型实现可扩展的3D人体放置

Nikita Kister, Pradyumna YM, István Sárándi, Jiayi Wang, Anna Khoreva, Gerard Pons-Moll

机构 * Bosch Center of Artificial Intelligence(博世人工智能中心) Max Planck Institute for Informatics(马克斯·普朗克信息学院)

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

AI总结 提出InHabit方法,通过渲染-生成-提升流程利用2D基础模型知识自动生成3D场景中与几何一致的人体交互数据,并构建大规模数据集InHabitants,显著提升3D人体-场景重建和接触估计性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.25374 2026-05-26 cs.SE 82%

Leveraging Language Models for Log Statement Generation in Multilingual Scenarios: How Far Are We?

利用语言模型在多语言场景下生成日志语句:我们走了多远?

Kazuki Kusama, Honglin Shu, Masanari Kondo, Yasutaka Kamei

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

AI总结 本文通过构建包含五种编程语言的多语言基准,比较评估了三种最先进的日志语句生成方法和五个大型语言模型,发现UniLog方法在多语言环境中表现最佳,并揭示了不同语言间日志生成难度的差异源于日志插入分布和语言特定日志习惯,指出单纯扩大模型规模或训练数据量不足以解决多语言日志生成问题,需针对目标语言特性设计方法。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.25242 2026-05-26 q-bio.GN 82%

C3P: Contrastive promoter-protein pretraining yields representations capturing bacterial gene regulation

C3P: 对比启动子-蛋白质预训练产生捕捉细菌基因调控的表征

Cameron Dufault, Scott Xu, Alan M. Moses

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

AI总结 提出对比启动子-蛋白质预训练(C3P),通过对齐启动子与对应蛋白质来学习细菌调控序列表征,在调控注释推断和零样本共调控基因检索中显著优于基因组语言模型。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.21906 2026-05-25 cs.CV 82%

Universal CT Representations from Anatomy to Disease Phenotype through Agglomerative Pretraining

从解剖到疾病表型的通用CT表示:通过聚合预训练

Yuheng Li, Yuan Gao, Haoyu Dong, Yuxiang Lai, Shansong Wang, Mojtaba Safari, James E. Baciak, Xiaofeng Yang

机构 * Wallace H. Coulter Department of Biomedical Engineering, Georgia Institute of Technology and Emory University(沃森·H·库勒生物医学工程系,佐治亚理工学院和埃默里大学) Department of Radiation Oncology and Winship Cancer Institute, Emory University(放射肿瘤学系和Winship癌症研究所,埃默里大学) Department of Electrical and Computer Engineering, Duke University(电气与计算机工程系,杜克大学) Department of Computer Science and Informatics, Emory University(计算机科学与信息学系,埃默里大学) Department of Materials Science & Engineering, Nuclear Engineering Program, University of Florida(材料科学与工程系、核工程项目,佛罗里达大学)

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

AI总结 提出FlexiCT系列CT基础模型,通过三阶段聚合连续预训练(二维轴向、三维解剖、报告引导语义对齐)统一CT分析,在分割、分类、配准、视觉语言理解和临床检索等任务上达到或超越专用模型,并捕获与肿瘤分期相关的影像特征。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.11679 2026-05-25 cs.CV 82%

Towards Brain MRI Foundation Models for the Clinic: Findings from the FOMO25 Challenge

面向临床的大脑MRI基础模型:来自FOMO25挑战赛的发现

Asbjørn Munk, Stefano Cerri, Vardan Nersesjan, Christian Hedeager Krag, Jakob Ambsdorf, Pablo Rocamora García, Julia Machnio, Peirong Liu, Suhyun Ahn, Nasrin Akbari, Yasmina Al Khalil, Kimberly Amador, Sina Amirrajab, Tal Arbel, Meritxell Bach Cuadra, Ujjwal Baid, Bhakti Baheti, Jaume Banus, Kamil Barbierik, Christoph Brune, Yansong Bu, Baptiste Callard, Yuhan Chen, Cornelius Crijnen, Corentin Dancette, Peter Drotar, Prasad Dutande, Nils D. Forkert, Saurabh Garg, Jakub Gazda, Matej Gazda, Benoît Gérin, Partha Ghosh, Weikang Gong, Pedro M. Gordaliza, Sam Hashemi, Tobias Heimann, Fucang Jia, Jiexin Jiang, Emily Kaczmarek, Chris Kang, Seung Kwan Kang, Mohammad Khazaei, Julien Khlaut, Petros Koutsouvelis, Jae Sung Lee, Yuchong Li, Mengye Lyu, Mingchen Ma, Anant Madabhushi, Klaus H. Maier-Hein, Pierre Manceron, Andrés Martínez Mora, Moona Mazher, Felix Meister, Nataliia Molchanova, Steven A. Niederer, Leonard Nürnberg, Jinah Park, Abdul Qayyum, Jonas Richiardi, Antoine Saporta, Branislav Setlak, Ning Shen, Justin Szeto, Constantin Ulrich, Puru Vaish, Vibujithan Vigneshwaran, Leroy Volmer, Zihao Wang, Siqi Wei, Anthony Winder, Jelmer M. Wolterink, Maxence Wynen, Chang Yang, Si Young Yie, Mostafa Mehdipour Ghazi, Akshay Pai, Espen Jimenez Solem, Sebastian Nørgaard Llambias, Mikael Boesen, Michael Eriksen Benros, Juan Eugenio Iglesias, Mads Nielsen

机构 * organization= Department of Computer Science, University of Copenhagen , city= Copenhagen , country= Denmark organization= Pioneer Centre for AI , city= Copenhagen , country= Denmark organization= Copenhagen Research Centre for Biological Precision Psychiatry, Mental Health Centre Copenhagen, Copenhagen University Hospital , region= Capital Region of Denmark , city= Copenhagen , country= Denmark organization= Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital Harvard Medical School , city= Boston , state= Massachusetts , country= USA Artificial Intelligence Laboratory, Massachusetts Institute of Technology , city= Boston , state= Massachusetts , country= USA organization= Johns Hopkins University , city= Baltimore , state= Maryland , country= USA organization= Radiological AI Testcenter (RAIT) , region= Capital Region of Denmark , city= Copenhagen , country= Denmark organization= Copenhagen University Hospital, Rigshospitalet , region= Capital Region of Denmark , city= Copenhagen , country= Denmark organization= Copenhagen University Hospital, Bispebjerg \& Frederiksberg Hospital , region= Capital Region of Denmark , city= Copenhagen , country= Denmark organization= Department of Clinical Medicine, Faculty of Health Medical Sciences, University of Copenhagen , city= Copenhagen , country= Denmark organization= Division of Medical Image Computing, German Cancer Research Center (DKFZ) , city= Heidelberg , country= Germany organization= University of British Columbia , city= Vancouver , state= British Columbia , country= Canada organization= Hawkes Institute, Department of Computer Science, University College London , city= London , country= United Kingdom Lung Institute, Faculty of Medicine, Imperial College London , city= London , country= United Kingdom organization= Department of Applied Mathematics, Technical Medical Centre, University of Twente , city= Enschede , country= Netherlands organization= IISLAB, Technical University of Košice , city= Košice , country= Slovakia organization= 2nd Department of Internal Medicine, Pavol Jozef Safarik University L Pasteur University Hospital , city= Košice , country= Slovakia organization= Fudan University , city= Shanghai , country= China organization= Shenzhen Technology University , city= Shenzhen , country= China organization= Department of Radiology, Lausanne University Hospital University of Lausanne , city= Lausanne , country= Switzerland organization= Louvain Neuroinflammation Imaging Lab (NIL), Université Catholique de Louvain , city= Brussels , country= Belgium organization= University of Applied Sciences organization= CIBM Center for Biomedical Imaging , city= Lausanne , country= Switzerland organization= Department of Radiation Oncology (Maastro), GROW Research Institute for Oncology Reproduction, Maastricht University Medical Centre+ , city= Maastricht , country= The Netherlands organization= Department of Biomedical Engineering, Medical Image Analysis, Eindhoven University of Technology , city= Eindhoven , country= The Netherlands organization= Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences , city= Shenzhen , country= China organization= McGill University Mila - Quebec AI Institute , city= Montreal , country= Canada organization= Hotchkiss Brain Institute Department of Radiology, University of Calgary , city= Calgary , state= Alberta , country= Canada organization= Department of Radiology, University of Calgary , city= Calgary , state= Alberta , country= Canada organization= Alberta Children's Hospital Research Institute, Department of Clinical Neuroscience, University of Calgary , city= Calgary , state= Alberta , country= Canada organization= The Wallace H. Coulter Department of Biomedical Engineering, Georgia Tech Emory University , city= Atlanta , state= Georgia , country= USA organization= SGGS College of Engineering organization= Seoul National University , city= Seoul , country= South Korea organization= The D-Lab, Department of Precision Medicine, GROW Research Institute for Oncology Reproduction, Maastricht University , city= Maastricht , country= The Netherlands organization= Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School , city= Boston , state= Massachusetts , country= USA Nuclear Medicine, CARIM \& GROW, Maastricht University , city= Maastricht , country= The Netherlands organization= Department of Radiation Oncology, Dana-Farber Cancer Institute, Brigham Women’s Hospital, Harvard Medical School , city= Boston , state= Massachusetts , country= USA Learning Group, Heidelberg University Hospital , city= Heidelberg , country= Germany

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

AI总结 针对临床脑MRI数据异质且标注成本高的问题,FOMO25挑战赛通过自监督预训练(FOMO60K数据集)评估了16个团队的基础模型,发现自监督预训练能提升域迁移泛化性,但不同任务需不同预训练目标,且模型规模扩展收益有限。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.21812 2026-05-22 cs.IR 82%

Bridging the Cold-Start Gap: LLM-Powered Synthetic Data Generation for Natural Language Search at Airbnb

弥合冷启动缺口:利用大语言模型生成合成数据用于Airbnb的自然语言搜索

Wendy Ran Wei, Hao Li, Weiwei Guo, Xiaowei Liu, Xueyin Chen, Dillon Davis, Malay Haldar, Soumyadip Banerjee, Kedar Bellare, Huiji Gao, Stephanie Moyerman, Sanjeev Katariya

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

AI总结 本文提出利用大语言模型生成合成查询和标签的方法,解决自然语言搜索系统中冷启动问题,通过生成真实用户数据的过渡来提升模型训练和评估效果。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.19849 2026-05-20 cs.IT math.IT 82%

SPA-MAE: A Physics-Guided CSI Foundation Model for Wireless Physical Layer

SPA-MAE:一种基于物理的CSI基础模型用于无线物理层

Chen Chen, Weijie Jin, Hengtao He, Xiaoheng Sun, Shi Jin

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

AI总结 本文提出了一种基于物理的CSI基础模型SPA-MAE,通过结合适应性的MAE骨干网络和通道知识,提升了无线物理层任务的泛化能力,实验表明其在参数较少的情况下,在低SNR和有限数据条件下表现更优。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.16600 2026-05-19 cs.LG cs.AI cs.CL 82%

Where Pretraining writes and Alignment reads: the asymmetry of Transformer weight space

预训练写入,对齐读取:Transformer权重空间的不对称性

Valeria Ruscio, Eli-Shaoul Khedouri, Keiran Thompson

机构 * Intuition Machines

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

AI总结 研究揭示了预训练和对齐在Transformer权重空间中的不对称性,通过分析权重变化在残差流激活子空间和预测子空间中的对齐情况,发现读路径权重集中于注意力输入激活的主方向,而写路径权重在预测子空间中保持各向同性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.02812 2026-05-18 cs.RO 82%

Learning Structured Robot Policies from Vision-Language Models via Synthetic Neuro-Symbolic Supervision

通过合成神经符号监督学习结构化机器人策略

Alessandro Adami, Tommaso Tubaldo, Marco Todescato, Ruggero Carli, Pietro Falco

机构 * University of Padova, Dept. of Information Engineering(帕多瓦大学信息工程系) Fraunhofer Italia Research(弗劳恩霍夫意大利研究所) Polytechnic of Bari Dept. of Electrical and Information Engineering(巴里理工学院电气与信息工程系)

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

AI总结 本文提出通过合成神经符号监督方法,利用视觉语言模型生成结构化机器人策略,结合多模态感知与符号控制,实现高维学习与符号控制的结合。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.15698 2026-05-18 cs.HC 82%

Handwriting decoding as a challenging motor task for EEG Foundation Models

手写解码作为EEG基础模型中的一个具有挑战性的运动任务

Srinivas Ravishankar, Ishayu Ghosh, Nora Zajzon, Teng Fei, Virginia de Sa

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

AI总结 本文提出将手写解码作为EEG基础模型的挑战性运动任务,发现现有数据集可能存在问题,并引入更严谨的评估数据集,显示基础模型在手写解码任务中不如专门模型表现优异。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.13059 2026-05-14 cs.CV 82%

BrainAnytime: Anatomy-Aware Cross-Modal Pretraining for Brain Image Analysis with Arbitrary Modality Availability

BrainAnytime: 基于解剖结构的跨模态预训练用于脑图像分析,支持任意模态可用性

Guangqian Yang, Tong Ding, Wenlong Hou, Yue Xun, Ye Du, Qian Niu, Shujun Wang

机构 * Department of Biomedical Engineering, The Hong Kong Polytechnic University, Hong Kong SAR, China(生物医学工程系,香港理工大学,香港特别行政区,中国) Department of Technology Management for Innovation, The University of Tokyo, Japan(创新技术管理系,东京大学,日本) Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University, Hong Kong SAR, China(数据科学与人工智能系,香港理工大学,香港特别行政区,中国)

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

AI总结 BrainAnytime通过跨模态蒸馏和解剖引导课程掩码,在共享的3D掩码自动编码器中学习MRI与PET的结构-分子对应关系,实现对任意模态可用性的统一预训练,提升多任务性能。

Comments Early accepted by MICCAI 2026

详情

展开后加载摘要…

URL PDF HTML 收藏