Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment for Low-Resource Spoken Language Models
弥合稳定性与表现力之间的差距:低资源口语语言模型的合成数据扩展与偏好对齐
Yizhong Geng, Yanliang Li, Jinghan Yang, Tianhan Jiang, Boxun An, Ya Li, Xiaoyu Shen
机构
*
Beijing University of Posts(北京邮电大学)
;
University of California, USA(美国加州大学)
;
Northwestern University, USA(美国西北大学)
;
Eastern Institute of Technology, Ningbo, China(宁波工程技术学院)
FLORO: A Multimodal Geospatial Foundation Model for Ecological Remote Sensing Across Sensors and Scales
FLORO:面向跨传感器与尺度的生态遥感多模态地理空间基础模型
Jorge L. Rodriguez, Victor Angulo Morales, Areej Alwahas, Mariana Elias Lara, Fida Mohammad Thoker, Kasper Johansen, Bernard Ghanem, Fernando T. Maestre, Matthew F. McCabe
机构
*
Biological and Environmental Science and Engineering Division, King Abdullah University of Science and Technology(国王阿卜杜勒·阿齐兹科技大学生物与环境科学与工程 division)
;
Computer, Electrical and Mathematical Science and Engineering Division, King Abdullah University of Science and Technology(国王阿卜杜勒·阿齐兹科技大学计算机、电气与数学科学与工程 division)
机构
*
School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院)
;
MAIS, Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所MAIS)
;
Meituan(美团)
专题命中
预训练与数据
:large language model(abstract);language model(abstract);pretraining(abstract);分类 cs.LG
机构
*
Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning(湖北人工智能与智能学习省级重点实验室)
;
National Language Resources Monitoring and Research Center for Network Media(网络媒体语言资源监测与研究中心)
;
School of Computer Science, Central China Normal University(华中师范大学计算机学院)
;
Faculty of Artificial Intelligence in Education, Central China Normal University(华中师范大学教育人工智能学院)
;
School of Chinese Language and Literature, Central China Normal University(华中师范大学中文语言文学学院)
Comments12 pages, 4 figures, KDD '26 camera-ready version
Journal refProceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2 (KDD '26), August 09--13, 2026, Jeju Island, Republic of Korea
机构
*
Dept. of Energy Conversion and Storage, Technical University of Denmark(丹麦技术大学能源转换与存储系)
;
Dept. of Applied Mathematics and Computer Science, Technical University of Denmark(丹麦技术大学应用数学与计算机科学系)
;
Pioneer Center for Accelerating P2X Materials Discovery (CAPeX), Kgs. Lyngby, Denmark(加速P2X材料发现的先锋中心(CAPeX),Lyngby,丹麦)
Can Entry-Wise Clipping Give Spectral Control of Stochastic Gradients?
逐元素裁剪能否实现随机梯度的谱控制?
Zitao Song, Cedar Site Bai, Zhe Zhang, Brian Bullins, David F. Gleich
机构
*
Department of Computer Science, Purdue University, West Lafayette, IN, USA(计算机科学系,普渡大学,西拉法塞特,印第安纳州,美国)
;
School of Industrial Engineering, Purdue University, West Lafayette, IN, USA(工业工程学院,普渡大学,西拉法塞特,印第安纳州,美国)
Bio-Inspired Self-Supervised Learning for Wrist-worn Accelerometer Data
生物启发的自监督学习用于腕戴式加速度计数据
Prithviraj Tarale, Kiet Chu, Abhishek Varghese, Kai-Chun Liu, Maxwell A. Xu, Mohit Iyyer, Sunghoon I. Lee
机构
*
College of Information and Computer Sciences, University of Massachusetts, Amherst, United States(信息与计算机科学学院,马萨诸塞大学阿默斯特分校)
;
Google Health, Seattle, United States(谷歌健康,西雅图,美国)
;
Department of Computer Science, University of Maryland, College Park, United States(计算机科学系,马里兰大学学院公园分校)
;
Stevens Institute of Technology, Hoboken, United States(史蒂文斯理工学院,霍博肯,美国)
A self-supervised learning approach to deep filter banks for texture recognition
一种用于纹理识别的深度滤波器组的自监督学习方法
Joao B. Florindo, Lucas O. Lyra, Antonio E. Fabris
机构
*
Institute of Mathematics and Statistics of the University of Sao Paulo(圣保罗大学数学与统计学研究所)
;
Institute of Mathematics, Statistics and Scientific Computing of the University of Campinas(坎皮纳斯大学数学、统计与科学计算研究所)
MVP-LAM: Learning Action-Centric Latent Action via Cross-Viewpoint Reconstruction
MVP-LAM:通过跨视角重建学习以动作为中心的潜在动作
Jung Min Lee, Dohyeok Lee, Seokhun Ju, Taehyun Cho, Jin Woo Koo, Li Zhao, Sangwoo Hong, Jungwoo Lee
机构
*
Seoul National University, Seoul, South Korea(首尔国立大学,首尔,韩国)
;
Konkuk University, Seoul, South Korea(韩国konkuk大学,首尔,韩国)
;
Microsoft Research Asia, Beijing, China(微软亚洲研究院,北京,中国)
;
HodooAI Labs, Seoul, South Korea(HodooAI实验室,首尔,韩国)