arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

Johns Hopkins University(约翰斯·霍普金斯大学)

2026-02-12 至 2026-02-12 共收录 5
2509.17143 2026-02-12 eess.AS cs.AI

MaskVCT: Masked Voice Codec Transformer for Zero-Shot Voice Conversion With Increased Controllability via Multiple Guidances

MaskVCT:基于多指导的零样本语音转换语音编解码器

Junhyeok Lee, Helin Wang, Yaohan Guan, Thomas Thebaud, Laureano Moro-Velazquez, Jesús Villalba, Najim Dehak

机构 * Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA(语言与语音处理中心,约翰霍普金斯大学,巴尔的摩,马里兰州,美国)

AI总结 MaskVCT通过多指导机制实现零样本语音转换的多因素可控性,提升说话人相似性和语调控制能力。

Comments ICASSP 2026 Accepted

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.10156 2026-02-12 q-bio.GN cs.LG q-bio.CB

STRAND: Sequence-Conditioned Transport for Single-Cell Perturbations

STRAND:基于序列的传输用于单细胞扰动

Boyang Fu, George Dasoulas, Sameer Gabbita, Xiang Lin, Shanghua Gao, Xiaorui Su, Soumya Ghosh, Marinka Zitnik

机构 * Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA Merck \& Co., Inc., Cambridge, MA, USA Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD, USA Kempner Institute for the Study of Natural Artificial Intelligence, Harvard University, Allston, MA, USA Broad Institute of MIT

AI总结 STRAND通过条件化调控DNA序列预测单细胞转录响应,提升基因扰动分析的准确性和泛化能力。

Comments 8 pages for main draft, 6 main figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.05252 2026-02-12 cs.CL

Copyright Detective: A Forensic System to Evidence LLMs Flickering Copyright Leakage Risks

版权侦探:一种用于证据LLM闪烁版权泄露风险的取证系统

Guangwei Zhang, Jianing Zhu, Cheng Qian, Neil Gong, Rada Mihalcea, Zhaozhuo Xu, Jingrui He, Jiaqi Ma, Yun Huang, Chaowei Xiao, Bo Li, Ahmed Abbasi, Dongwon Lee, Heng Ji, Denghui Zhang

机构 * Pine AI The University of Texas at Austin(德克萨斯大学奥斯汀分校) University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校) Duke University(杜克大学) University of Michigan(密歇根大学) Stevens Institute of Technology(史蒂文斯理工学院) Johns Hopkins University(约翰霍普金斯大学) University of Notre Dame(圣母大学) The Pennsylvania State University(宾夕法尼亚州立大学)

AI总结 Copyright Detective 是一种交互式系统,用于检测和可视化LLM输出中的版权风险,通过整合多种检测方法实现系统性审计。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.21014 2026-02-12 stat.ML cs.LG stat.AP

Efficient Causal Structure Learning via Modular Subgraph Integration

通过模块化子图整合实现高效的因果结构学习

Haixiang Sun, Pengchao Tian, Zihan Zhou, Jielei Zhang, Peiyi Li, Andrew L. Liu

机构 * Purdue University(普渡大学) Bilibili Inc(哔哩哔哩公司) Johns Hopkins University(约翰霍普金斯大学)

AI总结 VISTA通过模块化子图整合框架,有效解决高维数据中因果结构学习的计算挑战,提升准确性和效率。

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.23599 2026-02-12 cs.LG math.RT math.ST stat.ML stat.TH

On Transferring Transferability: Towards a Theory for Size Generalization

关于转移的转移:迈向大小泛化理论

Eitan Levin, Yuxin Ma, Mateo Díaz, Soledad Villar

机构 * Department of Computing and Mathematical Sciences, Caltech(加州理工学院计算与数学科学系) Department of Applied Mathematics and Statistics and the Mathematical Institute for Data Science, Johns Hopkins University(约翰霍普金斯大学应用数学与统计学系及数据科学数学研究所)

AI总结 本文提出了一种通用框架,用于研究不同维度间的转移性,并通过理论分析和实验验证了大小泛化的能力。

Comments 75 pages, 10 figures, closest to version to be published in NeurIPS

详情

展开后加载摘要…

URL PDF HTML 收藏