arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

University of Southern California(南加州大学)

2026-08-24 至 2026-08-24 共收录 5
2608.20818 2026-08-24 cs.LG cs.AI cs.CV 新提交

Scaling Muon for Diffusion Transformers

针对扩散Transformer的Muon优化器的缩放研究

Chenghao Li, Xiao Han, Xinxin Huang, Wei Liu, Boyang Li, Bing Xiao, Heran Zhang, Juanma Perez Rua, Ke Xu, Kangning Liu, Linjun Kuang, Na Li, Tan Wang, Tian Xie, Wei Peng, Yang Pei, Yifan Xu, Yuanhao Zhai, Yuwei Lin, Zhe Wang, Zihao He, Daniel Li, Junbiao Tang, Ziyang Jiang, Dake Chen

机构 * University of Southern California(南加州大学) Meta

AI总结 该研究针对大型扩散Transformer的Muon优化器,提出周期性行级Muon,在保留其生成质量优势的同时,大幅降低训练的计算、通信开销与时间。

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.20569 2026-08-24 cs.AI cs.CL 新提交

Open-Weight Masked Introspection: Measuring What Language Models Can Report About Their Own Computation

开放权重掩码内省:测量语言模型可报告自身计算的能力

Emilio Ferrara

机构 * University of Southern California(南加州大学)

AI总结 本研究构建OWMI框架检验8个开放权重模型的内省能力,发现其无法区分真实干预与虚假运行,仅内部存在相关信息,失败源于内部状态到文本报告的路径,需对照内部参考验证模型证词。

Comments We release OWMI as a library so that this emerging ability can be measured as it develops. Hugging Face OWMI library: this https URL (https://huggingface.co/emilioferrara/owmi)

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.20556 2026-08-24 cs.RO cs.LO eess.SY 新提交

Logic-VLA: A Temporal Logic Conditioned Vision-Language-Action Model

Logic-VLA:一种时序逻辑条件下的视觉-语言-动作模型

Celina Shiyu Wang, Yiqi Zhao, Junjie Ye, Yue Wang, Jyotirmoy V. Deshmukh

机构 * University of Southern California(南加州大学)

AI总结 Logic-VLA是感知形式化需求的VLA模型,以STL规约为条件,经两阶段适配后,在四旋翼导航仿真中大幅提升STL满足率,仅小幅降低常规NL任务成功率,可适配不同形式化需求。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.03212 2026-08-24 cs.CV 版本更新

ProtoFlow: Mitigating Forgetting in Class-Incremental Remote Sensing Segmentation via Low-Curvature Prototype Flow

ProtoFlow: 通过低曲率原型流缓解类别增量遥感分割中的遗忘

Jiekai Wu, Rong Fu, Chuangqi Li, Zijian Zhang, Guangxin Wu, Hao Zhang, Shiyin Lin, Yang Li, Dongxu Zhang, Amir H. Gandomi, Simon Fong, Pengbin Feng

机构 * Faculty of Health Data Science, Juntendo University(静冈大学健康数据科学学院) The Institute of Collaborative Innovation, University of Macau(澳门大学协同创新研究所) Department of Information and Computing Sciences, Faculty of Science, Utrecht University(乌得勒支大学科学学院信息与计算科学系) Department of Computer and Information Science, University of Pennsylvania(宾夕法尼亚大学计算机与信息科学系) School of Computer Science, University of Chinese Academy of Sciences(中国科学院大学计算机科学学院) Department of Computer & Information Science & Engineering, University of Florida(佛罗里达大学计算机与信息科学与工程系) Department of Computer Science, Juniata College(朱尼塔学院计算机科学系) National Engineering Research Center for Beijing Biochip Technology(北京生物芯片工程技术研究中心) CapitalBio Corporation(资本生物公司) Faculty of Engineering & Information Technology, University of Technology Sydney(悉尼科技大学工程与信息技术学院) University Research and Innovation Center (EKIK), Obuda University(布达佩斯大学研究与创新中心(EKIK)) Faculty of Science and Technology, University of Macau(澳门大学科学与技术学院) Department of Mathematics, University of Southern California(南加州大学数学系)

AI总结 本文提出ProtoFlow,一种时间感知的原型动态框架,通过将类别原型建模为轨迹并学习其演变,以缓解遥感分割中的遗忘问题,实验表明其在多个基准上取得了显著提升。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.21948 2026-08-24 cs.CV 版本更新

Deep Models, Shallow Alignment: Uncovering the Granularity Mismatch in Neural Decoding

深度模型,浅层对齐:揭示神经解码中的粒度不匹配

Yang Du, Siyuan Dai, Yonghao Song, Paul M. Thompson, Haoteng Tang, Liang Zhan

机构 * Dept. of Electrical & Computer Engineering, University of Pittsburgh, USA(宾夕法尼亚大学电气与计算机工程系) Dept. of Biomedical Engineering, Tsinghua University, China(清华大学生物医学工程系) Dept. of Neurology, University of Southern California, USA(美国南加州大学神经病学系) Dept. of Computer Science, University of Texas Rio Grande Valley, USA(德克萨斯理工大学里奥格兰德谷分校计算机科学系)

AI总结 本文提出浅层对齐方法,通过对比学习策略解决神经解码中的粒度不匹配问题,显著提升解码性能。

Comments 33 pages, 16 figures

详情

展开后加载摘要…

URL PDF HTML 收藏