arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

Fudan University(复旦大学)

2025-12-23 至 2025-12-23 共收录 6
2512.19043 2025-12-23 cs.RO

EGM: Efficiently Learning General Motion Tracking Policy for High Dynamic Humanoid Whole-Body Control

EGM: 为高动态人形全身体控高效学习通用运动跟踪策略

Chao Yang, Yingkai Sun, Peng Ye, Xin Chen, Chong Yu, Tao Chen

机构 * Shanghai Innovation Institute(上海创新研究院) College of Future Information Technology, Fudan University(复旦大学未来信息科技学院) College of Intelligent Robotics and Advanced Manufacturing, Fudan University(复旦大学智能机器人与先进制造学院) The Chinese University of Hong Kong(香港中文大学) ByteDance(字节跳动)

AI总结 EGM通过高效学习通用运动跟踪策略,提升高动态人形全身体控的鲁棒性和泛化能力。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.18766 2025-12-23 cs.CV

MaskFocus: Focusing Policy Optimization on Critical Steps for Masked Image Generation

MaskFocus: 为掩码图像生成聚焦策略优化

Guohui Zhang, Hu Yu, Xiaoxiao Ma, Yaning Pan, Hang Xu, Feng Zhao

机构 * University of Science and Technology of China(中国科学技术大学) Fudan University(复旦大学)

AI总结 MaskFocus通过聚焦关键步骤优化策略,提升掩码图像生成模型的性能。

Comments Code is available at https://github.com/zghhui/MaskFocus

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.18706 2025-12-23 cs.SD

X-Talk: On the Underestimated Potential of Modular Speech-to-Speech Dialogue System

X-Talk:模块化语音到语音对话系统的被低估潜力

Zhanxun Liu, Yifan Duan, Mengmeng Wang, Pengchao Feng, Haotian Zhang, Xiaoyu Xing, Yijia Shan, Haina Zhu, Yuhang Dai, Chaochao Lu, Xipeng Qiu, Lei Xie, Lan Wang, Nan Yan, Zilong Zheng, Ziyang Ma, Kai Yu, Xie Chen

机构 * MoE Key Lab of Artificial Intelligence, X-LANCE Lab, Shanghai Jiao Tong University(人工智能基础理论重点实验室,X-LANCE实验室,上海交通大学) Shanghai Innovation Institute(上海创新研究院) Shanghai AI Laboratory(上海人工智能实验室) State Key Laboratory of General Artificial Intelligence, BIGAI(通用人工智能国家重点实验室,BIGAI) Audio, Speech and Language Processing Group, Northwestern Polytechnical University(语音与语言处理组,西北工业大学) Fudan University(复旦大学) Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(深圳先进技术研究院,中国科学院)

AI总结 X-Talk通过模块化设计和流水线优化,提升语音到语音对话系统的性能与灵活性,展示其在复杂语音任务中的潜力。

Comments 14 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.18635 2025-12-23 cs.CV

Uni-Neur2Img: Unified Neural Signal-Guided Image Generation, Editing, and Stylization via Diffusion Transformers

Uni-Neur2Img:通过扩散变换器实现神经信号引导的图像生成、编辑和风格化

Xiyue Bai, Ronghao Yu, Jia Xiu, Pengfei Zhou, Jie Xia, Peng Ji

机构 * Fudan University(复旦大学) Zhejiang University(浙江大学) National University of Singapore(新加坡国立大学)

AI总结 Uni-Neur2Img通过扩散变换器实现神经信号引导的图像生成、编辑和风格化,提供统一且高效的解决方案。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.07651 2025-12-23 cs.CV

Liver Fibrosis Quantification and Analysis: The LiQA Dataset and Baseline Method

肝脏纤维化量化与分析:LiQA数据集及基线方法

Yuanye Liu, Hanxiao Zhang, Jiyao Liu, Nannan Shi, Yuxin Shi, Arif Mahmood, Murtaza Taj, Xiahai Zhuang

机构 * School of Data Science, Fudan University(复旦大学数据科学学院) Institute of Medical Robotics, Shanghai Jiao Tong University(上海交通大学医疗机器人研究院) Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University(复旦大学脑启发智能科学技术研究院) Department of Radiology, Shanghai Public Health Clinical Center(上海公共卫生临床中心放射科) Department of Computer Science, Information Technology University(信息技术大学计算机科学系) Department of Computer Science, Lahore University of Management Sciences(拉合尔管理科学大学计算机科学系)

AI总结 本文提出LiQA数据集及基线方法,用于肝脏纤维化量化与分析,通过半监督学习和多视图共识方法提升分割与分期的鲁棒性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.03198 2025-12-23 q-bio.NC cs.LG

SimSort: A Data-Driven Framework for Spike Sorting by Large-Scale Electrophysiology Simulation

SimSort:一种基于大规模电生理模拟的尖峰分拣数据驱动框架

Yimu Zhang, Dongqi Han, Yansen Wang, Zhenning Lv, Yu Gu, Dongsheng Li

机构 * Fudan University(复旦大学) Microsoft Research Asia(微软亚洲研究院)

AI总结 SimSort通过大规模电生理模拟数据预训练,实现了在真实尖峰分拣任务中的零样本泛化,提升了尖峰分拣的鲁棒性和可扩展性。

Journal ref 39th Conference on Neural Information Processing Systems (NeurIPS 2025)

详情

展开后加载摘要…

URL PDF HTML 收藏