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)

2025-12-01 至 2025-12-01 共收录 4
2511.19221 2025-12-01 cs.CV cs.RO

Percept-WAM: Perception-Enhanced World-Awareness-Action Model for Robust End-to-End Autonomous Driving

Percept-WAM:感知增强的环境感知-行动模型用于鲁棒的端到端自动驾驶

Jianhua Han, Meng Tian, Jiangtong Zhu, Fan He, Huixin Zhang, Sitong Guo, Dechang Zhu, Hao Tang, Pei Xu, Yuze Guo, Minzhe Niu, Haojie Zhu, Qichao Dong, Xuechao Yan, Siyuan Dong, Lu Hou, Qingqiu Huang, Xiaosong Jia, Hang Xu

机构 * Yinwang Intelligent Technology Co. Ltd.(亿网通智能科技有限公司) Fudan University(复旦大学)

AI总结 Percept-WAM通过整合2D/3D场景理解能力,提升自动驾驶的感知与行动决策,实现端到端鲁棒性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.24693 2025-12-01 cs.SD cs.CL eess.AS

STAR-Bench: Probing Deep Spatio-Temporal Reasoning as Audio 4D Intelligence

STAR-Bench:探测深度时空推理作为音频4D智能

Zihan Liu, Zhikang Niu, Qiuyang Xiao, Zhisheng Zheng, Ruoqi Yuan, Yuhang Zang, Yuhang Cao, Xiaoyi Dong, Jianze Liang, Xie Chen, Leilei Sun, Dahua Lin, Jiaqi Wang

机构 * Fudan University(复旦大学) Shanghai AI Laboratory(上海人工智能实验室) The Chinese University of Hong Kong(香港中文大学) Shanghai Innovation Institute(上海创新研究院) Beihang University(北京航空航天大学) Shanghai Jiao Tong University(上海交通大学)

AI总结 STAR-Bench通过测试音频4D智能,揭示了模型在细粒度感知和推理上的不足,为未来模型发展提供方向。

Comments Homepage: https://internlm.github.io/StarBench/

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.04327 2025-12-01 cs.LG stat.ML

Arithmetic-Mean $μ$P for Modern Architectures: A Unified Learning-Rate Scale for CNNs and ResNets

算术平均μP用于现代架构:CNN和ResNets的统一学习率缩放

Haosong Zhang, Shenxi Wu, Yichi Zhang, Xi Chen, Wei Lin

机构 * Fudan University(复旦大学) New York University(纽约大学)

AI总结 本文提出算术平均μP,通过统一学习率缩放方法,为CNN和ResNets提供稳健的深度定律,实现零样本学习率转移。

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.02373 2025-12-01 cs.CV

Active Negative Loss: A Robust Framework for Learning with Noisy Labels

主动负损失:一种在噪声标签下学习的稳健框架

Xichen Ye, Yifan Wu, Yiqi Wang, Xiaoqiang Li, Weizhong Zhang, Yifan Chen

机构 * School of Computer Engineering and Science, Shanghai University(上海大学计算机工程与科学学院) School of Computer Science, Fudan University(复旦大学计算机科学学院) School of Data Science, Fudan University(复旦大学数据科学学院) Departments of Computer Science and Math, Hong Kong Baptist University(香港 Baptist 大学计算机科学与数学系)

AI总结 本文提出主动负损失框架,通过改进的损失函数增强在噪声标签下的学习鲁棒性。

Comments This work has been submitted to the IEEE for possible publication

详情

展开后加载摘要…

URL PDF HTML 收藏