arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

Northeastern University(东北大学)

2026-01-16 至 2026-01-16 共收录 2
2601.10312 2026-01-16 cs.LG

We Need a More Robust Classifier: Dual Causal Learning Empowers Domain-Incremental Time Series Classification

我们需要一个更稳健的分类器:双因果学习赋能领域增量时间序列分类

Zhipeng Liu, Peibo Duan, Xuan Tang, Haodong Jing, Mingyang Geng, Yongsheng Huang, Jialu Xu, Bin Zhang, Binwu Wang

机构 * School of Software, Northeastern University(东北大学软件学院) Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University(西安交通大学人工智能与机器人研究所) College of Computer Science and Technology, National University of Defense Technology(国防科技大学计算机科学与技术学院) School of Software, University of Science and Technology of China(中国科学技术大学软件学院)

AI总结 本文提出双因果学习框架DualCD,通过解耦因果特征与虚假特征,提升领域增量时间序列分类的鲁棒性。

Comments This paper has been accepted for publication at ACM WWW 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.10064 2026-01-16 cs.CL

Long-Chain Reasoning Distillation via Adaptive Prefix Alignment

通过自适应前缀对齐实现长链推理蒸馏

Zhenghao Liu, Zhuoyang Wu, Xinze Li, Yukun Yan, Shuo Wang, Zulong Chen, Yu Gu, Ge Yu, Maosong Sun

机构 * School of Computer Science and Engineering, Northeastern University, China(东北大学计算机科学与工程学院) Department of Computer Science and Technology, Institute for AI, Tsinghua University, China(清华大学计算机科学与技术系) Alibaba Group, China(阿里巴巴集团)

AI总结 通过自适应前缀对齐方法提升学生模型的推理能力,有效蒸馏教师生成的长推理轨迹。

详情

展开后加载摘要…

URL PDF HTML 收藏