publications

2025

1. ACE: Attribution-Controlled Knowledge Editing for Multi-hop Factual Recall

   Jiayu Yang, Yuxuan Fan, Songning Lai, and 5 more authors

   arXiv preprint arXiv:2510.07896, 2025

   Bib

   @article{yang2025ace,
     title = {ACE: Attribution-Controlled Knowledge Editing for Multi-hop Factual Recall},
     author = {Yang, Jiayu and Fan, Yuxuan and Lai, Songning and Wu, Shengen and Tang, Jiaqi and Kang, Chun and Guo, Zhijiang and Yue, Yutao},
     journal = {arXiv preprint arXiv:2510.07896},
     year = {2025},
   }

2. Learning New Concepts, Remembering the Old: Continual Learning for Multimodal Concept Bottleneck Models

   Songning Lai, Mingqian Liao, Zhangyi Hu, and 6 more authors

   In Proceedings of the 33rd ACM International Conference on Multimedia, 2025
3. From Guesswork to Guarantee: Towards Faithful Multimedia Web Forecasting with TimeSieve

   Songning Lai, Ninghui Feng, Jiechao Gao, and 8 more authors

   In Proceedings of the 33rd ACM International Conference on Multimedia, 2025
4. Towards Reliable Time Series Forecasting under Future Uncertainty: Ambiguity and Novelty Rejection Mechanisms

   Ninghui Feng, Songning Lai, Xin Zhou, and 8 more authors

   arXiv preprint arXiv:2503.19656, 2025

2024

1. A comprehensive review of community detection in graphs

   Jiakang Li, Songning Lai, Zhihao Shuai, and 8 more authors

   Neurocomputing, 2024

   Bib

   @article{li2024comprehensive,
     title = {A comprehensive review of community detection in graphs},
     author = {Li, Jiakang and Lai, Songning and Shuai, Zhihao and Tan, Yuan and Jia, Yifan and Yu, Mianyang and Song, Zichen and Peng, Xiaokang and Xu, Ziyang and Ni, Yongxin and others},
     journal = {Neurocomputing},
     volume = {600},
     pages = {128169},
     year = {2024},
     publisher = {Elsevier},
   }

2. Cat: Concept-level backdoor attacks for concept bottleneck models

   Songning Lai, Jiayu Yang, Yu Huang, and 6 more authors

   arXiv preprint arXiv:2410.04823, 2024

   Bib

   @article{lai2024cat,
     title = {Cat: Concept-level backdoor attacks for concept bottleneck models},
     author = {Lai, Songning and Yang, Jiayu and Huang, Yu and Hu, Lijie and Xue, Tianlang and Hu, Zhangyi and Li, Jiaxu and Liao, Haicheng and Yue, Yutao},
     journal = {arXiv preprint arXiv:2410.04823},
     year = {2024},
   }

3. Guarding the gate: Conceptguard battles concept-level backdoors in concept bottleneck models

   Songning Lai, Yu Huang, Jiayu Yang, and 3 more authors

   arXiv preprint arXiv:2411.16512, 2024

   Bib

   @article{lai2024guarding,
     title = {Guarding the gate: Conceptguard battles concept-level backdoors in concept bottleneck models},
     author = {Lai, Songning and Huang, Yu and Yang, Jiayu and Huang, Gaoxiang and Chen, Wenshuo and Yue, Yutao},
     journal = {arXiv preprint arXiv:2411.16512},
     year = {2024},
   }

4. Timesieve: Extracting temporal dynamics through information bottlenecks

   Ninghui Feng, Songning Lai, Jiayu Yang, and 3 more authors

   arXiv preprint arXiv:2406.05036, 2024
5. Maintaining informative coherence: Migrating hallucinations in large language models via absorbing markov chains

   Jiemin Wu, Songning Lai, Ruiqiang Xiao, and 3 more authors

   arXiv preprint arXiv:2410.20340, 2024