publications

2026

1. ICLR

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

   Jiayu Yang, Yuxuan Fan, Songning Lai, Shengen Wu, Jiaqi Tang, and 3 more authors

   In International Conference on Learning Representations, 2026

   arXiv Bib

   @inproceedings{yang2026ace,
     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},
     booktitle = {International Conference on Learning Representations},
     year = {2026},
   }

2. TMLR

   CAT: Concept-Level Backdoor Attacks for Concept Bottleneck Models

   Songning Lai, Jiayu Yang, Yu Huang, Lijie Hu, Tianlang Xue, and 4 more authors

   Transactions on Machine Learning Research, 2026

   arXiv 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 = {Transactions on Machine Learning Research},
     year = {2026},
   }

3. EMNLP

   Demystifying Hidden-State Recurrence: Switchable Latent Reasoning with On-Policy Reinforcement Learning

   Jiayu Yang, Chao Chen, Shengen Wu, Yinhong Liu, Yuxuan Fan, and 4 more authors

   In Conference on Empirical Methods in Natural Language Processing, 2026

   arXiv Bib

   @inproceedings{yang2026switch,
     title = {Demystifying Hidden-State Recurrence: Switchable Latent Reasoning with On-Policy Reinforcement Learning},
     author = {Yang, Jiayu and Chen, Chao and Wu, Shengen and Liu, Yinhong and Fan, Yuxuan and Li, Lujundong and Lai, Songning and Qin, Chengwei and Guo, Zhijiang},
     booktitle = {Conference on Empirical Methods in Natural Language Processing},
     year = {2026},
   }

4. ECCV

   Dynamic-V2C: Editable and Continual Vision-to-Concept Bottleneck Models via Influence Functions

   Songning Lai, Shaofeng Liang, Jiayu Yang, Ninghui Feng, Yuxuan Fan, and 1 more author

   In European Conference on Computer Vision, 2026

   Bib

   @inproceedings{lai2026dynamic,
     title = {Dynamic-V2C: Editable and Continual Vision-to-Concept Bottleneck Models via Influence Functions},
     author = {Lai, Songning and Liang, Shaofeng and Yang, Jiayu and Feng, Ninghui and Fan, Yuxuan and Chen, Wenshuo},
     booktitle = {European Conference on Computer Vision},
     year = {2026},
   }

2025

1. ACM MM

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

   Songning Lai, Mingqian Liao, Zhangyi Hu, Jiayu Yang, Wenshuo Chen, and 4 more authors

   In Proceedings of the 33rd ACM International Conference on Multimedia, 2025

   Oral Bib

   Selected as an oral presentation at ACM Multimedia 2025.

   @inproceedings{lai2025learning,
     title = {Learning New Concepts, Remembering the Old: Continual Learning for Multimodal Concept Bottleneck Models},
     author = {Lai, Songning and Liao, Mingqian and Hu, Zhangyi and Yang, Jiayu and Chen, Wenshuo and Xiao, Hongru and Tang, Jianheng and Liao, Haicheng and Yue, Yutao},
     booktitle = {Proceedings of the 33rd ACM International Conference on Multimedia},
     pages = {12314--12322},
     year = {2025},
   }

2. From Guesswork to Guarantee: Towards Faithful Multimedia Web Forecasting with TimeSieve

   Songning Lai, Ninghui Feng, Jiechao Gao, Hao Wang, Haochen Sui, and 6 more authors

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

   Ninghui Feng, Songning Lai, Xin Zhou, Jiayu Yang, Kunlong Feng, and 6 more authors

   arXiv preprint arXiv:2503.19656, 2025

2024

1. A comprehensive review of community detection in graphs

   Jiakang Li, Songning Lai, Zhihao Shuai, Yuan Tan, Yifan Jia, and 6 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. Guarding the gate: Conceptguard battles concept-level backdoors in concept bottleneck models

   Jiayu Yang, Yu Huang, Songning Lai, Gaoxiang Huang, Wenshuo Chen, and 1 more author

   arXiv preprint arXiv:2411.16512, 2024

   arXiv Bib

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

3. Timesieve: Extracting temporal dynamics through information bottlenecks

   Ninghui Feng, Songning Lai, Jiayu Yang, Fobao Zhou, Zhenxiao Yin, and 1 more author

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

   Jiemin Wu, Songning Lai, Ruiqiang Xiao, Tianlang Xue, Jiayu Yang, and 1 more author

   arXiv preprint arXiv:2410.20340, 2024