publications

2026

1. ICLR

   MergOPT: A Merge-Aware Optimizer for Robust Model Merging

   Enneng Yang, Q Yang, P Wang, and 4 more authors

   In The Fourteenth International Conference on Learning Representations, 2026

   Bib

   @inproceedings{yang2026mergopt,
     title = {MergOPT: A Merge-Aware Optimizer for Robust Model Merging},
     author = {Yang, Enneng and Yang, Q and Wang, P and Tang, Anke and Guo, Guibing and Cao, Xiaochun and Shen, Li},
     booktitle = {The Fourteenth International Conference on Learning Representations},
     year = {2026},
   }

2. A Unified Generalization Framework for Model Merging: Trade-offs, Non-Linearity, and Scaling Laws

   Qinglun Li, Anke Tang, Miao Zhang, and 3 more authors

   arXiv preprint arXiv:2601.21690, 2026

   Bib

   @article{li2026understanding,
     title = {A Unified Generalization Framework for Model Merging: Trade-offs, Non-Linearity, and Scaling Laws},
     author = {Li, Qinglun and Tang, Anke and Zhang, Miao and Wang, Mengzhu and Yin, Quanjun and Shen, Li},
     journal = {arXiv preprint arXiv:2601.21690},
     year = {2026},
   }

2025

1. TPAMI

   

   Zero-Shot Sparse Mixture of Low-Rank Experts Construction From Pre-Trained Foundation Models

   Anke Tang, Li Shen, Yong Luo, and 5 more authors

   IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025

   Bib

   @article{tang2025zero,
     title = {Zero-Shot Sparse Mixture of Low-Rank Experts Construction From Pre-Trained Foundation Models},
     author = {Tang, Anke and Shen, Li and Luo, Yong and Xie, Shuai and Hu, Han and Zhang, Lefei and Du, Bo and Tao, Dacheng},
     journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
     year = {2025},
     publisher = {IEEE},
   }

2. IJCV

   Data-adaptive weight-ensembling for multi-task model fusion

   Anke Tang, Li Shen, Yong Luo, and 4 more authors

   International Journal of Computer Vision, 2025

   Bib

   @article{tang2025data,
     title = {Data-adaptive weight-ensembling for multi-task model fusion},
     author = {Tang, Anke and Shen, Li and Luo, Yong and Liu, Shiwei and Hu, Han and Du, Bo and Tao, Dacheng},
     journal = {International Journal of Computer Vision},
     pages = {1--17},
     year = {2025},
     publisher = {Springer US},
   }

3. NeurIPS

   

   Merging models on the fly without retraining: A sequential approach to scalable continual model merging

   Anke Tang, Enneng Yang, Li Shen, and 4 more authors

   The Thirty-Ninth Annual Conference on Neural Information Processing Systems, 2025

   Bib HTML

   @article{tang2025merging,
     title = {Merging models on the fly without retraining: A sequential approach to scalable continual model merging},
     author = {Tang, Anke and Yang, Enneng and Shen, Li and Luo, Yong and Hu, Han and Du, Bo and Tao, Dacheng},
     journal = {The Thirty-Ninth Annual Conference on Neural Information Processing Systems},
     year = {2025},
   }

4. NeurIPS

   Continual Model Merging without Data: Dual Projections for Balancing Stability and Plasticity

   Enneng Yang, Anke Tang, Li Shen, and 4 more authors

   The Thirty-Ninth Annual Conference on Neural Information Processing Systems, 2025

   Bib

   @article{yang2025continual,
     title = {Continual Model Merging without Data: Dual Projections for Balancing Stability and Plasticity},
     author = {Yang, Enneng and Tang, Anke and Shen, Li and Guo, Guibing and Wang, Xingwei and Cao, Xiaochun and Jie, Zhang},
     journal = {The Thirty-Ninth Annual Conference on Neural Information Processing Systems},
     year = {2025},
   }

5. NeurIPS

   Mix Data or Merge Models? Balancing the Helpfulness, Honesty, and Harmlessness of Large Language Model via Model Merging

   Jinluan Yang, Dingnan Jin, Anke Tang, and 10 more authors

   The Thirty-Ninth Annual Conference on Neural Information Processing Systems, 2025

   Bib

   @article{yang2025mix,
     title = {Mix Data or Merge Models? Balancing the Helpfulness, Honesty, and Harmlessness of Large Language Model via Model Merging},
     author = {Yang, Jinluan and Jin, Dingnan and Tang, Anke and Shen, Li and Zhu, Didi and Chen, Zhengyu and Zhao, Ziyu and Wang, Daixin and Cui, Qing and Zhang, Zhiqiang and Zhou, Jun and Wu, Fei and Kuang, Kun},
     journal = {The Thirty-Ninth Annual Conference on Neural Information Processing Systems},
     year = {2025},
   }

6. ICML

   Targeted Low-rank Refinement: Enhancing Sparse Language Models with Precision

   Li Shen, Anke Tang, Yong Luo, and 3 more authors

   In Forty-second International Conference on Machine Learning, 2025

   Bib

   @inproceedings{shentargeted,
     title = {Targeted Low-rank Refinement: Enhancing Sparse Language Models with Precision},
     author = {Shen, Li and Tang, Anke and Luo, Yong and Sun, Tao and Hu, Han and Cao, Xiaochun},
     booktitle = {Forty-second International Conference on Machine Learning},
     year = {2025},
   }

7. ICML

   Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent

   Yongxian Wei, Anke Tang, Li Shen, and 3 more authors

   In Forty-second International Conference on Machine Learning, 2025

   Bib

   @inproceedings{weimodeling,
     title = {Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent},
     author = {Wei, Yongxian and Tang, Anke and Shen, Li and Hu, Zixuan and Yuan, Chun and Cao, Xiaochun},
     booktitle = {Forty-second International Conference on Machine Learning},
     year = {2025},
   }

8. ICLR

   Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace

   Jinluan Yang, Anke Tang, Didi Zhu, and 3 more authors

   In The 13th International Conference on Learning Representations (ICLR), 2025

   Bib

   @inproceedings{yang2025mitigating,
     title = {Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace},
     author = {Yang, Jinluan and Tang, Anke and Zhu, Didi and Chen, Zhengyu and Shen, Li and Wu, Fei},
     booktitle = {The 13th International Conference on Learning Representations (ICLR)},
     year = {2025},
   }

9. NMI

   Learning from models beyond fine-tuning

   Hongling Zheng, Li Shen, Anke Tang, and 5 more authors

   Nature Machine Intelligence, 2025

   Bib

   @article{zheng2025learning,
     title = {Learning from models beyond fine-tuning},
     author = {Zheng, Hongling and Shen, Li and Tang, Anke and Luo, Yong and Hu, Han and Du, Bo and Wen, Yonggang and Tao, Dacheng},
     journal = {Nature Machine Intelligence},
     volume = {7},
     number = {1},
     pages = {6--17},
     year = {2025},
     publisher = {Nature Publishing Group UK London},
   }

10. JMLR

    FusionBench: A Unified Library and Comprehensive Benchmark for Deep Model Fusion

    Anke Tang, Li Shen, Yong Luo, and 5 more authors

    Journal of Machine Learning Research, 2025

    Bib

    @article{tang2025fusionbench,
      title = {FusionBench: A Unified Library and Comprehensive Benchmark for Deep Model Fusion},
      author = {Tang, Anke and Shen, Li and Luo, Yong and Yang, Enneng and Hu, Han and Zhang, Lefei and Du, Bo and Tao, Dacheng},
      journal = {Journal of Machine Learning Research},
      volume = {26},
      number = {307},
      year = {2025},
    }

11. ICONIP

    Successive Mouse Movement: Dual-Phase Adaptation with Pre-balancing and Test-Time Learning

    J Feng, Yong Luo, Anke Tang, and 1 more author

    In International Conference on Neural Information Processing, 2025

    Bib

    @inproceedings{feng2025successive,
      title = {Successive Mouse Movement: Dual-Phase Adaptation with Pre-balancing and Test-Time Learning},
      author = {Feng, J and Luo, Yong and Tang, Anke and Liu, X},
      booktitle = {International Conference on Neural Information Processing},
      year = {2025},
    }

12. TPAMI

    Efficient and Effective Weight-Ensembling Mixture of Experts for Multi-Task Model Merging

    Li Shen, Anke Tang, Enneng Yang, and 6 more authors

    IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025

    Bib

    @article{shen2024efficient,
      title = {Efficient and Effective Weight-Ensembling Mixture of Experts for Multi-Task Model Merging},
      author = {Shen, Li and Tang, Anke and Yang, Enneng and Guo, Guibing and Luo, Yong and Zhang, Lefei and Cao, Xiaochun and Du, Bo and Tao, Dacheng},
      journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
      year = {2025},
      publisher = {IEEE},
    }

2024

1. Fusionbench: A comprehensive benchmark of deep model fusion

   Anke Tang, Li Shen, Yong Luo, and 3 more authors

   arXiv preprint arXiv:2406.03280, 2024

   Bib

   @article{tang2024fusionbench,
     title = {Fusionbench: A comprehensive benchmark of deep model fusion},
     author = {Tang, Anke and Shen, Li and Luo, Yong and Hu, Han and Du, Bo and Tao, Dacheng},
     journal = {arXiv preprint arXiv:2406.03280},
     year = {2024},
   }

2. Towards efficient pareto set approximation via mixture of experts based model fusion

   Anke Tang, Li Shen, Yong Luo, and 3 more authors

   arXiv preprint arXiv:2406.09770, 2024
3. ICML

   

   Merging Multi-Task Models via Weight-Ensembling Mixture of Experts

   Anke Tang, Li Shen, Yong Luo, and 3 more authors

   In The 41th International Conference on Machine Learning (ICML), 2024

   Bib

   @inproceedings{tang2024merging,
     title = {Merging Multi-Task Models via Weight-Ensembling Mixture of Experts},
     author = {Tang, Anke and Shen, Li and Luo, Yong and Yin, Nan and Zhang, Lefei and Tao, Dacheng},
     booktitle = {The 41th International Conference on Machine Learning (ICML)},
     year = {2024},
   }

4. ICLR

   Parameter efficient multi-task model fusion with partial linearization

   Anke Tang, Li Shen, Yong Luo, and 5 more authors

   In the 12th International Conference on Learning Representations, 2024

   Bib

   @inproceedings{tang2024parameter,
     title = {Parameter efficient multi-task model fusion with partial linearization},
     author = {Tang, Anke and Shen, Li and Luo, Yong and Zhan, Yibing and Hu, Han and Du, Bo and Chen, Yixin and Tao, Dacheng},
     booktitle = {the 12th International Conference on Learning Representations},
     year = {2024},
   }

2023

1. Concrete subspace learning based interference elimination for multi-task model fusion

   Anke Tang, Li Shen, Yong Luo, and 4 more authors

   arXiv preprint arXiv:2312.06173, 2023
2. IJCAI

   Improving Heterogeneous Model Reuse by Density Estimation

   Anke Tang, Yong Luo, Han Hu, and 5 more authors

   In Thirty-Second International Joint Conference on Artificial Intelligence, 2023

   Bib

   @inproceedings{tang2023improving,
     title = {Improving Heterogeneous Model Reuse by Density Estimation},
     author = {Tang, Anke and Luo, Yong and Hu, Han and He, Fengxiang and Su, Kehua and Du, Bo and Chen, Yixin and Tao, Dacheng},
     booktitle = {Thirty-Second International Joint Conference on Artificial Intelligence},
     year = {2023},
   }