bib.txt

@inproceedings{DBLP:conf/icml/Yu0Y0L24,
  author       = {Le Yu and
                  Bowen Yu and
                  Haiyang Yu and
                  Fei Huang and
                  Yongbin Li},
  title        = {Language Models are Super Mario: Absorbing Abilities from Homologous
                  Models as a Free Lunch},
  booktitle    = {{ICML}},
  publisher    = {OpenReview.net},
  year         = {2024}
}
@misc{xu2024trainingfreeheterogeneousmodelmerging,
      title={Training-free Heterogeneous Model Merging}, 
      author={Zhengqi Xu and Han Zheng and Jie Song and Li Sun and Mingli Song},
      year={2024}}

@inproceedings{DBLP:conf/icml/FrankleD0C20,
  author       = {Jonathan Frankle and
                  Gintare Karolina Dziugaite and
                  Daniel M. Roy and
                  Michael Carbin},
  title        = {Linear Mode Connectivity and the Lottery Ticket Hypothesis},
  booktitle    = {{ICML}},
  volume       = {119},
  pages        = {3259--3269},
  publisher    = {{PMLR}},
  year         = {2020}
  }
  
  @inproceedings{DBLP:conf/iclr/EntezariSSN22,
  author       = {Rahim Entezari and
                  Hanie Sedghi and
                  Olga Saukh and
                  Behnam Neyshabur},
  title        = {The Role of Permutation Invariance in Linear Mode Connectivity of
                  Neural Networks},
  booktitle    = {{ICLR}},
  publisher    = {OpenReview.net},
  year         = {2022}
  }

@inproceedings{DBLP:conf/nips/MatenaR22,
  author       = {Michael Matena and
                  Colin Raffel},
  editor       = {Sanmi Koyejo and
                  S. Mohamed and
                  A. Agarwal and
                  Danielle Belgrave and
                  K. Cho and
                  A. Oh},
  title        = {Merging Models with Fisher-Weighted Averaging},
  booktitle    = {{NeurIPS} },
  year         = {2022}
  }
  @inproceedings{DBLP:conf/iclr/Jin0P023,
  author       = {Xisen Jin and
                  Xiang Ren and
                  Daniel Preotiuc{-}Pietro and
                  Pengxiang Cheng},
  title        = {Dataless Knowledge Fusion by Merging Weights of Language Models},
  booktitle    = {{ICLR}},
  publisher    = {OpenReview.net},
  year         = {2023}
  }

@inproceedings{DBLP:conf/icml/WortsmanIGRLMNF22,
  author       = {Mitchell Wortsman and
                  Gabriel Ilharco and
                  Samir Yitzhak Gadre and
                  Rebecca Roelofs and
                  Raphael Gontijo Lopes and
                  Ari S. Morcos and
                  Hongseok Namkoong and
                  Ali Farhadi and
                  Yair Carmon and
                  Simon Kornblith and
                  Ludwig Schmidt},
  editor       = {Kamalika Chaudhuri and
                  Stefanie Jegelka and
                  Le Song and
                  Csaba Szepesv{\'{a}}ri and
                  Gang Niu and
                  Sivan Sabato},
  title        = {Model soups: averaging weights of multiple fine-tuned models improves
                  accuracy without increasing inference time},
  booktitle    = {{ICML} },
  series       = {Proceedings of Machine Learning Research},
  volume       = {162},
  pages        = {23965--23998},
  publisher    = {{PMLR}},
  year         = {2022}
  }

@article{DBLP:journals/corr/abs-2406-11617,
  author       = {Pala Tej Deep and
                  Rishabh Bhardwaj and
                  Soujanya Poria},
  title        = {DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based
                  Sampling},
  journal      = {CoRR},
  volume       = {abs/2406.11617},
  year         = {2024}
  }
@inproceedings{DBLP:conf/eccv/JangYH24,
  author       = {Dong{-}Hwan Jang and
                  Sangdoo Yun and
                  Dongyoon Han},
  editor       = {Ales Leonardis and
                  Elisa Ricci and
                  Stefan Roth and
                  Olga Russakovsky and
                  Torsten Sattler and
                  G{\"{u}}l Varol},
  title        = {Model Stock: All We Need Is Just a Few Fine-Tuned Models},
  booktitle    = {{ECCV} },
  series       = {Lecture Notes in Computer Science},
  volume       = {15102},
  pages        = {207--223},
  publisher    = {Springer},
  year         = {2024}
  }
  
@article{DBLP:journals/corr/abs-2312-16240,
  author       = {Peng Ye and
                  Chenyu Huang and
                  Mingzhu Shen and
                  Tao Chen and
                  Yongqi Huang and
                  Yuning Zhang and
                  Wanli Ouyang},
  title        = {Merging Vision Transformers from Different Tasks and Domains},
  journal      = {CoRR},
  volume       = {abs/2312.16240},
  year         = {2023}}
  @article{DBLP:journals/corr/abs-2403-13187,
  author       = {Takuya Akiba and
                  Makoto Shing and
                  Yujin Tang and
                  Qi Sun and
                  David Ha},
  title        = {Evolutionary Optimization of Model Merging Recipes},
  journal      = {CoRR},
  volume       = {abs/2403.13187},
  year         = {2024}}

@article{DBLP:journals/corr/abs-2403-19390,
  author       = {Deyuan Liu and
                  Zecheng Wang and
                  Bingning Wang and
                  Weipeng Chen and
                  Chunshan Li and
                  Zhiying Tu and
                  Dianhui Chu and
                  Bo Li and
                  Dianbo Sui},
  title        = {Checkpoint Merging via Bayesian Optimization in {LLM} Pretraining},
  journal      = {CoRR},
  volume       = {abs/2403.19390},
  year         = {2024}}

@inproceedings{DBLP:conf/iclr/YangW00G0T24,
  author       = {Enneng Yang and
                  Zhenyi Wang and
                  Li Shen and
                  Shiwei Liu and
                  Guibing Guo and
                  Xingwei Wang and
                  Dacheng Tao},
  title        = {AdaMerging: Adaptive Model Merging for Multi-Task Learning},
  booktitle    = {{ICLR} },
  publisher    = {OpenReview.net},
  year         = {2024}}
  @inproceedings{DBLP:conf/iclr/AinsworthHS23,
  author       = {Samuel K. Ainsworth and
                  Jonathan Hayase and
                  Siddhartha S. Srinivasa},
  title        = {Git Re-Basin: Merging Models modulo Permutation Symmetries},
  booktitle    = {{ICLR} },
  publisher    = {OpenReview.net},
  year         = {2023}}

@inproceedings{DBLP:conf/acml/ONeillSG21,
  author       = {James O'Neill and
                  Greg Ver Steeg and
                  Aram Galstyan},
  editor       = {Vineeth N. Balasubramanian and
                  Ivor W. Tsang},
  title        = {Layer-Wise Neural Network Compression via Layer Fusion},
  booktitle    = {{ACML} },
  series       = {Proceedings of Machine Learning Research},
  volume       = {157},
  pages        = {1381--1396},
  publisher    = {{PMLR}},
  year         = {2021}}
@inproceedings{DBLP:conf/icml/HoroiCBW24,
  author       = {Stefan Horoi and
                  Albert Manuel Orozco Camacho and
                  Eugene Belilovsky and
                  Guy Wolf},
  title        = {Harmony in Diversity: Merging Neural Networks with Canonical Correlation
                  Analysis},
  booktitle    = {{ICML}},
  publisher    = {OpenReview.net},
  year         = {2024}}


@inproceedings{DBLP:conf/iclr/StoicaBBRHH24,
  author       = {George Stoica and
                  Daniel Bolya and
                  Jakob Bjorner and
                  Pratik Ramesh and
                  Taylor Hearn and
                  Judy Hoffman},
  title        = {ZipIt! Merging Models from Different Tasks without Training},
  booktitle    = {{ICLR} },
  publisher    = {OpenReview.net},
  year         = {2024}
}

@article{DBLP:journals/corr/abs-2403-00986,
  author       = {Neha Verma and
                  Maha Elbayad},
  title        = {Merging Text Transformer Models from Different Initializations},
  journal      = {CoRR},
  volume       = {abs/2403.00986},
  year         = {2024}}
@inproceedings{DBLP:conf/nips/SinghJ20,
  author       = {Sidak Pal Singh and
                  Martin Jaggi},
  editor       = {Hugo Larochelle and
                  Marc'Aurelio Ranzato and
                  Raia Hadsell and
                  Maria{-}Florina Balcan and
                  Hsuan{-}Tien Lin},
  title        = {Model Fusion via Optimal Transport},
  booktitle    = {{NeurIPS} },
  year         = {2020}}
@inproceedings{DBLP:conf/icassp/NguyenNNPBH23,
  author       = {Dang Nguyen and
                  Trang Nguyen and
                  Khai Nguyen and
                  Dinh Q. Phung and
                  Hung Hai Bui and
                  Nhat Ho},
  title        = {On Cross-Layer Alignment for Model Fusion of Heterogeneous Neural
                  Networks},
  booktitle    = {{ICASSP}},
  pages        = {1--5},
  publisher    = {{IEEE}},
  year         = {2023}}
@inproceedings{DBLP:conf/iclr/ImfeldGGHAS24,
  author       = {Moritz Imfeld and
                  Jacopo Graldi and
                  Marco Giordano and
                  Thomas Hofmann and
                  Sotiris Anagnostidis and
                  Sidak Pal Singh},
  title        = {Transformer Fusion with Optimal Transport},
  booktitle    = {{ICLR}},
  year         = {2024}}
@article{DBLP:journals/corr/abs-2402-16107,
  author       = {Fanqi Wan and
                  Ziyi Yang and
                  Longguang Zhong and
                  Xiaojun Quan and
                  Xinting Huang and
                  Wei Bi},
  title        = {FuseChat: Knowledge Fusion of Chat Models},
  journal      = {CoRR},
  volume       = {abs/2402.16107},
  year         = {2024}}

@inproceedings{DBLP:conf/emnlp/GoddardSEMKBMS24,
  author       = {Charles Goddard and
                  Shamane Siriwardhana and
                  Malikeh Ehghaghi and
                  Luke Meyers and
                  Vladimir Karpukhin and
                  Brian Benedict and
                  Mark McQuade and
                  Jacob Solawetz},
  editor       = {Franck Dernoncourt and
                  Daniel Preotiuc{-}Pietro and
                  Anastasia Shimorina},
  title        = {Arcee's MergeKit: {A} Toolkit for Merging Large Language Models},
  booktitle    = {{EMNLP}},
  pages        = {477--485},
  publisher    = {Association for Computational Linguistics},
  year         = {2024}}