ICLR · 2024 · Journal article

LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging

Ke Wang, Nikolaos Dimitriadis, Alessandro Favero, Guillermo Ortiz-Jiménez, François Fleuret, Pascal Frossard

Rendered by arXiv from the LaTeX source. If anything looks wrong, switch to the PDF.HTML · PDF · Open in a new tab ↗ · Close
Published in
International Conference on Learning Representations
Date
2024-10-22
Citations
43
arXiv
2410.17146
Cite
@article{wang2024lines,
  title = {LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging},
  author = {Ke Wang and Nikolaos Dimitriadis and Alessandro Favero and Guillermo Ortiz-Jiménez and François Fleuret and Pascal Frossard},
  year = {2024},
  journal = {International Conference on Learning Representations},
  eprint = {2410.17146},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.17146},
}