arXiv · 2026 · Preprint

Fine-Tuning Without Forgetting via Loss-Adaptive Learning Rates

P. Prashant, Jiongli Zhu, Aldan Creo, Babak Salimi

Rendered by arXiv from the LaTeX source. If anything looks wrong, switch to the PDF.HTML · PDF · Open in a new tab ↗ · Close

Date: 2026-05-19
Citations: 0
arXiv: 2605.20005 ↗

Cite

@misc{prashant2026finetuning,
  title = {Fine-Tuning Without Forgetting via Loss-Adaptive Learning Rates},
  author = {P. Prashant and Jiongli Zhu and Aldan Creo and Babak Salimi},
  year = {2026},
  eprint = {2605.20005},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.20005},
}