https://github.com/lucidrains/sdft-pytorch

Explorations into the proposed SDFT, Self-Distillation Enables Continual Learning, from Shenfeld et al. of MIT
https://github.com/lucidrains/sdft-pytorch

artificial-intelligence continual-learning deep-learning

Last synced: 5 months ago
JSON representation

Explorations into the proposed SDFT, Self-Distillation Enables Continual Learning, from Shenfeld et al. of MIT

• Host: GitHub
• URL: https://github.com/lucidrains/sdft-pytorch
• Owner: lucidrains
• License: mit
• Created: 2026-02-01T14:04:03.000Z (5 months ago)
• Default Branch: main
• Last Pushed: 2026-02-05T13:37:38.000Z (5 months ago)
• Last Synced: 2026-02-06T05:46:34.979Z (5 months ago)
• Topics: artificial-intelligence, continual-learning, deep-learning
• Language: Python
• Homepage:
• Size: 493 KB
• Stars: 27
• Watchers: 0
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          


## SDFT - Pytorch (wip)

Explorations into the proposed SDFT, [Self-Distillation Enables Continual Learning](https://arxiv.org/abs/2601.19897), from Shenfeld et al. of MIT

## Citations

```bibtex

@misc{shenfeld2026selfdistillationenablescontinuallearning,

    title   = {Self-Distillation Enables Continual Learning}, 

    author  = {Idan Shenfeld and Mehul Damani and Jonas Hübotter and Pulkit Agrawal},

    year    = {2026},

    eprint  = {2601.19897},

    archivePrefix = {arXiv},

    primaryClass = {cs.LG},

    url     = {https://arxiv.org/abs/2601.19897}, 

}

```