Author

Mathieu Salzmann

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Jun 2026

PriFT: Guiding Supervised Fine-Tuning with Pretrained Priors

PriFT (Prior-support guided Fine-Tuning), which derives token weights from a frozen pretrained reference to obtain a stable reweighting signal unaffected by fine-tuning, achieves state-of-the-art results among SFT baselines, while also providing a stronger initialization for subsequent RL.

Ke Wang, Shuang-Qi Li, Mathieu Salzmann et al. · 2 citations · ⚡2