Fine-Tuning Diffusion Language Models with Context Selection and Target Weighting
arXiv:2609.38385v1 Announce Type: new Abstract: Supervised fine-tuning of discrete diffusion language models masks some response tokens and trains the model to recover their original values from the visible context. The masking pattern...
Read more: https://arxiv.org/abs/2609.38385
Scan with your phone
Scan with your phone