Fine-Tuning Diffusion Language Models with Context Selection and Target Weighting
This story is from 2026-10-01. It is preserved in the archive; the latest stories are on the live feed.
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 therefore determines both the context available to the model an…
Read the full story at arXiv cs.AI ↗
Timeline · 1 report
- 2026-10-01 04:00 · arXiv cs.AI
Fine-Tuning Diffusion Language Models with Context Selection and Target Weighting