返回列表
更多 →
Fine-Tuning Diffusion Language Models with Context Selection and Target Weighting
国外 · 纸上电台 · 发布于 2026-10-01 · 0 次阅读
来源：arXiv cs.AI · 2026-10-01 · 新型 AI / 新品发布
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 v
本条资讯由「纸上电台」整理自 arXiv cs.AI，仅作交流参考，版权归原作者所有。
