Trace-Based On-Policy Distillation for Masked Diffusion Language Models
英文标题：Trace-Based On-Policy Distillation for Masked Diffusion Language Models
arXiv:2607.16872v1 Announce Type: new Abstract: Diffusion large language models (dLLMs) are a promising alternative to autoregressive generation. However, reasoning-oriented post-training for dLLMs remains challenging. Supervised fine-tuning (SFT) for dLLMs requires dense but often off-policy maske
打开原文相关 1.6 · 机会 0
2.1 KB
461 B
612 B
380 B
9.1 KB
32.7 KB
22.8 KB
24.2 KB
34.7 KB
中文
arXiv:2607.16872v1 Announce Type: new Abstract: Diffusion large language models (dLLMs) are a promising alternative to autoregressive generation. However, reasoning-oriented post-training for dLLMs remains challenging. Supervised fine-tuning (SFT) for dLLMs requires dense but often off-policy maske
中文全文翻译正在补齐，可先查看下方英文原文。
English / 原文
BibTeX formatted citation
×