提出一种基于分歧调度的策略自蒸馏方法，有效提升大模型推理训练效果。
arXiv:2607.02502v1 Announce Type: cross Abstract: On-policy self-distillation (OPSD) has emerged as a practical method for training large language mod…
自蒸馏让大模型在难题上学会专家推理，摆脱依赖更强模型或采样正确解的局限
arXiv:2602.02405v2 Announce Type: replace-cross Abstract: Improving the reasoning capabilities of large language models (LLMs) typically relies either…
物理引导的自我蒸馏策略优化，解决LLM后训练中更新步长信任难题，提升模型对齐效果。
arXiv:2606.03620v1 Announce Type: cross Abstract: Self-distilled policy optimization (SDPO) has become a popular paradigm for LLM post-training, where…
大模型推理新突破：在线策略自蒸馏结合结果引导的logit转向，有效提升推理性能。
arXiv:2605.12400v2 Announce Type: replace Abstract: We study on-policy self-distillation (OPSD), where a language model improves its reasoning ability…
用特权信息生成密集token级监督，提升LLM推理能力的新蒸馏方法。
arXiv:2605.28791v1 Announce Type: cross Abstract: On-policy self-distillation (SD) improves LLM reasoning by using teacher-side privileged information…
无需外部信号，自我蒸馏新范式：能力选择子空间投影让LLM自主提升性能
arXiv:2605.22675v1 Announce Type: new Abstract: Self-distillation bootstraps large language models (LLMs) by training on their own generations. Howeve…
互补自蒸馏如何维护大模型上下文完整性？这项研究提出双模型协作新方案，为LLM安全对齐提供创新思路。
arXiv:2605.20258v1 Announce Type: new Abstract: Contextual Integrity (CI) defines privacy not merely as keeping information hidden, but as governing i…