1
Self-Policy Distillation via Capability-Selective Subspace Projection
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…