{"slug": "muon-rt-reusing-the-teacher-s-trajectory-for-momentum-free-muon-for-llm-self", "title": "MUON-RT Reusing the Teacher's Trajectory for Momentum-Free Muon for LLM Self-Distillation", "summary": "A paper proposes Muon-RT, a variant of the Muon optimizer for large language model self-distillation that reuses the exponential moving average (EMA) teacher's trajectory instead of storing a separate momentum buffer, eliminating that persistent training memory. The method targets the memory overhead Muon adds on top of EMA-teacher self-distillation, which already retains a history of student updates.", "body_md": "Self-distillation methods for large language models with an exponential moving average (EMA) teacher already retain a history of student updates. Muon nevertheless stores a separate momentum buffer, increasing persistent training memory. We propose Muon with Reused Teacher (Muon-RT), which reuses th", "url": "https://wpnews.pro/news/muon-rt-reusing-the-teacher-s-trajectory-for-momentum-free-muon-for-llm-self", "canonical_source": "https://aiflash.com/news/145929/", "published_at": "2026-11-05 06:00:00+00:00", "updated_at": "2026-11-05 06:19:39.070531+00:00", "lang": "en", "topics": ["machine-learning", "large-language-models", "ai-research", "artificial-intelligence"], "entities": ["Muon", "Muon-RT"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/muon-rt-reusing-the-teacher-s-trajectory-for-momentum-free-muon-for-llm-self", "markdown": "https://wpnews.pro/news/muon-rt-reusing-the-teacher-s-trajectory-for-momentum-free-muon-for-llm-self.md", "text": "https://wpnews.pro/news/muon-rt-reusing-the-teacher-s-trajectory-for-momentum-free-muon-for-llm-self.txt", "jsonld": "https://wpnews.pro/news/muon-rt-reusing-the-teacher-s-trajectory-for-momentum-free-muon-for-llm-self.jsonld"}}