A generalized distillation process combining on-policy distillation with RL-based imitation learning for upward knowledge transfer from smaller to larger models
| Name | Categories | Topics | References | Credibility | CreateDate | UpdateDate | Title | RelatedNotes | NavigationOrder | Created |
|---|---|---|---|---|---|---|---|---|---|---|
| 20260604_language_models_need_sleep_self_modify_consolidate_memories | paper_analysis | memory_mechanism, self_evolving_agents, continual_learning, reinforce_learning, reasoning, llm | google_brain, knowledge_seeding, sleep_paradigm | 100 | Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories | memory_os_of_ai_agent, hipporag_neurobiologically_inspired_long_term_memory, muse_autoskill_self_evolving_skill_memory | [object Object] |