**摘要**
The past few decades have witnessed significant advances in the design of machine learning algorithms, from early studies on task-specific shallow models to more general deep Large Language Models (LLMs). Despite showing promising results in tasks that require instant prediction or in-context learning, existing models lack the ability to continually learn and effectively transfer their temporal in
👤 作者: Ali Behrouz, Farnoosh Hashemi, Vahab Mirrokni

---
🔗 **[Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories](https://arxiv.org/abs/2606.03979v1)**

> Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories
🏷️ 来源: ArXiv cs.AI
⏱️ 2026-06-03 14:01