HKUST Survey Maps In-Parameter Memory Augmentation for LLMs

A HKUST survey systematically reviews in-parameter memory augmentation for LLMs, which stores post-training knowledge in weights or adapters instead of context. It categorizes methods by parameter location and online/offline acquisition.

2026-10-07 ~ 2026-10-07 · 2 related posts

• Survey maps in-parameter memory methods for LLMs by placement and acquisition time — _reachsumit · 2026-10-07
• HKUST surveys in-parameter memory: storing post-training knowledge in LLM weights instead of context — HKUST · 2026-10-07