snap-stanford /
memorilla
🦍 Memorilla: Latent Semantic Memory for LLMs
Updated 2Â min ago
+1 stars gained this week
Stars gained each day, last 30 days
Usual pace · 1 / day
Oct 4Oct 19Today
This week Before Usual pace
In short
Memorilla compresses an entire document collection, such as a user's chat history or a long book, into 16 query-dependent memory tokens for a frozen LLM. It targets researchers working on long-context memory and personalization.
Summary written by AI from the repository’s description and README.
snap-stanford / memorilla
View on GitHub(opens in new tab)