EPISODE · Jun 16, 2025 · 17 MIN
Memoir: A Sparse Notebook for Lifelong Model Editing
from Intellectually Curious · host Mike Breault
We dive into the challenge of updating large language models without erasing what they already know. The Memoir framework freezes the base model, adds a sparse residual memory, and uses a top-hash masking scheme to store and retrieve thousands of edits. Learn how edits are written to tiny memory slots, kept from colliding, and pulled at inference time, plus what experiments say about reliability, generalization, and locality.Note: This podcast was AI-generated, and sometimes AI can make mistakes. Please double-check any critical information.Sponsored by Embersilk LLC
What this episode covers
We dive into the challenge of updating large language models without erasing what they already know. The Memoir framework freezes the base model, adds a sparse residual memory, and uses a top-hash masking scheme to store and retrieve thousands of edits. Learn how edits are written to tiny memory slots, kept from colliding, and pulled at inference time, plus what experiments say about reliability, generalization, and locality. Note: This podcast was AI-generated, and sometimes AI can mak...
NOW PLAYING
Memoir: A Sparse Notebook for Lifelong Model Editing
No transcript for this episode yet
Similar Episodes
No similar episodes found.