🚀NEW LABGetting Started with Claude AgentsStart lab
Memory

Unlimiformer

First page
Unlimiformer
Paper summary

Long-range Transformers with unlimited length input via external datastores.

Ask this paper

Key points
01

External datastore: Augments pre-trained encoder-decoder Transformers with a kNN datastore to support arbitrary-length input.

02

Training-free: No additional training required - works with existing pretrained Transformers.

03

Long-document tasks: Demonstrates usefulness in long-document summarization where context spans many thousands of tokens.

04

RAG-enhancer: Could improve the performance of retrieval-enhanced LLMs by providing unlimited lookback over long conversations or documents.

Every Monday
Get next week’s papers.
Subscribe on Substack