MemLong
Free while signed in. Answers cite the passages they came from.
First page
The curator’s take
utilizes an external retriever for retrieving historical information which enhances the capabilities of long-context LLMs; it consistently outperforms other SoTA LLMs on long-context benchmarks and can extend the context length on a single 3090 GPU from 4k up to 80k.
Every Monday
Get next week’s papers.
The same picks and the same summaries, in your inbox. Free, and 176 issues deep.
Subscribe on Substack