VentureBeat

MIT’s new ‘recursive’ framework lets LLMs process 10 million tokens without context rot

Recursive language models (RLMs) are an inference technique developed by researchers at MIT CSAIL that treat long prompts as an external environment to the model. Instead of forcing the entire prompt ...
InfoQ

MIT's Recursive Language Models Improve Performance on Long-Context Tasks

Researchers at MIT's CSAIL published a design for Recursive Language Models (RLM), a technique for improving LLM performance on long-context tasks. RLMs use a programming environment to recursively ...
Nature

The less human humans?: Recursion, songbirds and the limits of language

Brains sell magazines, mathematical linguistics sells caffeine. That basically summarizes coverage of a recent study on songbirds' "artificial grammar system". More on that later. First, a summary of ...