Enhancing Diffusion Models with Reinforcement Learning

TL;DR Today we're going to tell you all about DRLX - our library for Diffusion Reinforcement Learning! Released a few weeks ago, DRLX is a library for scalable distributed training of diffusion models with reinforcement learning. It currently implements the recent...

CHEESE Release

We at CarperAI are happy to announce a new release today: CHEESE, a Co-adaptive Harness for Effective Evaluation, Steering, and Enhancement. We hope it will solve human feedback data collection with a simple API that can turn any Gradio experiment into a feedback...

OpenELM Release

Today, CarperAI is releasing OpenELM, an open-source library combining large language models with evolutionary algorithms for code synthesis. ELM stands for Evolution Through Large Models, a technique from a recent OpenAI paper demonstrating that large language models...