mattfalconer

The model generates a prompt that's sent to SDXL, but it’s “seeded” with some randomness, we have an array of adjectives & colours that we input to try to make the output different.

Primarily the model is trying to generate “abstract publication cover art for a research paper covering the following topics…”.

Good point, we're updating now.

That is what it tries to do, the title, bulletpoints, summary and 'FAQs' try to simplify the paper, but LLMs are hard to tame when given an entire paper in the context window.

Agreed. It was built in 24 hours, and not as perfect as we'd like, but it does actually take the entire paper as context - the models aren't there yet, but we're going to keep refining this until it's super useful.