Paper Discussion: Liquid: Language Models are Multi-Modal Generators

Join us for an insightful meetup as we look into the paper "Liquid: Language Models are Scalable and Unified Multi-modal Generators". Which builds upon the work in our previous meetup (Visual Autoregressive Modeling) and tries to unify the image generation and language generation token space with promising results.

Find out more by discussing their published paper together so you can decide how useful it is to you.

References:
https://arxiv.org/abs/2412.04332