2024/11/29 by Michael Tschannen, André Susano Pinto, Tschannen, Michael +3 · 5 voices · 22 citations
Computer Science · Mathematics · #Artificial intelligence #Autoregressive model #Computer science #Econometrics #Generative grammar #Generative model #Image Processing and 3D Reconstruction #Mathematics #cs.AI #cs.CV #cs.LG
paper · pdf · doi:10.48550/arxiv.2411.19722
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2024/11/29 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Removing modeling constraints and unifying architectures across domains has been a key driver of the recent progress in training large multimodal models. However, most of these models still rely on many separately trained components such as modality-specific encoders and decoders. In this work, we further streamline joint generative modeling of images and text. We propose an autoregressive decoder-only transformer - JetFormer - which is trained to directly maximize the likelihood of raw data, without relying on any separately pretrained components, and can understand and generate both text and images. Specifically, we leverage a normalizing flow model to obtain a soft-token image representation that is jointly trained with an autoregressive multimodal transformer. The normalizing flow model serves as both an image encoder for perception tasks and an image decoder for image generation tasks during inference. JetFormer achieves text-to-image generation quality competitive with recent VQ-VAE- and VAE-based baselines. These baselines rely on pretrained image autoencoders, which are trained with a complex mixture of losses, including perceptual ones. At the same time, JetFormer demonstrates robust image understanding capabilities. To the best of our knowledge, JetFormer is the first model that is capable of generating high-fidelity images and producing strong log-likelihood bounds.