Pith. sign in

REVIEW 5 cited by

JetFormer: An Autoregressive Generative Model of Raw Images and Text

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2411.19722 v2 pith:XOXV7X4L submitted 2024-11-29 cs.LG cs.AIcs.CV

classification cs.LGcs.AIcs.CV
keywords imagejetformerimagesmodeltrainedautoregressivetextbaselines
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

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.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. MIMFlow: Integrating Masked Image Modeling with Normalizing Flows for End-to-End Image Generation

    cs.CV 2026-06 unverdicted novelty 6.0 of 10

    MIMFlow uses a VAE on masked images to feed semantic latents to a normalizing flow while a decoder handles high-frequency details, reporting FID 2.50 and 71.3% linear probing on ImageNet 256x256 with 128 tokens.

  2. SRC-Flow: Compact Semantic Representations Enable Normalizing Flows for Image Generation

    cs.CV 2026-05 unverdicted novelty 6.0 of 10

    SRC-Flow compresses RAE features via a Semantic Representation Compressor into a low-dimensional space, enabling normalizing flows to reach gFID 1.65 on ImageNet 256x256 and 2.07 on 512x512 while retaining exact likelihoods.

  3. PixNerd: Pixel Neural Field Diffusion

    cs.CV 2025-07 conditional novelty 6.0 of 10

    PixNerd is a single-stage pixel-space diffusion transformer that uses predicted neural field weights to decode large patches, reaching 2.15 FID on ImageNet 256 without a VAE.

  4. Diffuse Everything: Multimodal Diffusion Models on Arbitrary State Spaces

    cs.LG 2025-06 conditional novelty 6.0 of 10

    A unified diffusion framework with per-modality noise clocks lets one model generate images, text, and tabular data jointly or conditionally in their native spaces.

  5. STARFlow: Scaling Latent Normalizing Flows for High-resolution Image Synthesis

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A latent-space transformer autoregressive flow with one deep block plus shallow refiners, tuned noise injection, and score-based guidance reaches competitive FID in high-resolution image synthesis, the first at this s...

Pith tools