Saved in:
Bibliographic Details
Main Authors: Chen, Jiahui, Hansen-Estruch, Philippe, Han, Xiaochuang, Hu, Yushi, Dinan, Emily, Kamath, Amita, Drozdzal, Michal, Askari-Hemmat, Reyhane, Zettlemoyer, Luke, Ghazvininejad, Marjan
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.04339
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Unified multimodal generation architectures that jointly produce text and images have recently emerged as a promising direction for text-to-image (T2I) synthesis. However, many existing systems rely on explicit modality switching, generating reasoning text before switching manually to image generation. This separate, sequential inference process limits cross-modal coupling and prohibits automatic multimodal generation. This work explores post-training to achieve fully unified text-image generation, where models autonomously transition from textual reasoning to visual synthesis within a single inference process. We examine the impact of joint text-image generation on T2I performance and the relative importance of each modality during post-training. We additionally explore different post-training data strategies, showing that a targeted dataset addressing specific limitations achieves superior results compared to broad image-caption corpora or benchmark-aligned data. Using offline, reward-weighted post-training with fully self-generated synthetic data, our approach enables improvements in multimodal image generation across four diverse T2I benchmarks, demonstrating the effectiveness of reward-weighting both modalities and strategically designed post-training data.