#artificial intelligence
Jan 2026
Unified Text-Image Generation with Weakness-Targeted Post-Training
This work explores post-training to achieve fully unified text-image generation, where a model autonomously transitions from textual reasoning to visual synthesis within a single inference process, and enables improvements in multimodal image generation across four diverse, independent T2I benchmarks.
Jiahui Chen, Philippe Hansen-Estruch, Xiao-Chuang Han et al.
· arXiv.org · 1 citation