Unified Text-Image Generation with Weakness-Targeted Post-Training

• URL: http://arxiv.org/abs/2601.04339v1
• Date: Wed, 07 Jan 2026 19:19:44 GMT
• Title: Unified Text-Image Generation with Weakness-Targeted Post-Training
• Authors: Jiahui Chen, Philippe Hansen-Estruch, Xiaochuang Han, Yushi Hu, Emily Dinan, Amita Kamath, Michal Drozdzal, Reyhane Askari-Hemmat, Luke Zettlemoyer, Marjan Ghazvininejad,
• Abstract summary: Unified multimodal generation architectures that jointly produce text and images have recently emerged as a promising direction for text-to-image (T2I) synthesis.<n>This work explores post-training to achieve fully unified text-image generation, where models autonomously transition from textual reasoning to visual synthesis.
• Score: 57.956648078400775
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• When Vision Meets Texts in Listwise Reranking [1.2691047660244335]
  Rank-Nexus is a multimodal image-text document reranker that performs listwise qualitative reranking on retrieved lists incorporating both images and texts.<n>We first train modalities separately: leveraging abundant text reranking data, we distill knowledge into the text branch.<n>For images, where data is scarce, we construct distilled pairs from multimodal large language model (MLLM) captions on image retrieval benchmarks.
  arXiv  Detail & Related papers  (2026-01-28T13:57:14Z)
• Exploring a Unified Vision-Centric Contrastive Alternatives on Multi-Modal Web Documents [99.62178668680578]
  We propose Vision-Centric Contrastive Learning (VC2L), a unified framework that models text, images, and their combinations using a single vision transformer.<n> VC2L operates entirely in pixel space by rendering all inputs, whether textual, visual, or combined, as images.<n>To capture complex cross-modal relationships in web documents, VC2L employs a snippet-level contrastive learning objective that aligns consecutive multimodal segments.
  arXiv  Detail & Related papers  (2025-10-21T14:59:29Z)
• Interleaving Reasoning for Better Text-to-Image Generation [83.69082794730664]
  We introduce Interleaving Reasoning Generation (IRG), a framework that alternates between text-based thinking and image synthesis.<n>To train IRG effectively, we propose Interleaving Reasoning Generation Learning (IRGL), which targets two sub-goals.<n>Experiments show SoTA performance, yielding absolute gains of 5-10 points on GenEval, WISE, TIIF, GenAI-Bench, and OneIG-EN.
  arXiv  Detail & Related papers  (2025-09-08T17:56:23Z)
• Unified Autoregressive Visual Generation and Understanding with Continuous Tokens [52.21981295470491]
  We present UniFluid, a unified autoregressive framework for joint visual generation and understanding.<n>Our unified autoregressive architecture processes multimodal image and text inputs, generating discrete tokens for text and continuous tokens for image.<n>We find though there is an inherent trade-off between the image generation and understanding task, a carefully tuned training recipe enables them to improve each other.
  arXiv  Detail & Related papers  (2025-03-17T17:58:30Z)
• End-to-end Training for Text-to-Image Synthesis using Dual-Text Embeddings [5.217870815854702]
  We study an approach to learning text embeddings specifically tailored to the Text-to-Image synthesis network.<n>We combine generative and contrastive training and use two embeddings, one optimized to enhance the photo-realism of the generated images, and the other seeking to capture text-to-image alignment.<n>A comprehensive set of experiments on three text-to-image benchmark datasets reveal that having two separate embeddings gives better results than using a shared one and that such an approach performs favourably in comparison with methods that use text representations from a pre-trained text encoder trained using a discriminative approach.
  arXiv  Detail & Related papers  (2025-02-03T16:40:47Z)
• A Framework For Image Synthesis Using Supervised Contrastive Learning [14.016543383212706]
  Text-to-image (T2I) generation aims at producing realistic images corresponding to text descriptions.<n>We propose a framework leveraging both inter- and inner-modal correspondence by label guided supervised contrastive learning.<n>We demonstrate our framework on four novel T2I GANs by both single-object dataset CUB and multi-object dataset COCO.
  arXiv  Detail & Related papers  (2024-12-05T08:15:37Z)
• Contextualized Diffusion Models for Text-Guided Image and Video Generation [67.69171154637172]
  Conditional diffusion models have exhibited superior performance in high-fidelity text-guided visual generation and editing. We propose a novel and general contextualized diffusion model (ContextDiff) by incorporating the cross-modal context encompassing interactions and alignments between text condition and visual sample. We generalize our model to both DDPMs and DDIMs with theoretical derivations, and demonstrate the effectiveness of our model in evaluations with two challenging tasks: text-to-image generation, and text-to-video editing.
  arXiv  Detail & Related papers  (2024-02-26T15:01:16Z)
• UNIMO-G: Unified Image Generation through Multimodal Conditional Diffusion [36.06457895469353]
  UNIMO-G is a conditional diffusion framework that operates on multimodal prompts with interleaved textual and visual inputs. It excels in both text-to-image generation and zero-shot subject-driven synthesis.
  arXiv  Detail & Related papers  (2024-01-24T11:36:44Z)
• ERNIE-ViLG: Unified Generative Pre-training for Bidirectional Vision-Language Generation [22.47279425592133]
  We propose ERNIE-ViLG, a unified generative pre-training framework for bidirectional image-text generation. For the text-to-image generation process, we propose an end-to-end training method to jointly learn the visual sequence generator and the image reconstructor. We train a 10-billion parameter ERNIE-ViLG model on a large-scale dataset of 145 million (Chinese) image-text pairs.
  arXiv  Detail & Related papers  (2021-12-31T03:53:33Z)
• Towards Open-World Text-Guided Face Image Generation and Manipulation [52.83401421019309]
  We propose a unified framework for both face image generation and manipulation. Our method supports open-world scenarios, including both image and text, without any re-training, fine-tuning, or post-processing.
  arXiv  Detail & Related papers  (2021-04-18T16:56:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.