JEPA-T: Joint-Embedding Predictive Architecture with Text Fusion for Image Generation

• URL: http://arxiv.org/abs/2510.00974v1
• Date: Wed, 01 Oct 2025 14:51:10 GMT
• Title: JEPA-T: Joint-Embedding Predictive Architecture with Text Fusion for Image Generation
• Authors: Siheng Wan, Zhengtao Yao, Zhengdao Li, Junhao Dong, Yanshu Li, Yikai Li, Linshan Li, Haoyan Xu, Yijiang Li, Zhikang Dong, Huacan Wang, Jifeng Shen,
• Abstract summary: We propose a unified multimodal framework that encodes images and captions into discrete visual and textual tokens.<n>We incorporate cross-attention after the feature predictor for conditional denoising while maintaining a task-agnostic backbone.<n>Our approach shows that late architectural fusion combined with objective-level alignment offers an effective balance between conditioning strength and backbone generality in token-based T2I.
• Score: 10.00677022779314
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Modern Text-to-Image (T2I) generation increasingly relies on token-centric architectures that are trained with self-supervision, yet effectively fusing text with visual tokens remains a challenge. We propose \textbf{JEPA-T}, a unified multimodal framework that encodes images and captions into discrete visual and textual tokens, processed by a joint-embedding predictive Transformer. To enhance fusion, we incorporate cross-attention after the feature predictor for conditional denoising while maintaining a task-agnostic backbone. Additionally, raw texts embeddings are injected prior to the flow matching loss to improve alignment during training. During inference, the same network performs both class-conditional and free-text image generation by iteratively denoising visual tokens conditioned on text. Evaluations on ImageNet-1K demonstrate that JEPA-T achieves strong data efficiency, open-vocabulary generalization, and consistently outperforms non-fusion and late-fusion baselines. Our approach shows that late architectural fusion combined with objective-level alignment offers an effective balance between conditioning strength and backbone generality in token-based T2I.The code is now available: https://github.com/justin-herry/JEPA-T.git

Related papers

• Unified Text-Image Generation with Weakness-Targeted Post-Training [57.956648078400775]
  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.
  arXiv  Detail & Related papers  (2026-01-07T19:19:44Z)
• ResTok: Learning Hierarchical Residuals in 1D Visual Tokenizers for Autoregressive Image Generation [64.84095852784714]
  Residual Tokenizer (ResTok) is a 1D visual tokenizer that builds hierarchical residuals for both image tokens and latent tokens.<n>We show that restoring hierarchical residual priors in visual tokenization significantly improves AR image generation, achieving a gFID of 2.34 on ImageNet-256 with only 9 sampling steps.
  arXiv  Detail & Related papers  (2026-01-07T14:09:18Z)
• Qwen-Image Technical Report [86.46471547116158]
  We present Qwen-Image, an image generation foundation model that achieves significant advances in complex text rendering and precise image editing.<n>We design a comprehensive data pipeline that includes large-scale data collection, filtering, annotation, synthesis, and balancing.<n>Qwen-Image performs exceptionally well in alphabetic languages such as English, and also achieves remarkable progress on more challenging logographic languages like Chinese.
  arXiv  Detail & Related papers  (2025-08-04T11:49:20Z)
• Rethinking Cross-Modal Interaction in Multimodal Diffusion Transformers [79.94246924019984]
  Multimodal Diffusion Transformers (MM-DiTs) have achieved remarkable progress in text-driven visual generation.<n>We propose textbfTemperature-Adjusted Cross-modal Attention (TACA), a parameter-efficient method that dynamically rebalances multimodal interactions.<n>Our findings highlight the importance of balancing cross-modal attention in improving semantic fidelity in text-to-image diffusion models.
  arXiv  Detail & Related papers  (2025-06-09T17:54:04Z)
• Object-Attribute Binding in Text-to-Image Generation: Evaluation and Control [58.37323932401379]
  Current diffusion models create images given a text prompt as input but struggle to correctly bind attributes mentioned in the text to the right objects in the image. We propose focused cross-attention (FCA) that controls the visual attention maps by syntactic constraints found in the input sentence. We show substantial improvements in T2I generation and especially its attribute-object binding on several datasets.
  arXiv  Detail & Related papers  (2024-04-21T20:26:46Z)
• An Intermediate Fusion ViT Enables Efficient Text-Image Alignment in Diffusion Models [18.184158874126545]
  We investigate how different fusion strategies can affect vision-language alignment. A specially designed intermediate fusion can boost text-to-image alignment with improved generation quality. Our model achieves a higher CLIP Score and lower FID, with 20% reduced FLOPs, and 50% increased training speed.
  arXiv  Detail & Related papers  (2024-03-25T08:16:06Z)
• A Layer-Wise Tokens-to-Token Transformer Network for Improved Historical Document Image Enhancement [13.27528507177775]
  We propose textbfT2T-BinFormer which is a novel document binarization encoder-decoder architecture based on a Tokens-to-token vision transformer. Experiments on various DIBCO and H-DIBCO benchmarks demonstrate that the proposed model outperforms the existing CNN and ViT-based state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-12-06T23:01:11Z)
• Leveraging Unpaired Data for Vision-Language Generative Models via Cycle Consistency [47.3163261953469]
  Current vision-language generative models rely on expansive corpora of paired image-text data to attain optimal performance and generalization capabilities. We introduce ITIT: an innovative training paradigm grounded in the concept of cycle consistency which allows vision-language training on unpaired image and text data. ITIT is comprised of a joint image-text encoder with disjoint image and text decoders that enable bidirectional image-to-text and text-to-image generation in a single framework.
  arXiv  Detail & Related papers  (2023-10-05T17:55:19Z)
• COTS: Collaborative Two-Stream Vision-Language Pre-Training Model for Cross-Modal Retrieval [59.15034487974549]
  We propose a novel COllaborative Two-Stream vision-language pretraining model termed COTS for image-text retrieval. Our COTS achieves the highest performance among all two-stream methods and comparable performance with 10,800X faster in inference. Importantly, our COTS is also applicable to text-to-video retrieval, yielding new state-ofthe-art on the widely-used MSR-VTT dataset.
  arXiv  Detail & Related papers  (2022-04-15T12:34:47Z)
• Text to Image Generation with Semantic-Spatial Aware GAN [41.73685713621705]
  A text to image generation (T2I) model aims to generate photo-realistic images which are semantically consistent with the text descriptions. We propose a novel framework Semantic-Spatial Aware GAN, which is trained in an end-to-end fashion so that the text encoder can exploit better text information.
  arXiv  Detail & Related papers  (2021-04-01T15:48:01Z)
• DF-GAN: A Simple and Effective Baseline for Text-to-Image Synthesis [80.54273334640285]
  We propose a novel one-stage text-to-image backbone that directly synthesizes high-resolution images without entanglements between different generators. We also propose a novel Target-Aware Discriminator composed of Matching-Aware Gradient Penalty and One-Way Output. Compared with current state-of-the-art methods, our proposed DF-GAN is simpler but more efficient to synthesize realistic and text-matching images.
  arXiv  Detail & Related papers  (2020-08-13T12:51:17Z)
• TIME: Text and Image Mutual-Translation Adversarial Networks [55.1298552773457]
  We propose Text and Image Mutual-Translation Adversarial Networks (TIME) TIME learns a T2I generator G and an image captioning discriminator D under the Generative Adversarial Network framework. In experiments, TIME achieves state-of-the-art (SOTA) performance on the CUB and MS-COCO dataset.
  arXiv  Detail & Related papers  (2020-05-27T06:40:12Z)

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.