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

Source: [JEPA-T: Joint-Embedding Predictive Architecture with Text Fusion for Image Generation](<https://www.sota2.com/research/paper/68fa7bc51e209131cea8a53e>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:48:24.291Z

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

Published: 2025-10-01T14:51:10.000Z

## 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

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2510.00974>)

[PDF](<https://arxiv.org/pdf/2510.00974.pdf>)
