# ILLUME-X：面向自由形式交错图文生成的统一多模态模型

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-06-29 08:00
- AIHOT 分数：43
- AIHOT 链接：https://aihot.virxact.com/items/cmr0mfd3r035jslolobdv1i6g
- 原文链接：https://arxiv.org/abs/2606.30054

## AI 摘要

ILLUME-X是一个统一多模态模型，能够自主生成高质量、自由形式的交错文本-图像序列。它通过三项核心组件实现：面向交错图文生成的扩展训练数据管道、基于自适应目标的渐进训练策略（适用于自由长度的多模态token序列），以及用于评估交错图文序列的客观综合方法ILScore。ILLUME-X在风格迁移、图像分解和故事讲述等多个交错图文生成任务上优于此前统一模型。

## 正文

The advancement of generative AI models capable of producing text and image marks a critical step forward in the realm of multimodal intelligence, particularly for tasks involving the interleaving of both modalities. To advance this intelligence to the next stage, it is crucial for models to autonomously generate free-form interleaved text-image sequences. In this paper, we introduce ILLUME-X, an advanced unified multimodal paradigm that enables high-quality, free-form interleaved text-image generation by improving multimodal data efficiency and stabilizing the multimodal training process. ILLUME-X comprises three key components: (i) an expanded training data pipeline optimized for interleaved text-image generation, (ii) a progressive training strategy with self-adaptive objectives for free-length multimodal token sequences, and (iii) an objective and comprehensive evaluation method ILScore for interleaved text-image sequences. Notably, our ILLUME-X outperforms previous unified models across multiple interleaved text-image generation tasks like style transfer, image decomposition and storytelling.