ILLUME+
📌 核心贡献
提出 DualViTok 双视觉 tokenizer，同时保留细粒度纹理和文本对齐语义，支持粗到细的图像表示策略。引入扩散模型作为图像 detokenizer，实现更高质量的生成和高效超分。在 3B 规模下，在理解、生成、编辑三项能力上均与 SOTA 方法竞争。
📖 摘要
We present ILLUME+ that leverages dual visual tokenization and a diffusion decoder to improve both deep semantic understanding and high-fidelity image generation. Existing unified models have struggled to simultaneously handle the three fundamental capabilities in a unified model: understanding, generation, and editing. Models like Chameleon and EMU3 utilize VQGAN for image discretization, due to the lack of deep semantic interaction, they lag behind specialist models like LLaVA in visual understanding tasks. To mitigate this, LaViT and ILLUME employ semantic encoders for tokenization, but they struggle with image editing due to poor texture preservation. Meanwhile, Janus series decouples the input and output image representation, limiting their abilities to seamlessly handle interleaved image-text understanding and generation. In contrast, ILLUME+ introduces a unified dual visual tokenizer, DualViTok, which preserves both fine-grained textures and text-aligned semantics while enabling a coarse-to-fine image representation strategy for multimodal understanding and generation. Additionally, we employ a diffusion model as the image detokenizer for enhanced generation quality and efficient super-resolution. ILLUME+ follows a continuous-input, discrete-output scheme within the unified MLLM and adopts a progressive training procedure that supports dynamic resolution across the vision tokenizer, MLLM, and diffusion decoder. This design allows for flexible and efficient context-aware image editing and generation across diverse tasks. ILLUME+ (3B) exhibits competitive performance against existing unified MLLMs and specialized models across multimodal understanding, generation, and editing benchmarks. With its strong performance, ILLUME+ provides a scalable and versatile foundation for future multimodal applications. Project Page: https://illume-unified-mllm.github.io/.
🔍 关键信息
| 字段 | 内容 |
|---|---|
| 机构 | Huawei Noah’s Ark Lab |
| 发表 | 2025-04-02 |
| 分类 | cs.CV |
| 链接 | arXiv |
📝 我的笔记
🔗 相关论文
基于/改进自： ILLUME 同方向： Transfusion