Dual Diffusion for Unified Image Generation and Understanding
📌 核心贡献
该论文提出了一种大规模、端到端、用于多模态理解与生成的新型扩散模型，显著超越了现有基于扩散的多模态模型。它首次实现了全面的视觉-语言建模能力，通过结合多模态扩散Transformer (MM-DiT) 和离散扩散语言建模的最新进展，旨在统一图像生成和视觉理解任务。
📖 摘要
Diffusion models have gained tremendous success in text-to-image generation, yet still lag behind with visual understanding tasks, an area dominated by autoregressive vision-language models. We propose a large-scale and fully end-to-end diffusion model for multi-modal understanding and generation that significantly improves on existing diffusion-based multimodal models, and is the first of its kind to support the full suite of vision-language modeling capabilities. Inspired by the multimodal diffusion transformer (MM-DiT) and recent advances in discrete diffusion language modeling, we leverage a cross-modal maximum likelihood estimation framework that simultaneously trains the conditional likelihoods of both images and text jointly under a single loss function, which is back-propagated through both branches of the diffusion transformer. The resulting model is highly flexible and capable of a wide range of tasks including image generation, captioning, and visual question answering. Our model attained competitive performance compared to recent unified image understanding and generation models, demonstrating the potential of multimodal diffusion modeling as a promising alternative to autoregressive next-token prediction models.
🔍 关键信息
| 字段 | 内容 |
|---|---|
| 发表 | 2024-12-31 |
| 分类 | cs.CV, cs.AI |
| 链接 | arXiv |