一个视觉模型搞定理解、生成、编辑，不再需要两套系统
现在的多模态模型，理解图片和生成图片用的是两套视觉系统：理解靠语义编码器(只抓概念，丢细节)，生成靠VAE(保细节，但不懂语义)。这篇发现，问题不在语义ViT本身，而在它把图片切成小块的方式——那种切法天然逼着模型往抽象走。研究者换了一种切法(Patch Reparameterization)，让同一个ViT既能保留语义理解，又能保住像素级细节，从而在一个模型里同时做理解、生成和编辑，不再需要两套视觉通路。他们把这个思路放大到8B参数的MoE模型UniSpace，实测能做文生图和指令编辑。它不是你明天能用上的，但它是视觉模型架构的一个方向性变化：未来可能所有视觉任务都跑在同一个视觉空间里，不再分家。
📄 原文摘要(英文)
Semantic vision encoders have become a central visual interface for multimodal understanding and semantic conditioning in image generation. However, their final tokens discard fine-grained visual details, leading to poor pixel reconstruction and limiting their use in reconstruction-sensitive tasks such as image generation and editing. In this work, we ask whether understanding, generation, and editing can be modeled in a single visual representation space built from a pretrained semantic ViT. We show that the frozen Transformer blocks of a semantic ViT are not intrinsically unable to preserve visual details. Instead, the original patch parameterization drives the representation toward semantic abstraction, making fine-grained information difficult to recover from the final tokens. Based on this observation, we introduce Patch Reparameterization, which preserves the original semantic pathway while adding a reconstruction-aware patch embedding that provides fine-grained visual information to the same frozen ViT blocks. The resulting unified representation preserves multimodal understanding while enabling high-fidelity image reconstruction and a favorable reconstruction--generation trade-off. We further scale this representation into UniSpace, an 8B Mixture-of-Transformer-Experts model that performs understanding, generation, and editing in the same visual space without a separate VAE pathway. System-level evaluations demonstrate practical text-to-image generation and instruction-based image editing, showing that a reparameterized pretrained ViT can serve as a unified visual interface for scalable multimodal modeling.