Unified multimodal models (UMMs) aim to handle perception and generation in a single model. Yet existing UMMs still rely on a frozen, separately pretrained VAE for image generation, imposing a structural bottleneck. Naively removing it introduces a quality gap, as the model must learn both high-level structure and low-level details from raw pixels. In this paper, we propose Representation Forcing (RF), a technique that closes this gap by making representation prediction a native capability of the model. Concretely, RF forces the decoder to autoregressively predict visual representations as intermediate tokens before pixels; these tokens then stay in context to guide pixel diffusion within the same backbone. By turning representations from perception outputs into generation targets, RF eliminates the need for any external generative latent space. We find that RF benefits both understanding and generation. On image generation, our pixel-space model with RF matches state-of-the-art VAE-based unified models. On image understanding, pixel-space RF generally outperforms its VAE-based variant. Together, these results offer an effective step toward end-to-end, bottleneck-free UMMs.

翻译：统一多模态模型旨在通过单一模型实现感知与生成任务。然而现有统一多模态模型仍依赖独立预训练的冻结变分自编码器进行图像生成，由此引入了结构性瓶颈。若直接移除该模块则会导致质量下降，因为模型需要从原始像素同时学习高层结构与低层细节。本文提出表征强制技术，通过将表征预测内化为模型原生能力来弥合这一差距。具体而言，表征强制迫使解码器在生成像素之前以自回归方式将视觉表征作为中间令牌进行预测；这些令牌随后在上下文语境中保留，在同一个骨干网络中引导像素扩散。通过将表征从感知输出转化为生成目标，表征强制消除了对外部生成潜空间的依赖。我们发现表征强制同时提升了理解与生成性能。在图像生成方面，采用表征强制机制的像素空间模型性能与基于变分自编码器的先进统一模型相当。在图像理解方面，基于像素空间的表征强制方法普遍优于其变分自编码器变体。这些成果共同为构建端到端无瓶颈的统一多模态模型提供了有效路径。