TUNA：为原生统一多模态模型驯服统一视觉表征
TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models
把 VAE 编码器与预训练表征编码器级联成统一连续视觉空间，让理解与生成共享同一表征，视觉研究者可直接复用该表征设计来消除理解/生成双编码器的格式错配，并借鉴其「表征编码器越强则全任务越好」的结论选型骨干。
原文依据 builds a unified continuous visual representation by cascading a VAE encoder with a representation encoder
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论统一多模态模型（UMM）旨在单一框架内联合完成多模态理解与生成。本文提出 TUNA，一种原生 UMM，它通过将变分自编码器编码器与表征编码器级联，构建统一的连续视觉表征。该统一表征空间使图像与视频的端到端处理可同时服务于理解与生成任务。与此前采用解耦表征的 UMM 相比，TUNA 的统一视觉空间避免了由分离编码器引入的表征格式错配，在理解与生成两方面均优于解耦方案。此外，我们观察到更强的预训练表征编码器在所有多模态任务上都能稳定带来更优性能，凸显了表征编码器的重要性。最后，在这一统一设定下，同时在理解数据与生成数据上联合训练，可使两项任务相互受益而非相互干扰。我们在多模态理解与生成基准上的大量实验表明，TUNA 在图像与视频理解、图像与视频生成以及图像编辑上均取得最优结果，验证了其统一表征设计的有效性与可扩展性。
英文原文摘要 1281 字符
Unified multimodal models (UMMs) aim to jointly perform multimodal understanding and generation within a single framework. We present TUNA, a native UMM that builds a unified continuous visual representation by cascading a VAE encoder with a representation encoder. This unified representation space allows end-to-end processing of images and videos for both understanding and generation tasks. Compared to prior UMMs with decoupled representations, TUNA's unified visual space avoids representation format mismatches introduced by separate encoders, outperforming decoupled alternatives in both understanding and generation. Moreover, we observe that stronger pretrained representation encoders consistently yield better performance across all multimodal tasks, highlighting the importance of the representation encoder. Finally, in this unified setting, jointly training on both understanding and generation data allows the two tasks to benefit from each other rather than interfere. Our extensive experiments on multimodal understanding and generation benchmarks show that TUNA achieves state-of-the-art results in image and video understanding, image and video generation, and image editing, demonstrating the effectiveness and scalability of its unified representation design.