← 研踪 PaperTrailCVF · CVPR 2026:cvf:1c52d9e36eb847629a095dec264fae3e · 记录 #1
TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models
Liu, ZhihengRen, WeimingLiu, HaozheZhou, ZijianChen, ShoufaQiu, HaonanHuang, XiaokeAn, ZhaochongYang, FannyPatel, AdityaAtliha, ViktarNg, TonyHan, XiaoZhu, ChuyanZhang, ChenyangLiu, DingPerez-Rua, Juan-ManuelHe, SenSchmidhuber, JürgenChen, WenhuLuo, PingLiu, WeiXiang, TaoSchult, JonasCong, Yuren 来源日期（仅到年份） 2026
来源记录日期 2026
雷达观测 2026-11-05 02:35
摘要
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.
论文发现出处
这些页面提供论文线索，不代表同行评审或质量认证。
观测到的版本
平台记录号代表本站观测到的元数据变化，不是作者修订号。来源日期仅到月份或年份时，按该月或该年首日存档。
记录 #1 · 2026 · 最新观测版本
TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models
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.
查看此版本解读 →查看此版本原文 ↗