12 citations · 41 across the 26 of their papers we have counts for
4 papers · 1 filter
Looped Diffusion Transformer
Yong Xien Chng, Tianyi Chen, Wenwen Tong +7
Improving text-to-image models has traditionally relied on increasing model size or the number of denoising steps. In this work, we explore an alternative way to scale computation…
Uncovering Understanding-Generation Synergy in Native Unified Multimodal Models: From Representation, Task to System
Penghao Wu, Haiwen Diao, Weichen Fan +3
While unified multimodal models (UMMs) jointly perform visual understanding and generation within a single model, functional unification does not guarantee learning synergy: the tw…
Vision as Unified Multimodal Generation
Xiaoyang Han, Jianhua Li, Kewang Deng +14
We formulate computer vision as unified multimodal generation, where heterogeneous visual tasks are expressed in the native text and image generation spaces of a unified multimodal…
From Pixels to Words -- Towards Native One-Vision Models at Scale
Haiwen Diao, Jiahao Wang, Penghao Wu +18
Current vision-language models (VLMs) typically stitch together separate image encoders and language decoders via multi-stage alignment, a modular framework that inevitably fragmen…