Diffusion Models

V-Co: A Closer Look at Visual Representation Alignment via Co-Denoising
A systematic study of visual co-denoising for representation-aligned pixel-space diffusion
Han Lin, Xichen Pan, Zun Wang, Yue Zhang, Chu Wang, Jaemin Cho, Mohit Bansal
Preprint Cite Code
Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents
a unified framework that bridges multimodal LLMs and diffusion models with patch-level CLIP latents
Han Lin, Jaemin Cho, Amir Zadeh, Chuan Li, Mohit Bansal
Preprint Cite Code Project
Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents