LayoutDiffusion: Controllable Diffusion Model for Layout-to-image Generation

LayoutDiffusion: 布局到图像生成的可控扩散模型.

GLIGEN: Open-Set Grounded Text-to-Image Generation

GLIGEN：开集接地文本到图像生成.

布局引导图像生成(Layout-to-Image Generation)

Layout-to-Image Generation.

Sigmoid Loss for Language Image Pre-Training

语言图像预训练的Sigmoid损失.

VL-BEiT: Generative Vision-Language Pretraining

VL-BEiT：生成式视觉-语言预训练.

Unified View of Grokking, Double Descent and Emergent Abilities: A Perspective from Circuits Competition

理解领悟能力、U型尺度定律和涌现能力的统一视角.