RepFusion: Leveraging Multimodal Priors for Denoising in Representation Space 文章

ArXiv CS.CV2026-06-15NEWSen作者: Xichen Pan, Aashu Singh, Satya Narayan Shukla, Xiangjun Fan, Shlok Kumar Mishra, Saining Xie
大语言模型
查看原文 →
关系图谱

RepFusion: Leveraging Multimodal Priors for Denoising in Representation Space · 相关技术

相关技术

Diffusion TransformerLarge language modelRepresentation AutoencodersMLP projectormultimodal LLMsText-to-imageLLM