New Diffusion-APO method aligns video diffusion models with user intent

Researchers have introduced Diffusion-APO, a new method for aligning video diffusion models with human preferences. This approach addresses the gap between training noise distributions and real-world inference by synchronizing training noise with denoising paths. Diffusion-APO utilizes a flexible reinforcement learning framework that supports multi-stage alignment without needing scalar rewards, demonstrating superior visual quality and instruction following compared to existing methods. AI

影响 Improves alignment of video generation models, potentially leading to more controllable and higher-quality video synthesis.

排序理由 Publication of an academic paper on a new method for video diffusion models. [lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CV 阅读 →

• Diffusion-APO
• Direct Preference Optimization
• Group Relative Policy Optimization
• video diffusion models

• 论文
• 模型发布

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →