D-Fusion: Direct Preference Optimization for Aligning Diffusion Models with Visually Consistent Samples

Documenti analoghi

• Asynchronous Denoising Diffusion Models for Aligning Text-to-Image Generation
  di: Hu, Zijing, et al.
  Pubblicazione: (2025)
• Towards Better Alignment: Training Diffusion Models with Reinforcement Learning Against Sparse Rewards
  di: Hu, Zijing, et al.
  Pubblicazione: (2025)
• Fusion in Your Way: Aligning Image Fusion with Heterogeneous Demands via Direct Preference Optimization
  di: Su, Weijian, et al.
  Pubblicazione: (2026)
• Calibrated Multi-Preference Optimization for Aligning Diffusion Models
  di: Lee, Kyungmin, et al.
  Pubblicazione: (2025)
• Diffusion-NPO: Negative Preference Optimization for Better Preference Aligned Generation of Diffusion Models
  di: Wang, Fu-Yun, et al.
  Pubblicazione: (2025)