Diff-Instruct with Diffused Reward: Towards Principled One-step Generator RL

Documenti analoghi

• Diff-Instruct++: Training One-step Text-to-image Generator Model to Align with Human Preferences
  di: Luo, Weijian
  Pubblicazione: (2024)
• David and Goliath: Small One-step Model Beats Large Diffusion with Score Post-training
  di: Luo, Weijian, et al.
  Pubblicazione: (2024)
• Uni-Instruct: One-step Diffusion Model through Unified Diffusion Divergence Instruction
  di: Wang, Yifei, et al.
  Pubblicazione: (2025)
• Taming the Entropy Cliff: Variable Codebook Size Quantization for Autoregressive Visual Generation
  di: Zheng, Bowen, et al.
  Pubblicazione: (2026)
• Multi-student Diffusion Distillation for Better One-step Generators
  di: Song, Yanke, et al.
  Pubblicazione: (2024)