Reward-Instruct: A Reward-Centric Approach to Fast Photo-Realistic Image Generation

Documenti analoghi

• TDM-R1: Reinforcing Few-Step Diffusion Models with Non-Differentiable Reward
  di: Luo, Yihong, et al.
  Pubblicazione: (2026)
• Noise Consistency Training: A Native Approach for One-Step Generator in Learning Additional Controls
  di: Luo, Yihong, et al.
  Pubblicazione: (2025)
• Diff-Instruct with Diffused Reward: Towards Principled One-step Generator RL
  di: Wu, Junyi, et al.
  Pubblicazione: (2026)
• Reinforcing Diffusion Models by Direct Group Preference Optimization
  di: Luo, Yihong, et al.
  Pubblicazione: (2025)
• Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion Models
  di: Luo, Weijian, et al.
  Pubblicazione: (2023)