Confronting Reward Overoptimization for Diffusion Models: A Perspective of Inductive and Primacy Biases

Documenti analoghi

• Aligning Few-Step Diffusion Models with Dense Reward Difference Learning
  di: Zhang, Ziyi, et al.
  Pubblicazione: (2024)
• Merging Multi-Task Models via Weight-Ensembling Mixture of Experts
  di: Tang, Anke, et al.
  Pubblicazione: (2024)
• Object-Centric Temporal Consistency via Conditional Autoregressive Inductive Biases
  di: Meo, Cristian, et al.
  Pubblicazione: (2024)
• Tripod: Three Complementary Inductive Biases for Disentangled Representation Learning
  di: Hsu, Kyle, et al.
  Pubblicazione: (2024)
• Image Captions are Natural Prompts for Text-to-Image Models
  di: Lei, Shiye, et al.
  Pubblicazione: (2023)