PPD fine-tunes a single diffusion model to follow per-user preferences by conditioning on VLM-extracted embeddings, reporting 76-81% win rates over Stable Cascade with four examples per user.
Training a helpful and harmless assistant with reinforcement learning from human feedback, 2022
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Personalized Preference Fine-tuning of Diffusion Models
PPD fine-tunes a single diffusion model to follow per-user preferences by conditioning on VLM-extracted embeddings, reporting 76-81% win rates over Stable Cascade with four examples per user.