Pith. sign in

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 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

Personalized Preference Fine-tuning of Diffusion Models

cs.LG · 2025-01-11 · conditional · novelty 5.0

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.

citing papers explorer

Showing 1 of 1 citing paper.

  • Personalized Preference Fine-tuning of Diffusion Models cs.LG · 2025-01-11 · conditional · none · ref 1

    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.