Research map / Image generation / Fast diffusion sampling
Reward-Directed Conditional Diffusion: Provable Distribution Estimation and Reward Improvement
Hui Yuan, Kaixuan Huang, Chengzhuo Ni, Minshuo Chen, Mengdi Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Increase the target reward value | RCGDM simulation · Synthetic data | average generated reward | Mixed |
| Increase the target reward value | Reward-directed Stable Diffusion v1.5 · Text-to-image generation, prompt "A nice photo" | predicted reward | Improved |
| Increase the target reward value | Reward-directed Stable Diffusion v1.5 · Text-to-image generation, prompt "A nice photo" | gap between predicted and ground-truth rewards | Hurt |
| Increase the target reward value | Reward-directed Stable Diffusion v1.5 · Text-to-image generation, varied prompts | image quality | Hurt |
Closest papers by meaning
- Adding Conditional Control to Diffusion Models with Reinforcement Learning (ICLR 2025 · similarity 0.90)
- Feedback Efficient Online Fine-Tuning of Diffusion Models (ICML 2024 · similarity 0.89)
- Zero-Shot Conditioning of Score-Based Diffusion Models by Neuro-Symbolic Constraints (AAAI 2025 · similarity 0.88)
- VGB for Masked Diffusion Model: Efficient Test-time Scaling for Reward Satisfaction and Sample Editing (NeurIPS 2026 · similarity 0.88)
- Bridging Model-Based Optimization and Generative Modeling via Conservative Fine-Tuning of Diffusion Models (NeurIPS 2024 · similarity 0.88)
- Directly Fine-Tuning Diffusion Models on Differentiable Rewards (ICLR 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
