Research map / Image generation / Fast diffusion sampling
Mirror Diffusion Models for Constrained and Watermarked Generation
Guan-Horng Liu, Tianrong Chen, Evangelos Theodorou, Molei Tao
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 |
|---|---|---|---|
| fewer watermark constraints m (ablation) | MDM-proj · AFHQv2 | FID and watermark precision | Improved |
| looser constraint ranges (c_i, b_i) (ablation) | MDM-proj · AFHQv2 | FID and watermark precision | Improved |
| learn dual-space diffusion (MDM-dual) instead of projecting a pretrained model (MDM-proj) | MDM · FFHQ and AFHQv2 | FID | Hurt |
| replace Reflected Diffusion with Mirror Diffusion Model | constrained diffusion · ball and simplex sets, d from 2 to 20 | Sliced Wasserstein | Improved |
| replace DDPM with MDM | unconstrained diffusion · ball and simplex sets | constraint violation | Improved |
Closest papers by meaning
- Neural Approximate Mirror Maps for Constrained Diffusion Models (ICLR 2025 · similarity 0.91)
- Constrained Diffusion with Trust Sampling (NeurIPS 2024 · similarity 0.88)
- Constrained Diffusion Models via Dual Training (NeurIPS 2024 · similarity 0.88)
- RAPID: Retrieval Augmented Training of Differentially Private Diffusion Models (ICLR 2025 · similarity 0.87)
- Composition and Alignment of Diffusion Models using Constrained Learning (NeurIPS 2025 · similarity 0.86)
- Simplified and Generalized Masked Diffusion for Discrete Data (NeurIPS 2024 · similarity 0.86)
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.
