Research map / Image generation / Fast diffusion sampling
Multi-Subspace Multi-Modal Modeling for Diffusion Models: Estimation, Convergence and Mixture of Experts
Ruofeng Yang, Yongcan Li, Bo Jiang, Cheng Chen, Shuai Li
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 |
|---|---|---|---|
| Use latent MoG score network instead of latent Gaussian (MoLRG) score (ablation) | MoE-latent diffusion · ImageNet parachute class | CLIP score: 0.254 -> 0.293 | Improved |
| Use latent Unet instead of latent MoG NN (about 10x more parameters) (ablation) | MoE-latent diffusion · ImageNet parachute class | CLIP score: 0.293 -> 0.304 | No clear effect |
| Use expert-specific VAE instead of a unified VAE (ablation) | MoLR-MoG with small MoG experts · Qualitative generation | image clarity | Improved |
Closest papers by meaning
- A Mixture-Based Framework for Guiding Diffusion Models (ICML 2025 · similarity 0.87)
- Improving Probabilistic Diffusion Models With Optimal Diagonal Covariance Matching (ICLR 2025 · similarity 0.87)
- Adapting to Unknown Low-Dimensional Structures in Score-Based Diffusion Models (NeurIPS 2024 · similarity 0.87)
- Generalization Dynamics of Linear Diffusion Models (NeurIPS 2026 · similarity 0.87)
- Distillation of Discrete Diffusion through Dimensional Correlations (ICML 2025 · similarity 0.87)
- Diffusion Models With Learned Adaptive Noise (NeurIPS 2024 · similarity 0.87)
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.
