Research map / Image generation / Fast diffusion sampling
Enhancing Accuracy in Generative Models via Knowledge Transfer
Xinyu Tian, Xiaotong Shen
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 source sample size for transfer diffusion | transfer diffusion model (synthetic conditional/unconditional) · Simulation, n_t=5000 | generation error (TV-norm / Wasserstein) | Improved |
| use small source sample size for transfer | transfer diffusion model · Simulation, small n_s | generation error | Hurt |
| pre-train on more MNIST before fine-tuning on USPS | transfer diffusion (conditional, all digits) · MNIST-USPS (conditional) | 1-Wasserstein distance | Improved |
| pre-train on more MNIST before fine-tuning on USPS digit 3 | transfer diffusion (unconditional) · MNIST-USPS (unconditional, digit 3) | 1-Wasserstein distance | Improved |
Closest papers by meaning
- Localizing Knowledge in Diffusion Transformers (NeurIPS 2025 · similarity 0.88)
- Why Knowledge Distillation Works in Generative Models: A Minimal Working Explanation (NeurIPS 2025 · similarity 0.88)
- Unveiling Concept Attribution in Diffusion Models (NeurIPS 2025 · similarity 0.86)
- MergeNet: Knowledge Migration Across Heterogeneous Models, Tasks, and Modalities (AAAI 2025 · similarity 0.86)
- Domain Guidance: A Simple Transfer Approach for a Pre-trained Diffusion Model (ICLR 2025 · similarity 0.86)
- Blink of an eye: a simple theory for feature localization in generative models (ICML 2025 · similarity 0.85)
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.
