Correction training reduces diffusion models' training-inference gap
A corrector refines intermediate predictions and can be distilled back into the base model.
42
- Mentions · 7d0
- Mentions · 30d1
- All mentions3
- First seenSep 26, 2026
- Last mentioned19d ago
Timeline
3 articles · newest firstDC-SAE: Deep Compression Semantic Autoencoder for Faster Diffusion Convergence
DC-SAE compresses images 32x and speeds diffusion training while beating DC-AE on ImageNet.
47
HamiFormer: Dual-Expert Diffusion Fields with Affine Symplectic Maps
HamiFormer cuts Hamiltonian phase-space error using dual-expert diffusion and affine symplectic maps.
14
Appears with
- DC-AEproduct · 1
- JiTai model · 1
- SiTai model · 1
- DC-SAEproduct · 1
- PhysiFormerai model · 1
- HamiFormerai model · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.