ConceptACP erases diffusion concepts with sparse autoencoders
On SDXL-Turbo one-step generation, forgetting success rises 36.34 points over the best baseline.
44
AI model
SDXL-Turbo
- Mentions · 7d0
- Mentions · 30d1
- All mentions1
- First seenOct 23, 2026
- Last mentioned8d ago
Timeline
1 articles · newest firstAppears with
- Stable Diffusionai 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.