Pristine Models
Training on broad, unfiltered data enables high-quality image generation, but can also teach models concepts that should not be generated; restricting the training data ensures safety, but reduces quality because examples containing unsafe concepts also provide useful knowledge that is not itself unsafe. Existing approaches largely address this trade-off post hoc through concept unlearning, which can lead to catastrophic forgetting as the number of concepts to remove grows. We instead ask whether unsafe concept knowledge can be compartmentalized during pretraining so that access to it can be disabled at inference. We introduce Pristine Models, a novel text-to-image generation architecture...
| Authors | Anirudh Sundara Rajan, Krishna Kumar Singh, Richard Zhang et al. |
|---|---|
| Primary category | cs.CV |
| Published | 8 October 2026 |
| Last updated at source | 8 October 2026 |
Popularity, last 3 days
0 now (-13 since 2026-10-15). Counts as reported by the source, snapshotted daily by Silytics.
Recent changes
- 16 Oct 2026 Topics added cs.CV, cs.LG removed hf-daily-papers, text-to-image generation, attention mechanism, parameterized branches, concept unlearning, catastrophic forgetting, pristine models
- 16 Oct 2026 Description: Training on broad, unfiltered data enables high-quality image generation, but can also teach models concepts that should not be generated; restricting the training data ensures safety, but reduces quality because examples containing unsafe → Training on broad, unfiltered data enables high-quality image generation, but can also teach models concepts that should not be generated; restricting the training data ensures safety, but reduces quality because examples containing unsafe
Changes detected by Silytics between refreshes of the source.
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.