GEM bridges trajectory-based unlearning and teacher-guided erasure to create a geometric guidance objective for targeted concept suppression in Rectified Flow models.
T2i-riskyprompt: A benchmark for safety evaluation, attack, and defense on text-to-image model
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Geometric Erasure by Contrastive Velocity Matching in Rectified Flows
GEM bridges trajectory-based unlearning and teacher-guided erasure to create a geometric guidance objective for targeted concept suppression in Rectified Flow models.