A single steering vector extracted from the middle text layer of a multimodal diffusion transformer can erase concepts like nudity, celebrities, and art styles at inference time, with no training.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Semantic Steering for Controllable Generation: Tuning-Free Concept Erasure in Multimodal Diffusion Transformers
A single steering vector extracted from the middle text layer of a multimodal diffusion transformer can erase concepts like nudity, celebrities, and art styles at inference time, with no training.