Jonas Henry Grebe
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
This paper introduces the Token by Token Backdoor Attack (ToBAC), demonstrating that unified autoregressive models (UAMs) are vulnerable to backdoor attacks where a single trigger can compromise multiple output modalities (text and image).
The paper introduces GEM, an effective concept erasure framework for Rectified Flow Transformers, by unifying trajectory-based unlearning with classic teacher-guided flow matching.
Papers
Geometric Erasure by Contrastive Velocity Matching in Rectified Flows
The paper introduces GEM, an effective concept erasure framework for Rectified Flow Transformers, by unifying trajectory-based unlearning with classic teacher-guided flow matching.