Tobias Braun
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Publications per year
226
Top categories
AI×2ML×1Crypto×1
Frequent co-authors
Research Timeline
2026
Token by Token, Compromised: Backdoor Vulnerabilities in Unified Autoregressive Models
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).
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.
Highlighted terms show continued research focus across papers
Papers
cs.LGcs.AIRecentMay 29, 2026
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.
View →
cs.CRcs.AIRecentMay 19, 2026