13.06.2025
Volker Tresp and His Team Win ReGenAI @CVPR 2025 Best Paper Award
Honored for Work on New Jailbreak Vulnerability in T2I Diffusion Models
MCML Junior Members Tong Liu, Gengyuan Zhang, Shuo Chen, and MCML PI Volker Tresp and their co-authors have received the Best Paper Award at the Second Workshop on Responsible Generative AI (ReGenAI) Workshop at CVPR 2025 for their paper “Multimodal Pragmatic Jailbreak on Text-to-image Models”.
The authors show that text-to-image models can be easily exploited to produce unsafe content through cross‑modal interactions between safe text and images, a vulnerability that current safety filters fail to address effectively.
Congratulations from us!
Check out the full paper:
Multimodal Pragmatic Jailbreak on Text-to-image Models.
ACL 2025 - 63rd Annual Meeting of the Association for Computational Linguistics. Vienna, Austria, Jul 27-Aug 01, 2025. DOI GitHub
Related
01.05.2026
MCML at AISTATS 2026
MCML researchers are represented with 8 papers at AISTATS 2026 (7 Main, and 1 Workshop).
28.04.2026
Björn Ommer: How AI Can Transform Society if We Use It Responsibly
MCML PI Björn Ommer explains the philosophy behind Stable Diffusion and why his team focuses on efficiency.
23.04.2026
When Vision AI Hallucinates Details
Why do vision-language models invent details? Our PI Zeynep Akata and her team present a fix for AI hallucinations at CVPR 2026.
