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
20.07.2026
How Fair Does AI Seem in Job Interviews?
A new study by Enkelejda Kasneci examines how applicants perceive fairness in AI-driven job interviews.
20.07.2026
TUM Develops Intelligent 3D Twins of Crime Scenes
AI-powered 3D twins enable investigators to analyze virtual crime scenes through interactive object recognition and scene understanding.
09.07.2026
MCML Junior Member Bolei Ma Earns Best Paper and SAC Highlight Awards at ACL 2026
Bolei Ma receives a Best Paper Award and an SAC Highlight Award at ACL 2026 for outstanding contributions to NLP research.
