27.08.2025
©pauchi-stock-adobe.com
Top 20 in OpenAI’s Red-Teaming Challenge
MCML Junior Member Shuo Chen and Team Recognized for Advancing AI Safety Research
We are proud to share that MCML Junior Member Shuo Chen and his team ranked among the Top 20 worldwide (out of 600+) in OpenAI’s Red-Teaming Challenge on Kaggle, a global competition that attracted over 5,900 participants.
Their work, titled “Bag of Tricks for Subverting Reasoning-Based Safety Guardrails,” investigates systemic weaknesses in reasoning-based safety mechanisms and provides insights into the development of more robust and template-independent alignment strategies.
Related
09.10.2025
Rethinking AI in Public Institutions - Balancing Prediction and Capacity
Unai Fischer Abaigar explores how AI can make public decisions fairer, smarter, and more effective.
08.10.2025
MCML-LAMARR Workshop at University of Bonn
MCML and Lamarr researchers met in Bonn to exchange ideas on NLP, LLM finetuning, and AI ethics.
08.10.2025
Three MCML Members Win Best Paper Award at AutoML 2025
Former MCML TBF Matthias Feurer and Director Bernd Bischl’s paper on overtuning won Best Paper at AutoML 2025, offering insights for robust HPO.
29.09.2025
Machine Learning for Climate Action - With Researcher Kerstin Forster
Kerstin Forster researches how AI can cut emissions, boost renewable energy, and drive corporate sustainability.
