The Alignment Waltz: Jointly Training Agents to Collaborate for Safety Paper • 2510.08240 • Published Oct 9 • 41
IA2: Alignment with ICL Activations Improves Supervised Fine-Tuning Paper • 2509.22621 • Published Sep 26 • 8
Jointly Reinforcing Diversity and Quality in Language Model Generations Paper • 2509.02534 • Published Sep 2 • 24