AI.info

Lillian J. Ratliff

Explore Lillian J. Ratliff on AI.info.

• Efficient Uncoupled Learning Dynamics with $\tilde{O}\!\left(T^{-1/4}\right)$ Last-Iterate Convergence in Bilinear Saddle-Point Problems over Convex Sets under Bandit Feedback
• dUltra: Ultra-Fast Diffusion Language Models via Reinforcement Learning