AI.info

Andreas Krause

Explore Andreas Krause on AI.info.

• RewardUQ: A Unified Framework for Uncertainty-Aware Reward Models
• Flow Density Control: Generative Optimization Beyond Entropy-Regularized Fine-Tuning
• Sample-efficient and Scalable Exploration in Continuous-Time RL
• Optimistic Task Inference for Behavior Foundation Models
• Thompson Sampling via Fine-Tuning of LLMs