CLAIRE

Three essential pilars of the lab

Efficient deep learning algorithms

• Efficient RL
• Sample efficient learning algorithms
• Model Recycling
• Efficient sequence models

Robust, safe and responsible algorithms

• RLHF/Alignment
• Uncertainty aware/Bayesian algorithms
• Offline RL
• Active learning/Human in the loop algorithms
• Better evaluations

Improving reasoning: Moving from system 1 to system 2 level thinking

• Improving reasoning
• Creativity
• Deliberation
• Causality
• Imagination
• Planning

Notes

• omg, this is amazing
• Note to self: Look at CLAIRE's research ⏫