Learn to build truthful, safe, and secure AI systems with theoretical guarantees.

Conformal Prediction Conformal Abstention Uncertainty Quantification Reinforcement Learning Online Learning Meta Learning

Learn to align AI agents with multiple objectives.

Constrained Learning Multi-objective Learning Learning for Planning Learning for SW Bug Discovery and Patching

Learn to build safe robots.

Safe Reinforcement Learning Sim-to-Real Adaptation

Learn to red-team AI systems.

Learning for LLM Jailbreaking Learning for Agentic AI Jailbreaking