LLMs has become a critical research problem.

Unsupervised Environment Design (UED) formalizes the problem of autocur-ricula through interactive training between a teacher agent and a student agent. The teacher generates new training environments with high learning potential, curating an adaptive curriculum that strengthens the student's ability to handle unseen scenarios. Existing UED methods mainly rely on regret, a metric that measures the difference between the agent's optimal and actual performance, to

Off-policy estimation: Oftentimes, one needs to estimate the linear functional based on observational data collected from a behavior policy.

However, practical model deployment often operates in the gap between these two limit cases, as real-world applications demand adaptation to specific subdomains, tasks or concepts -- spread over the entire, varying life cycle of a model.

Hopfield Boosting, a boosting approach, which leverages modern Hopfield energy to sharpen the decision boundary between the in-distribution and OOD data.