Input reduction reduces the length of the input context before feeding to downstream LLMs.

Understanding how and why data distillation methods work is vital not only for improving these methods but also for revealing fundamental characteristics of "good" training data.

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

Image similarity measures are also crucial in the field of robust machine learning.