Konstantin Hess

Generative orthogonal learning unlocks rate double robustness and quasi-oracle efficiency for estimating distributional treatment effects under complex time-varying confounding.

LLM development is flying blind by ignoring causal inference, leaving models vulnerable to confounding and distribution shifts throughout pretraining, alignment, and evaluation.

Naive neural operator estimates of solution functional quantities can be significantly biased, but this paper provides a surprisingly simple debiasing technique to fix it.