Meta Research

We propose data-source-aware disentangled learning with adversarial examples to reduce the mismatch between the original and adversarial data.

This work introduces the expected utility of the best option (qEUBO) as a novel acquisition function for PBO.

This work shows how innovative data from social media can provide useful insights on conflictinduced migration flows.

We address this general problem in the context of image data (photos) by proposing which photos to archive to meet an online storage budget. The decision is based on factors such...

We propose XAIR, a design framework that addresses when, what, and how to provide explanations of AI output in AR. The framework was based on a multi-disciplinary literature...

From time to time, Meta invites academics to propose research in specific areas that align with our mission of building community and bringing the world closer together.

This work designs a method to estimate the item-level effects from the causal perspective. We resort to causal graphs to characterize the average treatment effect of...

The cumulative approach is currently unconventional, yet offers many favorable statistical properties, guaranteed via mathematical theory backed by rigorous proofs and...