We reduce the quantization loss of a given image representation by making imperceptible changes to the image before its release. The loss is back-propagated through the deep...
We reduce the quantization loss of a given image representation by making imperceptible changes to the image before its release. The loss is back-propagated through the deep...
While existing benchmarks surface examples that are challenging for models, they do not explain why such mistakes arise. To address this need, we introduce ImageNet-X–a set of...
In this paper, we present a framework for exploration in large-scale recommender systems to address these challenges. It consists of three parts, first the user-creator...
In this paper we present Que2Engage, a search EBR system designed to bridge the gap between retrieval and ranking for better end-to-end optimization. Que2Engage takes a...
In this paper we present HierCat, the query categorization system at Facebook Marketplace. HierCat addresses these challenges by leveraging multi-task pre-training of...
In this work, we introduce CAM2, a conformity-aware multi-task ranking model to serve relevant items to users on one of the largest industrial recommendation platforms.
In this paper, we propose a novel method which introduces diversity by modeling the impact of low diversity on user’s engagement on individual items, thus being able to account...
We introduce Continual Subspace of Policies (CSP), a new approach that incrementally builds a subspace of policies for training a reinforcement learning agent on a sequence of...
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...
In this work, as the first attempt, we initiate to repair DNNs by jointly optimizing the architecture and weights at a higher (i.e., block) level. We first perform empirical...