To address these issues, we propose a novel framework Feature Representation Learning with adaptive Displacement Generation and Transformer fusion (FRL-DGT), in which a...
This paper introduces an end-to-end echo cancellation network with a streaming cross-attention alignment (SCA). Our proposed method can handle unaligned inputs without requiring...
We present RecD (Recommendation Deduplication), a suite of end-to-end infrastructure optimizations across the Deep Learning Recommendation Model (DLRM) training pipeline.
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 introduce Token Merging (ToMe), a simple method to increase the throughput of existing ViT models without needing to train. ToMe gradually combines similar tokens in a...
We present a hierarchical abstraction approach to uncover these underlying entities and achieve combinatorial generalization from unstructured visual inputs. By constructing a...
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...
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...
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.
