activity
20172021
most citedTransformers are RNNs: Fast Autoregressive Transformers with Linear Attention

310 citations · 388 across the 5 of their papers we have counts for

collaborators

8 papers

cs.LG2025

Soup-of-Experts: Pretraining Specialist Models via Parameters Averaging

Pierre Ablin, Angelos Katharopoulos, Skyler Seto +1

Machine learning models are routinely trained on a mixture of different data domains. Different domain weights yield very different downstream performances. We propose the Soup-of-…

cs.CV20211 cited

Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks

Despoina Paschalidou, Angelos Katharopoulos, Andreas Geiger +1

Impressive progress in 3D shape extraction led to representations that can capture object geometries with high fidelity. In parallel, primitive-based methods seek to represent obje…

cs.LG20207 cited

Fast Transformers with Clustered Attention

Apoorv Vyas, Angelos Katharopoulos, François Fleuret

Transformers have been proven a successful model for a variety of tasks in sequence modeling. However, computing the attention matrix, which is their key component, has quadratic c…

cs.LG2020310 cited

Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention

Angelos Katharopoulos, Apoorv Vyas, Nikolaos Pappas +1

Transformers achieve remarkable performance in several tasks but due to their quadratic complexity, with respect to the input's length, they are prohibitively slow for very long se…

cs.CV201922 cited

Processing Megapixel Images with Deep Attention-Sampling Models

Angelos Katharopoulos, François Fleuret

Existing deep architectures cannot operate on very large signals such as megapixel images due to computational and memory constraints. To tackle this limitation, we propose a fully…

cs.LG2018

Not All Samples Are Created Equal: Deep Learning with Importance Sampling

Angelos Katharopoulos, François Fleuret

Deep neural network training spends most of the computation on examples that are properly handled, and could be ignored. We propose to mitigate this phenomenon with a principled im…