← Search

Pierre-David Letourneau

2 accepted papers

2025

PADRe: A Unifying Polynomial Attention Drop-in Replacement for Efficient Vision Transformer

ICLR 2025poster

We present Polynomial Attention Drop-in Replacement (PADRe), a novel and unifying framework designed to replace the conventional self-attention mechanism in transformer models. Notably, several recent alternative attention mechanisms, including Hyena, Mamba, SimA, Conv2Former, and Castling-ViT, can…

Cited by 2SourcePDFScholar
2023

Composite Slice Transformer: An Efficient Transformer with Composition of Multi-Scale Multi-Range Attentions

ICLR 2023poster

Since the introduction of Transformers, researchers have tackled the notoriously expensive quadratic complexity problem. While significant computational efficiency improvements have been achieved, they come at the cost of reduced accuracy trade-offs. In this paper, we propose Composite Slice Transf…

Cited by 2SourcePDFScholar