paper-with-me

홈 › Papers

PoM: A Linear-Time Replacement for Attention with the Polynomial Mixer

2026-04-07 · David Picard, Nicolas Dufour, Lucas Degeorge, Arijit Ghosh, Davide Allegro, Tom Ravaud, Yohann Perron, Corentin Sautier, Zeynep Sonat Baltaci, Fei Meng, Syrine Kalleli, Marta López-Rauhut, Thibaut Loiseau, Ségolène Albouy, Raphael Baena, Elliot Vincent, Loic Landrieu arxiv

This paper introduces the Polynomial Mixer (PoM), a novel token mixing mechanism with linear complexity that serves as a drop-in replacement for self-attention. PoM aggregates input tokens into a compact representation through a learned polynomial function, from which each token retrieves contextual information. We prove that PoM satisfies the contextual mapping property, ensuring that transformers equipped with PoM remain universal sequence-to-sequence approximators. We replace standard self-attention with PoM across five diverse domains: text generation, handwritten text recognition, image generation, 3D modeling, and Earth observation. PoM matches the performance of attention-based models while drastically reducing computational cost when working with long sequences. The code is available at https://github.com/davidpicard/pom.

📄 PDF Abstract BibTeX arXiv:2604.06129

Code (0)

등록된 구현이 없습니다.

Tasks

Handwritten Text RecognitionImage GenerationText Generation

Similar Papers 제목 키워드 기반

PoM: Efficient Image and Video Generation with the Polynomial Mixer

2024-11-19 · David Picard, Nicolas Dufour

Diffusion models based on Multi-Head Attention (MHA) have become ubiquitous to generate high quality images and videos. However, encoding an image or a video as a sequence of patches results in costly attention patterns,…

Video Generation

Polynomial Mixing for Efficient Self-supervised Speech Encoders

2026-02-28 · Eva Feillet, Ryan Whetten, David Picard, Alexandre Allauzen arxiv

State-of-the-art speech-to-text models typically employ Transformer-based encoders that model token dependencies via self-attention mechanisms. However, the quadratic complexity of self-attention in both memory and compu…

Representation LearningSpeech Recognition

Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers

2024-07-13 · Sukjun Hwang, Aakash Lahoti, Tri Dao, Albert Gu

A wide array of sequence models are built on a framework modeled after Transformers, comprising alternating sequence mixer and channel mixer layers. This paper studies a unifying matrix mixer view of sequence mixers that…

MambaState Space Models

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

2024-07-16 · Pierre-David Letourneau, Manish Kumar Singh, Hsin-Pai Cheng, Shizhong Han 외

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 attenti…

2D Object DetectionComputational EfficiencyGPUimage-classification+4

ChebMixer: Efficient Graph Representation Learning with MLP Mixer

2024-03-25 · Xiaoyan Kui, Haonan Yan, Qinsong Li, Liming Chen 외

Graph neural networks have achieved remarkable success in learning graph representations, especially graph Transformer, which has recently shown superior performance on various graph mining tasks. However, graph Transfor…

Graph MiningGraph Representation LearningImage SegmentationMedical Image Segmentation+3