Dynamic Short Convolutions Improve Transformers

• URL: http://arxiv.org/abs/2606.03825v1
• Date: Tue, 02 Jun 2026 16:07:55 GMT
• Title: Dynamic Short Convolutions Improve Transformers
• Abstract summary: This paper introduces dynamic short convolutions as an additional neural network primitive for improving Transformers.<n>Experiments show that applying dynamic short convolutions to key, query, and value representations improves performance.
• Score: 44.7573199674059
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Transformers have become the dominant architecture for large language models, largely due to the scalability and flexibility of attention, feed-forward layers, residual connections, and normalization. This paper introduces dynamic short convolutions as an additional neural network primitive for improving Transformers. Unlike static short convolutions, dynamic convolutions use input-dependent filters, which preserves the locality bias of convolution while increasing expressivity. Motivating experiments show that applying dynamic short convolutions to key, query, and value representations improves performance on challenging associative recall tasks compared with static convolutional variants. Across language-modeling experiments ranging from 150M to 2B parameters, dynamic convolutions consistently outperform standard Transformers and Transformers augmented with static short convolutions. Fitting scaling laws indicates a 1.33$\times$ compute advantage over compute-matched Transformers when dynamic convolutions are applied to the key, query, and value vectors, and a 1.60$\times$ advantage when adding dynamic convolutions after every linear layer. Dynamic convolutions also offer improvements on linear RNNs (Mamba-2/Gated DeltaNet) and mixture-of-experts architectures. We make these gains practical with custom Triton kernels that enable efficient training with a manageable end-to-end slowdown. These results suggest that dynamic short convolutions are a scalable, hardware-efficient, and expressive primitive for advancing Transformer-based language models.

Related papers

• Converting Transformers into DGNNs Form [3.7468283401703797]
  We introduce a synthetic unitary digraph convolution based on the digraph Fourier transform.<n>The resulting model, which we term Converter, effectively converts a Transformer into a Directed Graph Neural Network form.<n>We have tested Converter on Long-Range Arena benchmark, long document classification, and DNA sequence-based taxonomy classification.
  arXiv  Detail & Related papers  (2025-02-01T22:44:46Z)
• Mamba: Linear-Time Sequence Modeling with Selective State Spaces [31.985243136674146]
  Foundation models are almost universally based on the Transformer architecture and its core attention module. We identify that a key weakness of such models is their inability to perform content-based reasoning. We integrate these selective SSMs into a simplified end-to-end neural network architecture without attention or even blocks (Mamba) As a general sequence model backbone, Mamba achieves state-of-the-art performance across several modalities such as language, audio, and genomics.
  arXiv  Detail & Related papers  (2023-12-01T18:01:34Z)
• RWKV: Reinventing RNNs for the Transformer Era [54.716108899349614]
  We propose a novel model architecture that combines the efficient parallelizable training of transformers with the efficient inference of RNNs. We scale our models as large as 14 billion parameters, by far the largest dense RNN ever trained, and find RWKV performs on par with similarly sized Transformers.
  arXiv  Detail & Related papers  (2023-05-22T13:57:41Z)
• SD-Conv: Towards the Parameter-Efficiency of Dynamic Convolution [16.56592303409295]
  Dynamic convolution achieves better performance for efficient CNNs at the cost of negligible FLOPs increase. We propose a new framework, textbfSparse Dynamic Convolution (textscSD-Conv), to naturally integrate these two paths.
  arXiv  Detail & Related papers  (2022-04-05T14:03:54Z)
• nnFormer: Interleaved Transformer for Volumetric Segmentation [50.10441845967601]
  We introduce nnFormer, a powerful segmentation model with an interleaved architecture based on empirical combination of self-attention and convolution. nnFormer achieves tremendous improvements over previous transformer-based methods on two commonly used datasets Synapse and ACDC.
  arXiv  Detail & Related papers  (2021-09-07T17:08:24Z)
• Stable, Fast and Accurate: Kernelized Attention with Relative Positional Encoding [63.539333383965726]
  We propose a novel way to accelerate attention calculation for Transformers with relative positional encoding (RPE) Based upon the observation that relative positional encoding forms a Toeplitz matrix, we mathematically show that kernelized attention with RPE can be calculated efficiently using Fast Fourier Transform (FFT)
  arXiv  Detail & Related papers  (2021-06-23T17:51:26Z)
• Finetuning Pretrained Transformers into RNNs [81.72974646901136]
  Transformers have outperformed recurrent neural networks (RNNs) in natural language generation. A linear-complexity recurrent variant has proven well suited for autoregressive generation. This work aims to convert a pretrained transformer into its efficient recurrent counterpart.
  arXiv  Detail & Related papers  (2021-03-24T10:50:43Z)
• Revisiting Dynamic Convolution via Matrix Decomposition [81.89967403872147]
  We propose dynamic channel fusion to replace dynamic attention over channel groups. Our method is easier to train and requires significantly fewer parameters without sacrificing accuracy.
  arXiv  Detail & Related papers  (2021-03-15T23:03:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.