Hierarchical Resolution Transformers: A Wavelet-Inspired Architecture for Multi-Scale Language Understanding

• URL: http://arxiv.org/abs/2509.20581v1
• Date: Wed, 24 Sep 2025 21:46:18 GMT
• Title: Hierarchical Resolution Transformers: A Wavelet-Inspired Architecture for Multi-Scale Language Understanding
• Authors: Ayan Sar, Sampurna Roy, Kanav Gupta, Anurag Kaushish, Tanupriya Choudhury, Abhijit Kumar,
• Abstract summary: Hierarchical Resolution Transformer (HRT) is a novel wavelet-inspired neural architecture that processes language simultaneously across multiple resolutions.<n>By employing exponential sequence reduction across scales, HRT achieves O(nlogn) complexity, offering significant efficiency improvements over standard transformers.
• Score: 1.0518862318418605
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Transformer architectures have achieved state-of-the-art performance across natural language tasks, yet they fundamentally misrepresent the hierarchical nature of human language by processing text as flat token sequences. This results in quadratic computational cost, weak computational cost, weak compositional generalization, and inadequate discourse-level modeling. We propose Hierarchical Resolution Transformer (HRT), a novel wavelet-inspired neural architecture that processes language simultaneously across multiple resolutions, from characters to discourse-level units. HRT constructs a multi-resolution attention, enabling bottom-up composition and top-down contextualization. By employing exponential sequence reduction across scales, HRT achieves O(nlogn) complexity, offering significant efficiency improvements over standard transformers. We evaluated HRT on a diverse suite of benchmarks, including GLUE, SuperGLUE, Long Range Arena, and WikiText-103, and results demonstrated that HRT outperforms standard transformer baselines by an average of +3.8% on GLUE, +4.5% on SuperGLUE, and +6.1% on Long Range Arena, while reducing memory usage by 42% and inference latency by 37% compared to BERT and GPT style models of similar parameter count. Ablation studies confirm the effectiveness of cross-resolution attention and scale-specialized modules, showing that each contributes independently to both efficiency and accuracy. Our findings establish HRT as the first architecture to align computational structure with the hierarchical organization of human language, demonstrating that multi-scale, wavelet-inspired processing yields both theoretical efficiency gains and practical improvements in language understanding.

Related papers

• Resonant Sparse Geometry Networks [0.0]
  We introduce Resonant Sparse Geometry Networks (RSGN), a brain-inspired architecture with self-organizing sparse hierarchical input-dependent connectivity.<n> RSGN embeds computational nodes in learned hyperbolic space where connection strength decays with geodesic distance, achieving dynamic sparsity that adapts to each input.
  arXiv  Detail & Related papers  (2026-01-26T01:45:51Z)
• Learnable Multi-Scale Wavelet Transformer: A Novel Alternative to Self-Attention [0.0]
  Learnable Multi-Scale Wavelet Transformer (LMWT) is a novel architecture that replaces the standard dot-product self-attention.<n>We present the detailed mathematical formulation of the learnable Haar wavelet module and its integration into the transformer framework.<n>Our results indicate that the LMWT achieves competitive performance while offering substantial computational advantages.
  arXiv  Detail & Related papers  (2025-04-08T22:16:54Z)
• WaveFormer: A 3D Transformer with Wavelet-Driven Feature Representation for Efficient Medical Image Segmentation [0.5312470855079862]
  We present WaveFormer, a novel 3D-transformer for medical images.<n>It is inspired by the top-down mechanism of the human visual recognition system.<n>It preserves both global context and high-frequency details while replacing heavy upsampling layers with efficient wavelet-based summarization and reconstruction.
  arXiv  Detail & Related papers  (2025-03-31T06:28:41Z)
• Advancements in Natural Language Processing: Exploring Transformer-Based Architectures for Text Understanding [10.484788943232674]
  This paper explores the advancements in transformer models, such as BERT and GPT, focusing on their superior performance in text understanding tasks.<n>The results demonstrate state-of-the-art performance on benchmarks like GLUE and SQuAD, with F1 scores exceeding 90%, though challenges such as high computational costs persist.
  arXiv  Detail & Related papers  (2025-03-26T04:45:33Z)
• On the locality bias and results in the Long Range Arena [49.15148871877941]
  The Long Range Arena benchmark was designed to evaluate the performance of Transformer improvements.<n>A new series of architectures such as State Space Models (SSMs) gained some traction, greatly outperforming Transformers in the LRA.<n>We show that while the LRA is a benchmark for long-range dependency modeling, in reality most of the performance comes from short-range dependencies.
  arXiv  Detail & Related papers  (2025-01-24T15:34:50Z)
• Enhanced Computationally Efficient Long LoRA Inspired Perceiver Architectures for Auto-Regressive Language Modeling [2.9228447484533695]
  The Transformer architecture has revolutionized the Natural Language Processing field and is the backbone of Large Language Models (LLMs)<n>One of the challenges in the Transformer architecture is the quadratic complexity of the attention mechanism that prohibits the efficient processing of long sequence lengths.<n>One of the important works in this respect is the Perceiver class of architectures that have demonstrated excellent performance while reducing the computation complexity.
  arXiv  Detail & Related papers  (2024-12-08T23:41:38Z)
• Predictor-Corrector Enhanced Transformers with Exponential Moving Average Coefficient Learning [73.73967342609603]
  We introduce a predictor-corrector learning framework to minimize truncation errors. We also propose an exponential moving average-based coefficient learning method to strengthen our higher-order predictor. Our model surpasses a robust 3.8B DeepNet by an average of 2.9 SacreBLEU, using only 1/3 parameters.
  arXiv  Detail & Related papers  (2024-11-05T12:26:25Z)
• FAMLP: A Frequency-Aware MLP-Like Architecture For Domain Generalization [73.41395947275473]
  We propose a novel frequency-aware architecture, in which the domain-specific features are filtered out in the transformed frequency domain. Experiments on three benchmarks demonstrate significant performance, outperforming the state-of-the-art methods by a margin of 3%, 4% and 9%, respectively.
  arXiv  Detail & Related papers  (2022-03-24T07:26:29Z)
• CSformer: Bridging Convolution and Transformer for Compressive Sensing [65.22377493627687]
  This paper proposes a hybrid framework that integrates the advantages of leveraging detailed spatial information from CNN and the global context provided by transformer for enhanced representation learning. The proposed approach is an end-to-end compressive image sensing method, composed of adaptive sampling and recovery. The experimental results demonstrate the effectiveness of the dedicated transformer-based architecture for compressive sensing.
  arXiv  Detail & Related papers  (2021-12-31T04:37:11Z)
• GroupBERT: Enhanced Transformer Architecture with Efficient Grouped Structures [57.46093180685175]
  We demonstrate a set of modifications to the structure of a Transformer layer, producing a more efficient architecture. We add a convolutional module to complement the self-attention module, decoupling the learning of local and global interactions. We apply the resulting architecture to language representation learning and demonstrate its superior performance compared to BERT models of different scales.
  arXiv  Detail & Related papers  (2021-06-10T15:41:53Z)
• Bayesian Transformer Language Models for Speech Recognition [59.235405107295655]
  State-of-the-art neural language models (LMs) represented by Transformers are highly complex. This paper proposes a full Bayesian learning framework for Transformer LM estimation.
  arXiv  Detail & Related papers  (2021-02-09T10:55:27Z)

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.