# Of All StrIPEs: Investigating Structure-informed Positional Encoding for Efficient Music Generation

arXiv: https://arxiv.org/abs/2504.05364 · HTML: https://mlsanity.com/paper/2504.05364/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 36 of its 48 references that are in the map.
- First posted on arXiv 7 Apr 2025.

## Builds on (most cited first, 30 of 36)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [Rethinking Attention with Performers](https://mlsanity.com/paper/2009.14794/) (2020)
- [Self-Attention with Relative Position Representations](https://mlsanity.com/paper/1803.02155/) (2018)
- [Gemma: Open Models Based on Gemini Research and Technology](https://mlsanity.com/paper/2403.08295/) (2024)
- [Efficient Transformers: A Survey](https://mlsanity.com/paper/2009.06732/) (2020)
- [Extending Context Window of Large Language Models via Positional Interpolation](https://mlsanity.com/paper/2306.15595/) (2023)
- [GPT-NeoX-20B: An Open-Source Autoregressive Language Model](https://mlsanity.com/paper/2204.06745/) (2022)
- [Efficient Attention: Attention with Linear Complexities](https://mlsanity.com/paper/1812.01243/) (2018)
- [Transformer Dissection: A Unified Understanding of Transformer's Attention via the Lens of Kernel](https://mlsanity.com/paper/1908.11775/) (2019)
- [Rethinking Positional Encoding in Language Pre-training](https://mlsanity.com/paper/2006.15595/) (2020)
- [Round and Round We Go! What makes Rotary Positional Encodings useful?](https://mlsanity.com/paper/2410.06205/) (2024)
- [POP909: A Pop-song Dataset for Music Arrangement Generation](https://mlsanity.com/paper/2008.07142/) (2020)
- [PopMAG: Pop Music Accompaniment Generation](https://mlsanity.com/paper/2008.07703/) (2020)
- [The Jazz Transformer on the Front Line: Exploring the Shortcomings of AI-composed Music through Quantitative Measures](https://mlsanity.com/paper/2008.01307/) (2020)
- [MuseMorphose: Full-Song and Fine-Grained Piano Music Style Transfer with One Transformer VAE](https://mlsanity.com/paper/2105.04090/) (2021)
- [A Simple and Effective Positional Encoding for Transformers](https://mlsanity.com/paper/2104.08698/) (2021)
- [Relative Positional Encoding for Transformers with Linear Complexity](https://mlsanity.com/paper/2105.08399/) (2021)
- [Symphony Generation with Permutation Invariant Language Model](https://mlsanity.com/paper/2205.05448/) (2022)
- [The What, Why, and How of Context Length Extension Techniques in Large Language Models -- A Detailed Survey](https://mlsanity.com/paper/2401.07872/) (2024)
- [Resonance RoPE: Improving Context Length Generalization of Large Language Models](https://mlsanity.com/paper/2403.00071/) (2024)
- [How Compositional Generalization and Creativity Improve as Diffusion Models are Trained](https://mlsanity.com/paper/2502.12089/) (2025)
- [Automatic Analysis and Influence of Hierarchical Structure on Melody, Rhythm and Harmony in Popular Music](https://mlsanity.com/paper/2010.07518/) (2020)
- [A Domain-Knowledge-Inspired Music Embedding Space and a Novel Attention Mechanism for Symbolic Music Modeling](https://mlsanity.com/paper/2212.00973/) (2022)
- [Linearized Relative Positional Encoding](https://mlsanity.com/paper/2307.09270/) (2023)
- [The Power of Context: How Multimodality Improves Image Super-Resolution](https://mlsanity.com/paper/2503.14503/) (2025)

## Abstract (arXiv)

While music remains a challenging domain for generative models like Transformers, a two-pronged approach has recently proved successful: inserting musically-relevant structural information into the positional encoding (PE) module and using kernel approximation techniques based on Random Fourier Features (RFF) to lower the computational cost from quadratic to linear. Yet, it is not clear how such RFF-based efficient PEs compare with those based on rotation matrices, such as Rotary Positional Encoding (RoPE). In this paper, we present a unified framework based on kernel methods to analyze both families of efficient PEs. We use this framework to develop a novel PE method called RoPEPool, capable of extracting causal relationships from temporal sequences. Using RFF-based PEs and rotation-based PEs, we demonstrate how seemingly disparate PEs can be jointly studied by considering the content-context interactions they induce. For empirical validation, we use a symbolic music generation task, namely, melody harmonization. We show that RoPEPool, combined with highly-informative structural priors, outperforms all methods.