paper-with-me

Papers

F-StrIPE: Fast Structure-Informed Positional Encoding for Symbolic Music Generation

2025-02-14 · Manvi Agarwal, Changhong Wang, Gael Richard

While music remains a challenging domain for generative models like Transformers, recent progress has been made by exploiting suitable musically-informed priors. One technique to leverage information about musical structure in Transformers is inserting such knowledge into the positional encoding (PE) module. However, Transformers carry a quadratic cost in sequence length. In this paper, we propose F-StrIPE, a structure-informed PE scheme that works in linear complexity. Using existing kernel approximation techniques based on random features, we show that F-StrIPE is a generalization of Stochastic Positional Encoding (SPE). We illustrate the empirical merits of F-StrIPE using melody harmonization for symbolic music.

📄 PDF Abstract BibTeX arXiv:2502.10491

Code (0)

등록된 구현이 없습니다.

Tasks

Music Generation

Similar Papers 제목 키워드 기반

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

2025-04-07 · Manvi Agarwal, Changhong Wang, Gael Richard

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 (P…

AllMusic GenerationTemporal Sequences

CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows

2021-07-01 · CVPR 2022 1 · Xiaoyi Dong, Jianmin Bao, Dongdong Chen, Weiming Zhang 외

We present CSWin Transformer, an efficient and effective Transformer-based backbone for general-purpose vision tasks. A challenging issue in Transformer design is that global self-attention is very expensive to compute w…

Image ClassificationSemantic Segmentation

Structure-informed Positional Encoding for Music Generation

2024-02-20 · Manvi Agarwal, Changhong Wang, Gaël Richard

Music generated by deep learning methods often suffers from a lack of coherence and long-term organization. Yet, multi-scale hierarchical structure is a distinctive feature of music signals. To leverage this information,…

Music Generation

Transformers with Physics-Informed Encodings and Simulation-Based Inference for Robust Detection of Eccentric Binary Black Holes in Pulsar Timing Array Data

2026-07-04 · Subhajit Dandapat, Alvin J. K. Chua arxiv

Pulsar timing arrays (PTAs) provide a unique window into nanohertz gravitational waves (GWs), but extracting astrophysical parameters from noisy, long-baseline timing residuals remains computationally challenging with tr…

Transformed Low-Rank Model for Line Pattern Noise Removal

2017-10-01 · ICCV 2017 10 · Yi Chang, Luxin Yan, Sheng Zhong

This paper addresses the problem of line pattern noise removal from a single image, such as rain streak, hyperspectral stripe and so on. Most of the previous methods model the line pattern noise in original image domain,…