Hugging Face Trending Papers June 2, 2026

Tonal parsimony in chord-sequence analysis: combining modulation cost and tonal vocabulary

Read the original on Hugging Face Trending Papers →

We study the assignment of local tonalities to chord sequences, a task useful for harmonic analysis, composition, and jazz-oriented improvisation. Standard dynamic-programming approaches minimize modulations but can introduce unnecessarily many tonal centers.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv AI

Jun 3

Tonal parsimony in chord-sequence analysis: combining modulation cost and tonal vocabulary

arXiv:2606. 03459v1 Announce Type: cross Abstract: We study the assignment of local tonalities to chord sequences, a task useful for harmonic analysis, composition, and jazz-oriented improvisation.

By Fran\c{c}ois Pachet

arXiv Machine Learning

Jun 8

How Far Can Chord-Symbol Time-Series Adaptation Carry Genre Identity? Capabilities and Boundaries in Multi-Genre Chord-Symbol Modeling

arXiv:2606. 07334v1 Announce Type: cross Abstract: Harmony is a compact symbolic layer where mathematical pitch relations, acoustic consonance, and musical convention meet.

By Jinju Lee

llms fine-tuning benchmarks

arXiv AI

22h ago

Why GPT-Style Models Do Not Directly Transfer to Symbolic Music: Compression in the Wrong Coordinate System

arXiv:2608. 18025v1 Announce Type: cross Abstract: GPT-style models achieve strong performance by representing language with finite vocabularies of reusable discrete tokens.

By Yi Wang

llms nlp

arXiv Machine Learning

Jun 16

Empirical Study of Pop and Jazz Mix Ratios for Genre-Adaptive Chord Generation

arXiv:2605. 04998v2 Announce Type: replace-cross Abstract: This revision updates a pop-to-jazz chord-generation rehearsal study.

By Jinju Lee

arXiv AI

Jun 12

CMI-RewardBench: Evaluating Music Reward Models with Compositional Multimodal Instruction

arXiv:2603. 00610v3 Announce Type: replace-cross Abstract: While music generation models have evolved to handle complex multimodal inputs mixing text, lyrics, and reference audio, evaluation mechanisms have lagged behind.

By Yinghao Ma, Haiwen Xia, Hewei Gao, Weixiong Chen, Yuxin Ye, Yuchen Yang, Sungkyun Chang, Mingshuo Ding, Yizhi Li, Ruibin Yuan, Simon Dixon, Emmanouil Benetos

reinforcement-learning multimodal benchmarks safety

arXiv AI

Jun 6

Exploring LLMs for South Asian Music Understanding and Generation

arXiv:2606. 05522v1 Announce Type: cross Abstract: Recent advancements in Large Language Models (LLMs) have shown promising results in music understanding and generation tasks.

By Faria Binte Kader, Mohtasim Hadi Rafi, Shah Wasif Sajjad, Santu Karmaker

llms benchmarks

Related stories

Tonal parsimony in chord-sequence analysis: combining modulation cost and tonal vocabulary

How Far Can Chord-Symbol Time-Series Adaptation Carry Genre Identity? Capabilities and Boundaries in Multi-Genre Chord-Symbol Modeling

Why GPT-Style Models Do Not Directly Transfer to Symbolic Music: Compression in the Wrong Coordinate System

Empirical Study of Pop and Jazz Mix Ratios for Genre-Adaptive Chord Generation

CMI-RewardBench: Evaluating Music Reward Models with Compositional Multimodal Instruction

Exploring LLMs for South Asian Music Understanding and Generation