arXiv Machine Learning June 8, 2026 By Zixi Li, Youzhen Li

Entropy as a Structural Prior: How a Log-Barrier on DiT Belief Space Drives Musical Diversity and Development

Read the original on arXiv Machine Learning →

arXiv:2606. 07207v1 Announce Type: cross Abstract: Confidence-based loss weighting is usually avoided in generative models because it accelerates errors when the model is confidently wrong, but this intuition breaks down in supervised diffusion training.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jun 24

SLEEPING-DISCO 9M: A large-scale pre-training dataset for generative music modeling

arXiv:2506. 14293v4 Announce Type: replace-cross Abstract: We present Sleeping-DISCO 9M, a large-scale pre-training dataset for music and song.

By Tawsif Ahmed, Andrej Radonjic, Gollam Rabby

arXiv Machine Learning

Jul 17

MIDI-RAE-JEPA: Hierarchical Representation Learning and Generation for Symbolic Music

arXiv:2607. 14537v1 Announce Type: cross Abstract: Rich internal representations of musical structure are essential for music understanding tasks such as machine-assisted music co-writing, yet self-supervised approaches for symbolic music representation remain underexplored, particularly those that encode the hierarchical multiscale nature of musical structures.

By Scott H. Hawley

llms rag diffusion

arXiv AI

Jun 18

Continuous Audio Thinking for Large Audio Language Models

arXiv:2606. 18273v1 Announce Type: cross Abstract: Large audio language models (LALMs) have shown impressive capabilities on diverse audio understanding tasks, ranging from speech transcription to music analysis.

By Gyojin Han, Dong-Jae Lee, Changho Choi, Jongsuk Kim, Junmo Kim

llms efficiency benchmarks

arXiv AI

Jul 8

Perceptually Aligning Representations of Music via Noise-Augmented Autoencoders

arXiv:2511. 05350v3 Announce Type: replace-cross Abstract: We argue that training autoencoders to reconstruct inputs from noised versions of their encodings, when combined with perceptually motivated losses, yields encodings that are structured according to a perceptual hierarchy.

By Mathias Rose Bjare, Giorgia Cantisani, Marco Pasini, Stefan Lattner, Gerhard Widmer

diffusion

arXiv AI

Jun 30

LeVo 2: Stable and Melodious Song Generation via Hierarchical Representation Modeling and Progressive Post-Training

arXiv:2606. 30642v1 Announce Type: cross Abstract: Full-length song generation must preserve coherence and musicality, render detailed vocal and accompaniment acoustics, and follow lyrics and prompts.

By Shun Lei, Huaicheng Zhang, Dapeng Wu, Yaoxun Xu, Lishi Zuo, Wei Tan, Hangting Chen, Guangzheng Li, Jianwei Yu, Zhiyong Wu, Dong Yu

llms diffusion reinforcement-learning fine-tuning safety

arXiv Machine Learning

1d ago

What Makes a Good Layer? Assessing the Layer-Wise Intrinsic Properties of Music Foundation Models

arXiv:2608. 14819v1 Announce Type: cross Abstract: Music foundation models are commonly used as frozen audio feature extractors, yet selecting which layer to extract from remains largely heuristic.

By Angelos-Nikolaos Kanatas, Yuexuan Kong, Pablo Alonso-Jim\'enez, Xavier Serra, Dmitry Bogdanov

Related stories

SLEEPING-DISCO 9M: A large-scale pre-training dataset for generative music modeling

MIDI-RAE-JEPA: Hierarchical Representation Learning and Generation for Symbolic Music

Continuous Audio Thinking for Large Audio Language Models

Perceptually Aligning Representations of Music via Noise-Augmented Autoencoders

LeVo 2: Stable and Melodious Song Generation via Hierarchical Representation Modeling and Progressive Post-Training

What Makes a Good Layer? Assessing the Layer-Wise Intrinsic Properties of Music Foundation Models