arXiv AI By Yungang Yi, Weihua Li, Matthew Kuo, Catherine Shi, Quan Bai

Whole-Piece Training for Symbolic Music Language Models via Full-Horizon Compressed Recurrence

Read the original on arXiv AI →

The paper introduces Whole-Piece Training for Symbolic Music Language Models using Full-Horizon Compressed Recurrence (FHCR), which maintains the full temporal horizon of recurrent memory while compressing its key-value representation to fit GPU limits. An evaluation diagnostic, KV-Reset Context Utilization (KRCU), demonstrates that full-horizon models retain long-range context beyond local windows, whereas limiting recurrent memory weakens this dependence. FHCR thus preserves long-range context utilization while significantly reducing recurrent memory cost, enabling efficient whole-piece modeling.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI
Jul 16

From Prediction to Collaboration: Interactive Symbolic Music Analysis

arXiv:2607. 13587v1 Announce Type: cross Abstract: Automatic symbolic music analysis has made substantial progress, yet existing systems are typically designed for a single mode of use, such as full-score prediction, and therefore do not match the broader range of operations that arise in analysis workflows, including partial completion, local correction, and iterative refinement.

By Emmanouil Karystinaios, Johannes Hentschel, Markus Neuwirth, Gerhard Widmer
arXiv AI
Aug 19

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

The paper explains why GPT‑style language models fail to transfer directly to symbolic music. It argues that success in language comes from tokenization that compresses data by creating a coordinate system where recurring patterns become predictable. For music, the authors propose that tokenization must build a predictively effective, relationally lossless coordinate system—defining Fact–Token and Token–State boundaries—to enable compression without sacrificing contextual freedom. Controlled experiments confirm that proper coordinate construction improves predictive compressibility, whereas mere sequence compaction does not.

By Yi Wang
arXiv Machine Learning
Aug 31

How Far Should Tokenization Go? Predictive Effectiveness and Relational Losslessness

The paper proposes the Effectiveness–Losslessness Framework to guide tokenization in domains beyond language, using predictive codelength as a criterion. It introduces two boundaries: the Fact–Token Boundary, where observable structure should be encoded into tokens, and the Token–State Boundary, where context‑dependent relations should remain for model state rather than being pre‑tokenized. Experiments on symbolic music show that making musical time explicit and applying tonal‑frame canonicalization improve predictive performance, while fixed pitch coordinates and reversible BPE can increase predictive code length, indicating that carrier compaction alone does not guarantee better predictions.

By Yi Wang
arXiv AI
Sep 1

TEMPO: Temporally-grounded Multi-task Post-training for Large Audio-Language Models

TEMPO is a unified model that adds temporally‑grounded capabilities to large audio‑language models, enabling timestamping of events, speakers, and sounds in audio, speech, and music. It introduces a supervised fine‑tuning stage featuring atomic timestamp tokens, a time‑aware projector with sinusoidal encodings, and a distance‑aware Gaussian loss, trained via a synthetic‑to‑real curriculum. Additionally, TEMPO employs reinforcement learning (GRPO) as a refinement step, and achieves state‑of‑the‑art performance on a benchmark of 10K samples across five timestamping tasks, surpassing Audio Flamingo Next and Qwen3‑Omni.

By Apoorva Kulkarni, Kaousheik Jayakumar, Sreyan Ghosh, Utathya Aich, Ramani Duraiswami, Dinesh Manocha
arXiv Machine Learning
Aug 4

Structured Recurrent Mixers for Massively Parallelized Sequence Generation

arXiv:2605. 08696v4 Announce Type: replace-cross Abstract: Over the last two decades, language modeling has experienced a shift from the use of predominantly recurrent architectures that process tokens sequentially during training and inference to non-recurrent models that process sequence elements in parallel during training, which results in greater training efficiency and stability at the expense of lower inference throughput.

By Benjamin L. Badger