Tradi-fusion Refined: Evaluating and Fine-tuning the Riffusion Model for Irish Traditional Music

Unifying Score and Performance for Fine-Grained Music Understanding in Audio-Language Models

MuNo-SP (Music Notation unifying Score and Performance), a text-based representation that jointly encodes score content and performance information, is introduced and an automatic training-data generation pipeline is developed that uses aligned scores and performances to produce long-form auditory analyses and musicall...

Synthetic Text Generation for Mexican Magical Towns via Supervised Fine-Tuning with QLoRA

MIDI-REPA: Improving Text-to-Music Generation with Symbolic Representation Alignment

State-of-the-art text-to-music models increasingly rely on scaling model capacity, data, and compute, while still learning musical structure directly from dense audio. Yet melody, rhythm, harmony, and structure can be represented compactly in symbolic form. We introduce MIDI-REPA, a representation-alignment framework t...

AudioLens: Multi-Perspective Speech Clustering with Reasoning Audio-Language Models

This work introduces audio multi-perspective clustering, where a model directly partitions speech recordings according to a natural-language perspective while inferring both the number of clusters and their assignments.

Rubric-Based Optimization for Text-to-Music Generation

Together, these results suggest a practical division of labor: ALM rubrics are effective for broad perceptual qualities that are difficult to formalize, while specialized objective rewards remain preferable when reliable measurements are available.

Talk Less, Rank Better: A Decoupled Pipeline for Conversational Music Recommendation

This paper describes the solution submitted by team Hallucinated to the ACM RecSys Challenge 2026, based on the TalkPlayData conversational music recommendation dataset, which addresses the ranking task with a classic multi-stage pipeline that combines a diverse pool of candidate generators, Reciprocal Rank Fusion, and...