activity
20242026
collaborators
Showing cs.SDShow all

10 papers · 1 filter

cs.SD2026

MI-MIDI: Mechanistic Interpretability of Text-to-MIDI Generation Models via Probing, Lenses and Steering

Jakub Poćwiardowski, Mateusz Modrzejewski

Mechanistic interpretability of music generation has concentrated on audio models, leaving symbolic models largely unexplored. We analyze two public text-to-MIDI systems of contras…

cs.SD2026

The Perceived Fragility of Explanations in Audio Models: Manipulation of Attribution with Unchanged Predictions

Piotr Kitłowski, Dominik WiÄ cek, Mateusz Modrzejewski

This paper investigates the fragility of post-hoc explanation methods in audio deepfake detection. While previous work on explanation manipulation focused on images using standard…

cs.SD2026

TADA! Tuning Audio Diffusion Models through Activation Steering

Łukasz Staniszewski, Katarzyna Zaleska, Mateusz Modrzejewski +1

Audio diffusion models can synthesize high-fidelity music from text, yet achieving fine-grained control over specific musical attributes remains challenging, as their internal mech…

cs.SD2026

ConceptCaps: a Distilled Concept Dataset for Interpretability in Music Models

Bruno Sienkiewicz, Łukasz Neumann, Mateusz Modrzejewski

Concept-based interpretability methods like TCAV require clean, well-separated positive and negative examples for each concept. Existing music datasets lack this structure: tags ar…

cs.SD2025

M6(GPT)3: Generating Multitrack Modifiable Multi-Minute MIDI Music from Text using Genetic algorithms, Probabilistic methods and GPT Models in any Progression and Time Signature

Jakub Poćwiardowski, Mateusz Modrzejewski, Marek S. Tatara

This work introduces the M6(GPT)3 composer system, capable of generating complete, multi-minute musical compositions with complex structures in any time signature, in the MIDI doma…

cs.SD2025

Evaluating Fake Music Detection Performance Under Audio Augmentations

Tomasz Sroka, Tomasz Wężowicz, Dominik Sidorczuk +1

With the rapid advancement of generative audio models, distinguishing between human-composed and generated music is becoming increasingly challenging. As a response, models for det…