Related papers: Large-Scale Training Data Attribution for Music Ge…

As large language models (LLMs) are trained on massive datasets, they have raised significant privacy and ethical concerns due to their potential to inadvertently retain sensitive information. Unlearning seeks to selectively remove specific…

Recent years have seen increasing interest in applying deep learning methods to the modeling of guitar amplifiers or effect pedals. Existing methods are mainly based on the supervised approach, requiring temporally-aligned data pairs of…

State-of-the-art generative models exhibit powerful image-generation capabilities, introducing various ethical and legal challenges to service providers hosting these models. Consequently, Content Removal Techniques (CRTs) have emerged as a…

Large monolithic generative models trained on massive amounts of data have become an increasingly dominant approach in AI research. In this paper, we argue that we should instead construct large generative systems by composing smaller…

Diffusion models have become increasingly popular for synthesizing high-quality samples based on training datasets. However, given the oftentimes enormous sizes of the training datasets, it is difficult to assess how training data impact…

As generative models become increasingly powerful and pervasive, the ability to unlearn specific data, whether due to privacy concerns, legal requirements, or the correction of harmful content, has become increasingly important. Unlike in…

"Machine unlearning" is a popular proposed solution for mitigating the existence of content in an AI model that is problematic for legal or moral reasons, including privacy, copyright, safety, and more. For example, unlearning is often…

Text-to-music (TTM) generation, which converts textual descriptions into audio, opens up innovative avenues for multimedia creation. Achieving high quality and diversity in this process demands extensive, high-quality data, which are often…

This paper is a survey and an analysis of different ways of using deep learning (deep artificial neural networks) to generate musical content. We propose a methodology based on five dimensions for our analysis: Objective - What musical…

Deep neural networks are often considered opaque systems, prompting the need for explainability methods to improve trust and accountability. Existing approaches typically attribute test-time predictions either to input features (e.g.,…

Deepfake detection has gained significant attention across audio, text, and image modalities, with high accuracy in distinguishing real from fake. However, identifying the exact source--such as the system or model behind a deepfake--remains…

Current training data attribution (TDA) methods treat the influence one sample has on another as static, but neural networks learn in distinct stages that exhibit changing patterns of influence. In this work, we introduce a framework for…

Training the deep neural networks that dominate NLP requires large datasets. These are often collected automatically or via crowdsourcing, and may exhibit systematic biases or annotation artifacts. By the latter we mean spurious…

Machine unlearning has emerged as a new paradigm to deliberately forget data samples from a given model in order to adhere to stringent regulations. However, existing machine unlearning methods have been primarily focused on classification…

Large language models trained on web-scale corpora can memorize undesirable data containing misinformation, copyrighted material, or private or sensitive information. Recently, several machine unlearning algorithms have been proposed to…

Large deep-learning models for music, including those focused on learning general-purpose music audio representations, are often assumed to require substantial training data to achieve high performance. If true, this would pose challenges…

Despite the strong capabilities of Large Language Models (LLMs) to acquire knowledge from their training corpora, the memorization of sensitive information in the corpora such as copyrighted, biased, and private content has led to ethical…

Text-to-music models have revolutionized the creative landscape, offering new possibilities for music creation. Yet their integration into musicians workflows remains underexplored. This paper presents a case study on how TTM models impact…

Large Language Models (LLMs) have demonstrated strong capabilities in memorizing vast amounts of knowledge across diverse domains. However, the ability to selectively forget specific knowledge is critical for ensuring the safety and…

Supervised deep learning methods for performing audio source separation can be very effective in domains where there is a large amount of training data. While some music domains have enough data suitable for training a separation system,…