Related papers: Discovering and Steering Interpretable Concepts in…

High-level musical qualities (such as emotion) are often abstract, subjective, and hard to quantify. Given these difficulties, it is not easy to learn good feature representations with supervised learning techniques, either because of the…

Sparse autoencoders (SAEs) are a useful tool for uncovering human-interpretable features in the activations of large language models (LLMs). While some expect SAEs to find the true underlying features used by a model, our research shows…

Latent representations are at the heart of the majority of modern generative models. In the audio domain they are typically produced by a neural-audio-codec autoencoder. In this work we introduce SAME (Semantically-Aligned Music…

Despite strong performance in audio perception tasks, large audio-language models (AudioLLMs) remain opaque to interpretation. A major factor behind this lack of interpretability is that individual neurons in these models frequently…

Current generative models are able to generate high-quality artefacts but have been shown to struggle with compositional reasoning, which can be defined as the ability to generate complex structures from simpler elements. In this paper, we…

Sparse dictionary learning (and, in particular, sparse autoencoders) attempts to learn a set of human-understandable concepts that can explain variation on an abstract space. A basic limitation of this approach is that it neither exploits…

Sparse autoencoders (SAEs) decompose large language model (LLM) activations into latent features that reveal mechanistic structure. Conventional SAEs train on broad data distributions, forcing a fixed latent budget to capture only…

Diffusion models, while powerful, can inadvertently generate harmful or undesirable content, raising significant ethical and safety concerns. Recent machine unlearning approaches offer potential solutions but often lack transparency, making…

Recent studies show the ability of unsupervised models to learn invertible audio representations using Auto-Encoders. They enable high-quality sound synthesis but a limited control since the latent spaces do not disentangle timbre…

Integrating physics models within machine learning models holds considerable promise toward learning robust models with improved interpretability and abilities to extrapolate. In this work, we focus on the integration of incomplete physics…

Abstract This project presents a system of neural networks to translate between images and melodies. Autoencoders compress the information in samples to abstract representation. A translation network learns a set of correspondences between…

Machine learning models that first learn a representation of a domain in terms of human-understandable concepts, then use it to make predictions, have been proposed to facilitate interpretation and interaction with models trained on…

Interpretable machine learning is rapidly becoming a crucial tool for scientific discovery. Among existing approaches, variational autoencoders (VAEs) have shown promise in extracting the hidden physical features of some input data, with no…

We propose to learn model invariances as a means of interpreting a model. This is motivated by a reverse engineering principle. If we understand a problem, we may introduce inductive biases in our model in the form of invariances.…

Text-to-image generative models have enabled high-resolution image synthesis across different domains, but require users to specify the content they wish to generate. In this paper, we consider the inverse problem -- given a collection of…

Interpretability benefits the theoretical understanding of representations. Existing word embeddings are generally dense representations. Hence, the meaning of latent dimensions is difficult to interpret. This makes word embeddings like a…

We develop the sparse VAE for unsupervised representation learning on high-dimensional data. The sparse VAE learns a set of latent factors (representations) which summarize the associations in the observed data features. The underlying…

Computational Music Generation is evolving towards non-conventional styles, demanding methods that enable precise and controllable blending of diverse music elements. In this work, we present a method for fine grained control using…

Understanding the multilingual mechanisms of large language models (LLMs) provides insight into how they process different languages, yet this remains challenging. Existing studies often focus on individual neurons, but their polysemantic…

The linear representation hypothesis states that neural network activations encode high-level concepts as linear mixtures. However, under superposition, this encoding is a projection from a higher-dimensional concept space into a…