Related papers: Quantifying Dimensional Independence in Speech: An…
Distributed linguistic representations are powerful tools for modelling the uncertainty and complexity of preference information in linguistic decision making. To provide a comprehensive perspective on the development of distributed…
The GPT-4 technical report suggests that downstream performance can be predicted from pre-training signals, but offers little methodological detail on how to quantify this. This work address this gap by modeling knowledge retention, the…
Encoding models provide a powerful framework for linking continuous stimulus features to neural activity; however, traditional voxelwise approaches are limited by measurement noise, inter-subject variability, and redundancy arising from…
Self-supervised representations excel at many vision and speech tasks, but their potential for audio-visual deepfake detection remains underexplored. Unlike prior work that uses these features in isolation or buried within complex…
Disentangled representations, where the higher level data generative factors are reflected in disjoint latent dimensions, offer several benefits such as ease of deriving invariant representations, transferability to other tasks,…
Representation learning constitutes a pivotal cornerstone in contemporary deep learning paradigms, offering a conduit to elucidate distinctive features within the latent space and interpret the deep models. Nevertheless, the inherent…
The idea behind the \emph{unsupervised} learning of \emph{disentangled} representations is that real-world data is generated by a few explanatory factors of variation which can be recovered by unsupervised learning algorithms. In this…
Recent years have seen growing interest in learning disentangled representations, in which distinct features, such as size or shape, are represented by distinct neurons. Quantifying the extent to which a given representation is disentangled…
Dimensional analysis is one of the most fundamental tools for understanding physical systems. However, the construction of dimensionless variables, as guided by the Buckingham-$\pi$ theorem, is not uniquely determined. Here, we introduce…
Disentangled representation learning plays a pivotal role in making representations controllable, interpretable and transferable. Despite its significance in the domain, the quest for reliable and consistent quantitative disentanglement…
How people narrate their experiences offers a window into how the mind organizes them. Computational approaches to therapeutic writing have evolved from lexical counting to neural methods, yet remain fragmented: dictionary tools miss…
In a hybrid speech model, both voiced and unvoiced components can coexist in a segment. Often, the voiced speech is regarded as the deterministic component, and the unvoiced speech and additive noise are the stochastic components.…
Digital journaling creates an authenticity gap: users consciously translate raw emotions into text, often sanitizing narratives even in private writing. We formalize this as Cross-Modal Affective Dissonance Detection (CADD), a directional…
Self-supervised representation learning approaches have grown in popularity due to the ability to train models on large amounts of unlabeled data and have demonstrated success in diverse fields such as natural language processing, computer…
Recent advances in large language models (LLMs) have revolutionized natural language processing, yet evaluating their intrinsic linguistic understanding remains challenging. Moving beyond specialized evaluation tasks, we propose an…
Speech information can be roughly decomposed into four components: language content, timbre, pitch, and rhythm. Obtaining disentangled representations of these components is useful in many speech analysis and generation applications.…
Generalization capabilities of learning-based medical image segmentation across domains are currently limited by the performance degradation caused by the domain shift, particularly for ultrasound (US) imaging. The quality of US images…
Hidden hearing loss, or cochlear neural degeneration (CND), disrupts suprathreshold auditory coding without affecting clinical thresholds, making it difficult to diagnose. We present an information-theoretic framework to evaluate speech…
Intrinsic dimension (ID) is an important tool in modern LLM analysis, informing studies of training dynamics, scaling behavior, and dataset structure, yet its textual determinants remain underexplored. We provide the first comprehensive…
Large scale neural models show impressive performance across a wide array of linguistic tasks. Despite this they remain, largely, black-boxes - inducing vector-representations of their input that prove difficult to interpret. This limits…