Related papers: Decoding Structure-Spectrum Relationships with Phy…
Texture is one of the most-studied visual attribute for image characterization since the 1960s. However, most hand-crafted descriptors are monochromatic, focusing on the gray scale images and discarding the color information. In this…
Deep Learning based techniques have gained significance over the past few years in the field of medicine. They are used in various applications such as classifying medical images, segmentation and identification. The existing architectures…
Adapting foundation models for specific purposes has become a standard approach to build machine learning systems for downstream applications. Yet, it is an open question which mechanisms take place during adaptation. Here we develop a new…
The current state-of-the-art image-sentence retrieval methods implicitly align the visual-textual fragments, like regions in images and words in sentences, and adopt attention modules to highlight the relevance of cross-modal semantic…
Sparse auto-encoders (SAEs) have become a prevalent tool for interpreting language models' inner workings. However, it is unknown how tightly SAE features correspond to computationally important directions in the model. This work…
Variational auto-encoders (VAEs) are a popular and powerful deep generative model. Previous works on VAEs have assumed a factorized likelihood model, whereby the output uncertainty of each pixel is assumed to be independent. This…
Motivation: Despite advances in the computational analysis of high-throughput molecular profiling assays (e.g. transcriptomics), a dichotomy exists between methods that are simple and interpretable, and ones that are complex but with lower…
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…
Discriminative features extracted from the sparse coding model have been shown to perform well for classification. Recent deep learning architectures have further improved reconstruction in inverse problems by considering new dense priors…
Detecting anomalies for multivariate time-series without manual supervision continues a challenging problem due to the increased scale of dimensions and complexity of today's IT monitoring systems. Recent progress of unsupervised…
Despite recent successes in synthesizing faces and bedrooms, existing generative models struggle to capture more complex image types, potentially due to the oversimplification of their latent space constructions. To tackle this issue,…
With the metaverse slowly becoming a reality and given the rapid pace of developments toward the creation of digital humans, the need for a principled style editing pipeline for human faces is bound to increase manifold. We cater to this…
A popular new method in mechanistic interpretability is to train high-dimensional sparse autoencoders (SAEs) on neuron activations and use SAE features as the atomic units of analysis. However, the body of evidence on whether SAE feature…
Explainable AI (XAI) has become essential in computer vision to make the decision-making processes of deep learning models transparent. However, current visual explanation (XAI) methods face a critical trade-off between the high fidelity of…
Machine learning can reveal new insights into X-ray spectroscopy of liquids when the local atomistic environment is presented to the model in a suitable way. Many unique structural descriptor families have been developed for this purpose.…
We introduce a novel masked graph autoencoder (MGAE) framework to perform effective learning on graph structure data. Taking insights from self-supervised learning, we randomly mask a large proportion of edges and try to reconstruct these…
Deep learning, particularly with the advancement of Large Language Models, has transformed biomolecular modeling, with protein language models such as ESM inspiring emerging RNA language models such as RiNALMo. Recent work has begun…
We present DC-AE 1.5, a new family of deep compression autoencoders for high-resolution diffusion models. Increasing the autoencoder's latent channel number is a highly effective approach for improving its reconstruction quality. However,…
This study explores the integration of multiple Explainable AI (XAI) techniques to enhance the interpretability of deep learning models for brain tumour detection. A custom Convolutional Neural Network (CNN) was developed and trained on the…
In Materials Science, material development involves evaluating and optimizing the internal structures of the material, generically referred to as microstructures. Microstructures structure is stochastic, analogously to image textures. A…