Related papers: Vector Quantized Latent Concepts: A Scalable Alter…

Recent advances in multimodal large language models (LLMs) have shown extreme effectiveness in visual question answering (VQA). However, the design nature of these end-to-end models prevents them from being interpretable to humans,…

Machine unlearning in Vision-Language Models (VLMs) is typically performed at the image or instance level, making it difficult to precisely remove target knowledge without affecting unrelated semantics. This issue is especially pronounced…

Concept Bottleneck Models (CBMs) aim for ante-hoc interpretability by learning a bottleneck layer that predicts interpretable concepts before the decision. State-of-the-art approaches typically select which concepts to learn via human…

With the representation learning capability of the deep learning models, deep embedded multi-view clustering (MVC) achieves impressive performance in many scenarios and has become increasingly popular in recent years. Although great…

We consider methods for learning vector representations of SQL queries to support generalized workload analytics tasks, including workload summarization for index selection and predicting queries that will trigger memory errors. We consider…

Quantum Language Models (QLMs) in which words are modelled as quantum superposition of sememes have demonstrated a high level of model transparency and good post-hoc interpretability. Nevertheless, in the current literature word sequences…

Latent representations are the essence of deep generative models and determine their usefulness and power. For latent representations to be useful as generative concept representations, their latent space must support latent space…

A variational framework for structural topology optimization is developed, integrating quantum and classical latent encoding strategies within a coordinate-based neural decoding architecture. In this approach, a low-dimensional latent…

Variational autoencoders employ an amortized inference model to approximate the posterior of latent variables. However, such amortized variational inference faces two challenges: (1) the limited posterior expressiveness of fully-factorized…

We propose a deep structure encoder using the recently introduced Volterra Neural Networks (VNNs) to seek a latent representation of multi-modal data whose features are jointly captured by a union of subspaces. The so-called…

Quantum Machine Learning (QML) offers tremendous potential but is currently limited by the availability of qubits. We introduce an innovative approach that utilizes pre-trained neural networks to enhance Variational Quantum Circuits (VQC).…

Deep learning has brought significant improvements to the field of cross-modal representation learning. For tasks such as text-to-speech (TTS), voice conversion (VC), and automatic speech recognition (ASR), a cross-modal fine-grained…

Deep latent variable models (DLVMs) are designed to learn meaningful representations in an unsupervised manner, such that the hidden explanatory factors are interpretable by independent latent variables (aka disentanglement). The…

Variational Autoencoders (VAEs) have been shown to be remarkably effective in recovering model latent spaces for several computer vision tasks. However, currently trained VAEs, for a number of reasons, seem to fall short in learning…

Variational Autoencoder is a scalable method for learning latent variable models of complex data. It employs a clear objective that can be easily optimized. However, it does not explicitly measure the quality of learned representations. We…

Retrieval augmentation is a powerful but expensive method to make language models more knowledgeable about the world. Memory-based methods like LUMEN pre-compute token representations for retrieved passages to drastically speed up…

Understanding how generative models represent and transform data is a foundational problem in deep learning interpretability. While mechanistic interpretability of discriminative architectures has yielded substantial insights, relatively…

Identifying customer segments in retail banking portfolios with different risk profiles can improve the accuracy of credit scoring. The Variational Autoencoder (VAE) has shown promising results in different research domains, and it has been…

Autoencoders and their variations provide unsupervised models for learning low-dimensional representations for downstream tasks. Without proper regularization, autoencoder models are susceptible to the overfitting problem and the so-called…

Multiview clustering (MVC) segregates data samples into meaningful clusters by synthesizing information across multiple views. Moreover, deep learning-based methods have demonstrated their strong feature learning capabilities in MVC…