Related papers: Dimension Reduction for Efficient Dense Retrieval …

Steered-Mixtures-of-Experts (SMoE) models provide sparse, edge-aware representations, applicable to many use-cases in image processing. This includes denoising, super-resolution and compression of 2D- and higher dimensional pixel data.…

Word embedding, a high-dimensional (HD) numerical representation of words generated by machine learning models, has been used for different natural language processing tasks, e.g., translation between two languages. Recently, there has been…

Dual-encoder-based dense retrieval models have become the standard in IR. They employ large Transformer-based language models, which are notoriously inefficient in terms of resources and latency. We propose Fast-Forward indexes -- vector…

Unsupervised learning can leverage large-scale data sources without the need for annotations. In this context, deep learning-based auto encoders have shown great potential in detecting anomalies in medical images. However, state-of-the-art…

This paper presents a novel convolutional neural network (CNN) based image compression framework via scalable auto-encoder (SAE). Specifically, our SAE based deep image codec consists of hierarchical coding layers, each of which is an…

The cosmic microwave background power spectra are a primary window into the early universe. However, achieving interpretable, likelihood-compatible compression and fast inference under weak model assumptions remains challenging. We propose…

Dense retrieval, which describes the use of contextualised language models such as BERT to identify documents from a collection by leveraging approximate nearest neighbour (ANN) techniques, has been increasing in popularity. Two families of…

While the current state-of-the-art dense retrieval models exhibit strong out-of-domain generalization, they might fail to capture nuanced domain-specific knowledge. In principle, fine-tuning these models for specialized retrieval tasks…

Accelerating deep neural networks (DNNs) has been attracting increasing attention as it can benefit a wide range of applications, e.g., enabling mobile systems with limited computing resources to own powerful visual recognition ability. A…

Deep neural network autoencoders are routinely used computationally for model reduction. They allow recognizing the intrinsic dimension of data that lie in a $k$-dimensional subset $K$ of an input Euclidean space $\mathbb{R}^n$. The…

Conversational dense retrieval has shown to be effective in conversational search. However, a major limitation of conversational dense retrieval is their lack of interpretability, hindering intuitive understanding of model behaviors for…

Online continual learning aims to learn from a non-IID stream of data from a number of different tasks, where the learner is only allowed to consider data once. Methods are typically allowed to use a limited buffer to store some of the…

The central question in representation learning is what constitutes a good or meaningful representation. In this work we argue that if we consider data with inherent cluster structures, where clusters can be characterized through different…

Learning a robust video Variational Autoencoder (VAE) is essential for reducing video redundancy and facilitating efficient video generation. Directly applying image VAEs to individual frames in isolation can result in temporal…

Autoencoder (AE) is the key to the success of latent diffusion models for image and video generation, reducing the denoising resolution and improving efficiency. However, the power of AE has long been underexplored in terms of network…

Traditional language models, adept at next-token prediction in text sequences, often struggle with transduction tasks between distinct symbolic systems, particularly when parallel data is scarce. Addressing this issue, we introduce…

For many Automatic Speech Recognition (ASR) tasks audio features as spectrograms show better results than Mel-frequency Cepstral Coefficients (MFCC), but in practice they are hard to use due to a complex dimensionality of a feature space.…

Linear autoencoder models learn an item-to-item weight matrix via convex optimization with L2 regularization and zero-diagonal constraints. Despite their simplicity, they have shown remarkable performance compared to sophisticated…

Data encoding is a common and central operation in most data analysis tasks. The performance of other models downstream in the computational process highly depends on the quality of data encoding. One of the most powerful ways to encode…

Generating textual descriptions for images has been an attractive problem for the computer vision and natural language processing researchers in recent years. Dozens of models based on deep learning have been proposed to solve this problem.…