Related papers: Superior Molecular Representations from Intermedia…

Autoencoders learn data representations (codes) in such a way that the input is reproduced at the output of the network. However, it is not always clear what kind of properties of the input data need to be captured by the codes. Kernel…

Image compression and reconstruction are crucial for various digital applications. While contemporary neural compression methods achieve impressive compression rates, the adoption of such technology has been largely hindered by the…

We present an architecture that is effective for continual learning in an especially demanding setting, where task boundaries do not exist or are unknown, and where classes have to be learned online (with each example presented only once).…

Representation learning is important for solving sequence-to-sequence problems in natural language processing. Representation learning transforms raw data into vector-form representations while preserving their features. However, data with…

Representation learning has been widely studied in the context of meta-learning, enabling rapid learning of new tasks through shared representations. Recent works such as MAML have explored using fine-tuning-based metrics, which measure the…

Graphics rendering applications increasingly leverage neural networks in tasks such as denoising, supersampling, and frame extrapolation to improve image quality while maintaining frame rates. The temporal coherence inherent in these tasks…

Inpainting-based image compression is a promising alternative to classical transform-based lossy codecs. Typically it stores a carefully selected subset of all pixel locations and their colour values. In the decoding phase the missing…

The traditional SegNet architecture commonly encounters significant information loss during the sampling process, which detrimentally affects its accuracy in image semantic segmentation tasks. To counter this challenge, we introduce an…

Interest in quantum machine learning is increasingly growing due to its potential to offer more efficient solutions for problems that are difficult to tackle with classical methods. In this context, the research work presented here focuses…

In this paper, we build autoencoder based pipelines for extreme end-to-end image compression based on Ball\'e's approach, which is the state-of-the-art open source implementation in image compression using deep learning. We deepened the…

BERTopic is a topic modeling algorithm that leverages transformer-based embeddings to create dense clusters, enabling the estimation of topic structures and the extraction of valuable insights from a corpus of documents. This approach…

Recent breakthroughs in deep learning often rely on representation learning and knowledge transfer. In recent years, unsupervised and self-supervised techniques for learning speech representation were developed to foster automatic speech…

Code datasets, often collected from diverse and uncontrolled sources such as GitHub, potentially suffer from quality issues, thereby affecting the performance and training efficiency of Large Language Models (LLMs) optimized for code…

Molecular communication (MC) provides a foundational framework for information transmission in the Internet of Bio-Nano Things (IoBNT), where efficiency and reliability are crucial. However, the inherent limitations of molecular channels,…

Objective functions that optimize deep neural networks play a vital role in creating an enhanced feature representation of the input data. Although cross-entropy-based loss formulations have been extensively used in a variety of supervised…

While learning based compression techniques for images have outperformed traditional methods, they have not been widely adopted in machine learning pipelines. This is largely due to lack of standardization and lack of retention of salient…

Learning vectorized embeddings is fundamental to many recommender systems for user-item matching. To enable efficient online inference, representation binarization, which embeds latent features into compact binary sequences, has recently…

Modern large language models (LLMs) excel at tasks that require storing and retrieving knowledge, such as factual recall and question answering. Transformers are central to this capability because they can encode information during training…

Video frame interpolation is an increasingly important research task with several key industrial applications in the video coding, broadcast and production sectors. Recently, transformers have been introduced to the field resulting in…

Neural models have become ubiquitous in automatic speech recognition systems. While neural networks are typically used as acoustic models in more complex systems, recent studies have explored end-to-end speech recognition systems based on…