Related papers: The effect of multiple internal representations on…

Automatic art analysis aims to classify and retrieve artistic representations from a collection of images by using computer vision and machine learning techniques. In this work, we propose to enhance visual representations from neural…

In this paper, we focus on learning structure-aware document representations from data without recourse to a discourse parser or additional annotations. Drawing inspiration from recent efforts to empower neural networks with a structural…

Understanding the importance of the inputs on the output is useful across many tasks. This work provides an information-theoretic framework to analyse the influence of inputs for text classification tasks. Natural language processing (NLP)…

Pretrained contextualized text encoders are now a staple of the NLP community. We present a survey on language representation learning with the aim of consolidating a series of shared lessons learned across a variety of recent efforts.…

For any video codecs, the coding efficiency highly relies on whether the current signal to be encoded can find the relevant contexts from the previous reconstructed signals. Traditional codec has verified more contexts bring substantial…

We investigated the human capacity to acquire multiple visuomotor mappings for de novo skills. Using a grid navigation paradigm, we tested whether contextual cues implemented as different "grid worlds", allow participants to learn two…

Predictive coding has emerged as a prominent model of how the brain learns through predictions, anticipating the importance accorded to predictive learning in recent AI architectures such as transformers. Here we propose a new framework for…

Speech perception involves storing and integrating sequentially presented items. Recent work in cognitive neuroscience has identified temporal and contextual characteristics in humans' neural encoding of speech that may facilitate this…

Humans possess a remarkable ability to acquire knowledge efficiently and apply it across diverse modalities through a coherent and shared understanding of the world. Inspired by this cognitive capability, we introduce a concept-centric…

Students of visualization come to formal education with an abundance of personal experience. However, one's exposure to graphics through media and education may not be sufficiently diverse to appreciate the nuance and complexity required to…

This paper proposes a learning model, based on rank-fusion graphs, for general applicability in multimodal prediction tasks, such as multimodal regression and image classification. Rank-fusion graphs encode information from multiple…

In-context learning is a surprising and important phenomenon that emerged when modern language models were scaled to billions of learned parameters. Without modifying a large language model's weights, it can be tuned to perform various…

Representation learning is the foundation of natural language processing (NLP). This work presents new methods to employ visual information as assistant signals to general NLP tasks. For each sentence, we first retrieve a flexible number of…

With the success of contextualized language models, much research explores what these models really learn and in which cases they still fail. Most of this work focuses on specific NLP tasks and on the learning outcome. Little research has…

High\-cardinality categorical variables pose significant challenges in machine learning, particularly in terms of computational efficiency and model interpretability. Traditional one\-hot encoding often results in high\-dimensional sparse…

This practical experience report explores Neural Machine Translation (NMT) models' capability to generate offensive security code from natural language (NL) descriptions, highlighting the significance of contextual understanding and its…

Open-ended learning frames intelligence as emerging from continual interaction with an ever-expanding space of environments. While recent advances have utilized foundation models to programmatically generate diverse environments, these…

Temporal abstraction allows reinforcement learning agents to represent knowledge and develop strategies over different temporal scales. The option-critic framework has been demonstrated to learn temporally extended actions, represented as…

Transformer-based language models exhibit In-Context Learning (ICL), where predictions are made adaptively based on context. While prior work links induction heads to ICL through a sudden jump in accuracy, this can only account for ICL when…

Estimating causal effects from observational data (at either an individual -- or a population -- level) is critical for making many types of decisions. One approach to address this task is to learn decomposed representations of the…