Related papers: Dataset vs Reality: Understanding Model Performanc…

Biological science produces large amounts of data in a variety of formats, which necessitates the use of computational tools to process, integrate, analyse, and glean insights from the data. Researchers who use computational biology tools…

Recently, several data-sets associating data to text have been created to train data-to-text surface realisers. It is unclear however to what extent the surface realisation task exercised by these data-sets is linguistically challenging. Do…

The Information Bottleneck principle offers both a mechanism to explain how deep neural networks train and generalize, as well as a regularized objective with which to train models. However, multiple competing objectives are proposed in the…

Large language models (LLMs) have enabled a range of applications in zero-shot and few-shot learning settings, including the generation of synthetic datasets for training and testing. However, to reliably use these synthetic datasets, it is…

Data science is an integrated workflow of technical, analytical, communication, and ethical skills, but current AI benchmarks focus mostly on constituent parts. We test whether AI models can generate end-to-end data science projects. To do…

Problems at the intersection of vision and language are of significant importance both as challenging research questions and for the rich set of applications they enable. However, inherent structure in our world and bias in our language…

Humans often have to read multiple documents to address their information needs. However, most existing reading comprehension (RC) tasks only focus on questions for which the contexts provide all the information required to answer them,…

Dataset Condensation is a newly emerging technique aiming at learning a tiny dataset that captures the rich information encoded in the original dataset. As the size of datasets contemporary machine learning models rely on becomes…

Rising concern for the societal implications of artificial intelligence systems has inspired demands for greater transparency and accountability. However the datasets which empower machine learning are often used, shared and re-used with…

Recent progress in generative AI, primarily through diffusion models, presents significant challenges for real-world deepfake detection. The increased realism in image details, diverse content, and widespread accessibility to the general…

This study contributes to the literature by considering the difference in vocabulary used to express document content and information needs. Users are integrated into all research phases in order to provide them with relevant information…

Deep learning methods such as multitask neural networks have recently been applied to ligand-based virtual screening and other drug discovery applications. Using a set of industrial ADMET datasets, we compare neural networks to standard…

Deep reading models for question-answering have demonstrated promising performance over the last couple of years. However current systems tend to learn how to cleverly extract a span of the source document, based on its similarity with the…

When selecting data for training large-scale models, standard practice is to filter for examples that match human notions of data quality. Such filtering yields qualitatively clean datapoints that intuitively should improve model behavior.…

Generating a description of an image is called image captioning. Image captioning requires to recognize the important objects, their attributes and their relationships in an image. It also needs to generate syntactically and semantically…

Deep learning, computational neuroscience, and cognitive science have overlapping goals related to understanding intelligence such that perception and behaviour can be simulated in computational systems. In neuroimaging, machine learning…

Generating images conditioned on multiple visual references is critical for real-world applications such as multi-subject composition, narrative illustration, and novel view synthesis, yet current models suffer from severe performance…

Robots should be able to learn complex behaviors from human demonstrations. In practice, these human-provided datasets are inevitably imbalanced: i.e., the human demonstrates some subtasks more frequently than others. State-of-the-art…

Question answering is an important task for autonomous agents and virtual assistants alike and was shown to support the disabled in efficiently navigating an overwhelming environment. Many existing methods focus on observation-based…

Visual question answering (or VQA) is a new and exciting problem that combines natural language processing and computer vision techniques. We present a survey of the various datasets and models that have been used to tackle this task. The…