Related papers: The IBEX Knowledge-Base: Achieving more together w…
Information Bottleneck (IB) based multi-view learning provides an information theoretic principle for seeking shared information contained in heterogeneous data descriptions. However, its great success is generally attributed to estimate…
Diffusion models have found phenomenal success as expressive priors for solving inverse problems, but their extension beyond natural images to more structured scientific domains remains limited. Motivated by applications in materials…
Effectiveness and interpretability are two essential properties for trustworthy AI systems. Most recent studies in visual reasoning are dedicated to improving the accuracy of predicted answers, and less attention is paid to explaining the…
We introduce a multiple testing procedure (TreeBH) which addresses the challenge of controlling error rates at multiple levels of resolution. Conceptually, we frame this problem as the selection of hypotheses which are organized…
Information extraction (IE) in scientific literature has facilitated many down-stream tasks. OpenIE, which does not require any relation schema but identifies a relational phrase to describe the relationship between a subject and an object,…
Latest research proposes to replace existing index structures with learned models. However, current learned indexes tend to have many hyperparameters, often do not provide any error guarantees, and are expensive to build. We introduce…
In this work, we propose an interactive system to design diverse high-quality garment images from fashion sketches and the texture information. The major challenge behind this system is to generate high-quality and detailed texture…
Information bottleneck is an information-theoretic principle of representation learning that aims to learn a maximally compressed representation that preserves as much information about labels as possible. Under this principle, two…
The web does not only enable new forms of science, it also creates new possibilities to study science and new digital scholarship. This paper brings together multiple perspectives: from individual researchers seeking the best options to…
Probing (or diagnostic classification) has become a popular strategy for investigating whether a given set of intermediate features is present in the representations of neural models. Probing studies may have misleading results, but various…
Due to the highly inhomogeneous distributions of refractive indexes, light propagation in complex media such as biological tissue experiences multiple light scattering events. The suppression and control of multiple light scattering events…
Bayesian probabilistic numerical methods are a set of tools providing posterior distributions on the output of numerical methods. The use of these methods is usually motivated by the fact that they can represent our uncertainty due to…
We propose a new paradigm for universal information extraction (IE) that is compatible with any schema format and applicable to a list of IE tasks, such as named entity recognition, relation extraction, event extraction and sentiment…
In this work, a multiple-expert binarization framework for multispectral images is proposed. The framework is based on a constrained subspace selection limited to the spectral bands combined with state-of-the-art gray-level binarization…
The authors discuss information-based complexity theory, which is a model of finite-precision computations with real numbers, and its applications to numerical analysis.
We present a baseline science operations plan for the Black Hole Explorer (BHEX), a space mission concept aiming to confirm the existence of the predicted sharp ``photon ring" resulting from strongly lensed photon trajectories around black…
The Belief Rule Base (BRB) system that adopts a hybrid approach integrating the precision of expert systems with the adaptability of data-driven models. Characterized by its use of if-then rules to accommodate various types of uncertainty…
Our growing ability to tailor healthcare to the needs of individuals has the potential to transform clinical treatment. However, the measurement of multiple biomarkers to inform clinical decisions requires rapid, effective, and affordable…
Mixup data augmentation approaches have been applied for various tasks of deep learning to improve the generalization ability of deep neural networks. Some existing approaches CutMix, SaliencyMix, etc. randomly replace a patch in one image…
We present a prototype of a software tool for exploration of multiple combinatorial optimisation problems in large real-world and synthetic complex networks. Our tool, called GraphCombEx (an acronym of Graph Combinatorial Explorer),…