Related papers: Towards Equitable, Diverse, and Inclusive Science …
Distance-based methods involve the computation of distance values between features and are a well-established paradigm in machine learning. In anomaly detection, anomalies are identified by their large distance from normal data points.…
Innovative ideas are often situated where disciplines meet, and socio-economic problems generally require contributions from several disciplines. Ways to stimulate interdisciplinary research collaborations are therefore an increasing point…
We present EDDY (Exact-marginal Diversification via Divergence-free dYnamics), a guidance mechanism for diffusion and flow matching models that promotes diversity among samples generated while maintaining quality. EDDY exploits symmetries…
Scientific discovery is increasingly dependent on a scientist's ability to acquire, curate, integrate, analyze, and share large and diverse collections of data. While the details vary from domain to domain, these data often consist of…
Link prediction algorithms can help to understand the structure and dynamics of scientific collaborations and the evolution of Science. However, available algorithms based on similarity between nodes of collaboration networks are bounded by…
Data from many real-world applications can be naturally represented by multi-view networks where the different views encode different types of relationships (e.g., friendship, shared interests in music, etc.) between real-world individuals…
Our experience of the world is multisensory, spanning a synthesis of language, sight, sound, touch, taste, and smell. Yet, artificial intelligence has primarily advanced in digital modalities like text, vision, and audio. This paper…
Astronomy has been an inherently visual area of science for millenia, yet a majority of its significant discoveries take place in wavelengths beyond human vision. There are many people, including those with low or no vision, who cannot…
Non-terrestrial networks (NTNs) will complement terrestrial networks (TNs) in 5G and beyond, which can be attributed to recent deployment and standardization activities. Maximizing the efficiency of NTN communications is critical to unlock…
The advances in remote sensing technologies have boosted applications for Earth observation. These technologies provide multiple observations or views with different levels of information. They might contain static or temporary views with…
Distributed Mean Estimation (DME) is a central building block in federated learning, where clients send local gradients to a parameter server for averaging and updating the model. Due to communication constraints, clients often use lossy…
Over the last four decades, the way knowledge is created in academia has transformed dramatically: research teams have grown larger, scholars draw from ever-wider pools of prior work, and the most influential discoveries increasingly emerge…
Two novel decoupling and matching networks (DMNs) in microstrip technology for three-element uniform circular arrays (UCAs) are investigated and compared to a more conventional DMN approach with simple neutralization lines. The array…
The exponential growth of astronomical data collected by both ground based and space borne instruments has fostered the growth of Astroinformatics: a new discipline laying at the intersection between astronomy, applied computer science, and…
Nowadays, collaborative modeling performed by multiple stakeholders is gaining a growing interest in both academia and practice. However, it poses a set of research challenges, such as large and complex models management, support for…
Multi-modal behavior cloning faces significant challenges due to mode averaging and mode collapse, where traditional models fail to capture diverse input-output mappings. This problem is critical in applications like robotics, where…
As large-scale international collaborations become the standard for astronomy research, a wealth of opportunities have emerged to create innovative education and public outreach (EPO) programming. In the past two decades, large…
Introduction: Digital products increasingly reshape industries, influencing human behavior and decision-making. However, the software development teams developing these systems often lack diversity, which may lead to designs that overlook…
The Entity Set Expansion (ESE) task aims to expand a handful of seed entities with new entities belonging to the same semantic class. Conventional ESE methods are based on mono-modality (i.e., literal modality), which struggle to deal with…
With the extremely rapid advances in remote sensing (RS) technology, a great quantity of Earth observation (EO) data featuring considerable and complicated heterogeneity is readily available nowadays, which renders researchers an…