Blog
How Private is Your Attention? Bridging Privacy with In-Context Learning
In-context learning (ICL)-the ability of transformer-based models to perform new tasks from examples provided at inference time-has emerged as a hallmark of modern language models. While recent works have investigated the mechanisms underlying ICL, its feasibility under formal privacy constraints remains largely...
Approximation of Invariant Solutions to the Nonlinear Filtration Equation by Modified Pade Approximants
This paper deals with a mathematical model for oil filtration in a porous medium and its self-similar and traveling wave regimes. The model consists of the equation for conservation mass and dependencies for porosity, permeability, and oil density on pressure. The oil...
MVQA: Mamba with Unified Sampling for Efficient Video Quality Assessment
The rapid growth of long-duration, high-definition videos has made efficient video quality assessment (VQA) a critical challenge. Existing research typically tackles this problem through two main strategies: reducing model parameters and resampling inputs. However, light-weight Convolution Neural Networks (CNN) and Transformers often...
Heterogeneous networks in drug-target interaction prediction
Drug discovery requires a tremendous amount of time and cost. Computational drug-target interaction prediction, a significant part of this process, can reduce these requirements by narrowing the search space for wet lab experiments. In this survey, we provide comprehensive details of graph...
From observed transitions to hidden paths in Markov networks
The number of observable degrees of freedom is typically limited in experiments. Here, we consider discrete Markov networks in which an observer has access to a few visible transitions and the waiting times between these transitions. Focusing on the underlying structure of...
Leveraging Social Media Analytics for Sustainability Trend Detection in Saudi Arabias Evolving Market
Saudi Arabias rapid economic growth and social evolution under Vision 2030 present a unique opportunity to track emerging trends in real time. Uncovering trends in real time can open up new avenues for business and investment opportunities. This paper explores how AI...
Navigating the State of Cognitive Flow: Context-Aware AI Interventions for Effective Reasoning Support
Flow theory describes an optimal cognitive state where individuals experience deep focus and intrinsic motivation when a task’s difficulty aligns with their skill level. In AI-augmented reasoning, interventions that disrupt the state of cognitive flow can hinder rather than enhance decision-making. This...
Non-Renormalizable SU(5) GUTs: Leptoquark-Induced Neutrino Masses
We revisit the doublet-triplet splitting problem within the $SU(5)$ gauge group framework to advocate a viable regime with the light scalar leptoquark of the doublet-triplet splitting notoriety that is compatible with the current experimental bounds on partial proton decay lifetimes. We explicitly...
EnsAI: An Emulator for Atmospheric Chemical Ensembles
Ensemble-based methods for data assimilation and emission inversions are a popular way to encode flow-dependency within the model error covariance. While most ensemble methods do not require the use of an adjoint model, the need to repeatedly run a geophysical model to...
Modeling Tidal Disruptions with Dynamical Tides
Tidal disruption events (TDEs) occur when stars pass close enough to supermassive black holes to be torn apart by tidal forces. Traditionally, these events are studied with computationally intensive hydrodynamical simulations. In this paper, we present a fast, physically motivated two-stage model...