arXiv:2509.16891v2 Announce Type: replace Abstract: While Large Language Models (LLMs) have demonstrated impressive reasoning and planning abilities in textual domains and can effectively follow instructions for complex tasks, their ability to understand and manipulate spatial relationships remains limited. Such capabilities are crucial for content-aware graphic layout design, where the goal is to arrange heterogeneous elements […]
Autoencoding Random Forests
arXiv:2505.21441v3 Announce Type: replace-cross Abstract: We propose a principled method for autoencoding with random forests. Our strategy builds on foundational results from nonparametric statistics and spectral graph theory to learn a low-dimensional embedding of the model that optimally represents relationships in the data. We provide exact and approximate solutions to the decoding problem via constrained […]
SKGE: Spherical Knowledge Graph Embedding with Geometric Regularization
arXiv:2511.02460v1 Announce Type: cross Abstract: Knowledge graph embedding (KGE) has become a fundamental technique for representation learning on multi-relational data. Many seminal models, such as TransE, operate in an unbounded Euclidean space, which presents inherent limitations in modeling complex relations and can lead to inefficient training. In this paper, we propose Spherical Knowledge Graph Embedding […]
Neural dynamics of cognitive control: Current tensions and future promise
arXiv:2511.02063v1 Announce Type: new Abstract: Cognitive control is a suite of processes that helps individuals pursue goals despite resistance or uncertainty about what to do. Although cognitive control has been extensively studied as a dynamic feedback loop of perception, valuation, and action, it remains incompletely understood as a cohesive dynamic and distributed neural process. Here, […]
A Cognitive Process-Inspired Architecture for Subject-Agnostic Brain Visual Decoding
arXiv:2511.02565v1 Announce Type: cross Abstract: Subject-agnostic brain decoding, which aims to reconstruct continuous visual experiences from fMRI without subject-specific training, holds great potential for clinical applications. However, this direction remains underexplored due to challenges in cross-subject generalization and the complex nature of brain signals. In this work, we propose Visual Cortex Flow Architecture (VCFlow), a […]
Epidemic Momentum
arXiv:2511.01939v1 Announce Type: new Abstract: Infectious disease outbreaks have precipitated a profusion of mathematical models. We introduce a unifying concept of “epidemic momentum” — prevalence weighted by the capacity to infect in the future — and use it to reveal a common underlying geometry that corresponds to contours of a generic first integral. Exploiting this […]
Vibe Learning: Education in the age of AI
arXiv:2511.01956v1 Announce Type: cross Abstract: The debate over whether “thinking machines” could replace human intellectual labor has existed in both public and expert discussions since the mid-twentieth century, when the concept and terminology of Artificial Intelligence (AI) first emerged. For decades, this idea remained largely theoretical. However, with the recent advent of Generative AI – […]
From the RNA world to land plants: Evolutionary insights from tRNA genes
arXiv:2511.01943v1 Announce Type: new Abstract: Transfer RNAs (tRNAs) are universal adaptors of the genetic code, yet their evolutionary dynamics across photosynthetic eukaryotes remain underexplored. Here, we present the largest comparative re-analysis integrating the PlantRNA database with published data to explore tRNA gene evolution. We find that tRNA gene repertoires have been deeply shaped by ecological […]
Quantum-Enhanced Generative Models for Rare Event Prediction
arXiv:2511.02042v1 Announce Type: cross Abstract: Rare events such as financial crashes, climate extremes, and biological anomalies are notoriously difficult to model due to their scarcity and heavy-tailed distributions. Classical deep generative models often struggle to capture these rare occurrences, either collapsing low-probability modes or producing poorly calibrated uncertainty estimates. In this work, we propose the […]
Stochastic Models and Estimation of Undetected Infections in the Transmission of Zika Virus
arXiv:2511.01920v1 Announce Type: new Abstract: Zika fever, a mosquito-borne viral disease with potential severe neurological complications and birth defects, remains a significant public health concern. The epidemiological models often oversimplify the dynamics of Zika transmission by assuming immediate detection of all infected cases. This study provides an enhanced SEIR (Susceptible-Exposed-Infectious-Recovered) model to incorporate partial information […]