arXiv:2604.06222v1 Announce Type: new Abstract: Why do we forget? Why do we remember things that never happened? The conventional answer points to biological hardware. We propose a different one: geometry. Here we show that high-dimensional embedding spaces, subjected to noise, interference, and temporal degradation, reproduce quantitative signatures of human memory with no phenomenon-specific engineering. Power-law […]
Lost in Cultural Translation: Do LLMs Struggle with Math Across Cultural Contexts?
arXiv:2503.18018v2 Announce Type: replace Abstract: We demonstrate that large language models’ (LLMs) mathematical reasoning is culturally sensitive: testing 14 models from Anthropic, OpenAI, Google, Meta, DeepSeek, Mistral, and Microsoft across six culturally adapted variants of the GSM8K benchmark, we find accuracy drops ranging from 0.3% (Claude 3.5 Sonnet) to 5.9% (LLaMA 3.1-8B) when math problems […]
Unsupervised Neural Network for Automated Classification of Surgical Urgency Levels in Medical Transcriptions
arXiv:2604.06214v1 Announce Type: cross Abstract: Efficient classification of surgical procedures by urgency is paramount to optimize patient care and resource allocation within healthcare systems. This study introduces an unsupervised neural network approach to automatically categorize surgical transcriptions into three urgency levels: immediate, urgent, and elective. Leveraging BioClinicalBERT, a domain-specific language model, surgical transcripts are transformed […]
Looking Beyond the Obvious: A Survey on Abstract Concept Recognition for Video Understanding
arXiv:2508.20765v2 Announce Type: replace-cross Abstract: The automatic understanding of video content is advancing rapidly. Empowered by deeper neural networks and large datasets, machines are increasingly capable of understanding what is concretely visible in video frames, whether it be objects, actions, events, or scenes. In comparison, humans retain a unique ability to also look beyond concrete […]
HingeMem: Boundary Guided Long-Term Memory with Query Adaptive Retrieval for Scalable Dialogues
arXiv:2604.06845v1 Announce Type: cross Abstract: Long-term memory is critical for dialogue systems that support continuous, sustainable, and personalized interactions. However, existing methods rely on continuous summarization or OpenIE-based graph construction paired with fixed Top-textitk retrieval, leading to limited adaptability across query categories and high computational overhead. In this paper, we propose HingeMem, a boundary-guided long-term […]
Synthetic Homes: A Multimodal Generative AI Pipeline for Residential Building Data Generation under Data Scarcity
arXiv:2509.09794v4 Announce Type: replace Abstract: Computational models have emerged as powerful tools for multi-scale energy modeling research at the building and urban scale, supporting data-driven analysis across building and urban energy systems. However, these models require large amounts of building parameter data that is often inaccessible, expensive to collect, or subject to privacy constraints. We […]
Path Regularization: A Near-Complete and Optimal Nonasymptotic Generalization Theory for Multilayer Neural Networks and Double Descent Phenomenon
arXiv:2503.02129v2 Announce Type: replace-cross Abstract: Path regularization has shown to be a very effective regularization to train neural networks, leading to a better generalization property than common regularizations i.e. weight decay, etc. We propose a first near-complete (as will be made explicit in the main text) nonasymptotic generalization theory for multilayer neural networks with path […]
FBS: Modeling Native Parallel Reading inside a Transformer
arXiv:2601.21708v2 Announce Type: replace Abstract: Large language models (LLMs) excel across many tasks, yet inference is still dominated by strictly token-by-token autoregression. Existing acceleration methods largely patch this pipeline and miss core human-reading ingredients: content-adaptive foresight, chunk-structure-aware compute allocation, and train-test consistency for preview/skimming. We propose the Fovea-Block-Skip Transformer (FBS), which injects a causal, trainable […]
Matrix Profile for Anomaly Detection on Multidimensional Time Series
arXiv:2409.09298v2 Announce Type: replace-cross Abstract: The Matrix Profile (MP), a versatile tool for time series data mining, has been shown effective in time series anomaly detection (TSAD). This paper delves into the problem of anomaly detection in multidimensional time series, a common occurrence in real-world applications. For instance, in a manufacturing factory, multiple sensors installed […]
Weakly Supervised Distillation of Hallucination Signals into Transformer Representations
arXiv:2604.06277v1 Announce Type: new Abstract: Existing hallucination detection methods for large language models (LLMs) rely on external verification at inference time, requiring gold answers, retrieval systems, or auxiliary judge models. We ask whether this external supervision can instead be distilled into the model’s own representations during training, enabling hallucination detection from internal activations alone at […]
Luwen Technical Report
arXiv:2604.06737v1 Announce Type: cross Abstract: Large language models have demonstrated remarkable capabilities across a wide range of natural language processing tasks, yet their application in the legal domain remains challenging due to the specialized terminology, complex reasoning requirements, and rapidly evolving legal knowledge involved. In this paper, we present Luwen, an open-source Chinese legal language […]
Governing frontier general-purpose AI in the public sector: adaptive risk management and policy capacity under uncertainty through 2030
arXiv:2604.06215v1 Announce Type: cross Abstract: The governance of frontier general-purpose artificial intelligence has become a public-sector problem of institutional design, not merely a technical issue of model performance. Recent evidence indicates that AI capabilities are advancing rapidly, though unevenly, while knowledge about harms, safeguards, and effective interventions remains partial and lagged. This combination creates a […]