We propose a framework for the joint inference of network topology, multi-type interaction kernels, and latent type assignments in heterogeneous interacting particle systems from multi-trajectory data. This learning task is a challenging non-convex mixed-integer optimization problem, which we address through a novel three-stage approach. First, we leverage shared structure across agent interactions to recover a low-rank embedding of the system parameters via matrix sensing. Second, we identify discrete interaction types by clustering within the learned embedding. Third, we […]

Ver mais

We know that engaging developers isn’t easy. They despise flashy ads and can spot “marketing” from a mile away.  But there’s one thing developers consistently show up for: Hackathons. They’re hands-on. They’re competitive. They’re creative. They let builders actually use your tech, instead of just hearing about it, and create something useful from it.  Incentivization + gamification + awareness = win-win-win! :::tip Learn more about HackerNoon Hackathons ::: HackerNoon Remote Technology Hackathons: Built for Longevity (Not Weekend Noise) […]

Ver mais

With the rise of generative AI, creative ownership has been a hot topic worldwide. As AI tools like ChatGPT, Gemini, and others are becoming much more capable of generating images, text, and music independently, legal questions about copyright infringement and authorship are intensifying. Who truly owns content generated by AI, and can it ever qualify for legal protection? Well, the U.S. Supreme Court may have just answered that question. Thaler’s AI artwork sparks landmark copyright debate As reported […]

Ver mais

arXiv:2601.14267v1 Announce Type: new Abstract: Biomedical evidence synthesis relies on accurate extraction of methodological, laboratory, and outcome variables from full-text research articles, yet these variables are embedded in complex scientific PDFs that make manual abstraction time-consuming and difficult to scale. Existing document AI systems remain limited by OCR errors, long-document fragmentation, constrained throughput, and insufficient auditability for high-stakes synthesis. We present a schema-constrained AI extraction system that transforms full-text biomedical PDFs into structured, analysis-ready records by explicitly restricting […]

Ver mais

arXiv:2601.17096v1 Announce Type: new Abstract: Recent scholarship typically characterizes Large Language Models (LLMs) through either an textit{Instrumental Paradigm} (viewing models as reflections of their developers’ culture) or a textit{Substitutive Paradigm} (viewing models as bilingual proxies that switch cultural frames based on language). This study challenges these anthropomorphic frameworks by proposing textbf{Machine Culture} as an emergent, distinct phenomenon. We employed a 2 (Model Origin: US vs. China) $times$ 2 (Prompt Language: English vs. Chinese) factorial design across eight multimodal […]

Ver mais

arXiv:2505.20754v2 Announce Type: replace Abstract: Approximation of a target probability distribution using a finite set of points is a problem of fundamental importance in numerical integration. Several authors have proposed to select points by minimising a maximum mean discrepancy (MMD), but the non-convexity of this objective typically precludes global minimisation. Instead, we consider the concept of emph{stationary points of the MMD} which, in contrast to points globally minimising the MMD, can be accurately computed. Our main contributions are […]

Ver mais

arXiv:2601.18823v1 Announce Type: new Abstract: Variational autoencoders (VAE) encode data into lower-dimensional latent vectors before decoding those vectors back to data. Once trained, one can hope to detect out-of-distribution (abnormal) latent vectors, but several issues arise when the latent space is high dimensional. This includes an exponential growth of the hypervolume with the dimension, which severely affects the generative capacity of the VAE. In this paper, we draw insights from high dimensional statistics: in these regimes, the latent […]

Ver mais

arXiv:2601.05451v1 Announce Type: new Abstract: Recent advances in text-to-SQL systems have been driven by larger models and improved datasets, yet progress is still limited by the scarcity of high-quality training data. Manual data creation is expensive, and existing synthetic methods trade off reliability and scalability. Template-based approaches ensure correct SQL but require schema-specific templates, while LLM-based generation scales easily but lacks quality and correctness guarantees. We introduce RingSQL, a hybrid data generation framework that combines schema-independent query templates […]

Ver mais

arXiv:2502.03792v2 Announce Type: replace Abstract: We demonstrate that applying an eventual decay to the learning rate (LR) in empirical risk minimization (ERM), where the mean-squared-error loss is minimized using standard gradient descent (GD) for training a two-layer neural network with Lipschitz activation functions, ensures that the resulting network exhibits a high degree of Lipschitz regularity, that is, a small Lipschitz constant. Moreover, we show that this decay does not hinder the convergence rate of the empirical risk, now […]

Ver mais