arXiv:2405.18828v2 Announce Type: replace-cross Abstract: The present work aims at proving mathematically that a neural network inspired by biology can learn a classification task thanks to local transformations only. In this purpose, we propose a spiking neural network named CHANI (Correlation-based Hawkes Aggregation of Neurons with bio-Inspiration), whose neurons activity is modeled by Hawkes processes. Synaptic weights are updated thanks to an expert aggregation algorithm, providing a local and simple learning rule. We were able to prove that […]

Ver mais

arXiv:2602.13061v1 Announce Type: cross Abstract: The ability of Flow Matching (FM) to model complex conditional distributions has established it as the state-of-the-art for prediction tasks (e.g., robotics, weather forecasting). However, deployment in safety-critical settings is hindered by a critical extrapolation hazard: driven by smoothness biases, flow models yield plausible outputs even for off-manifold conditions, resulting in silent failures indistinguishable from valid predictions. In this work, we introduce Diverging Flows, a novel approach that enables a single model to […]

Ver mais

Gemma 3n is a cutting-edge open model designed for fast, multimodal AI on devices, featuring optimized performance, unique flexibility with a 2-in-1 model, and expanded multimodal understanding with audio, empowering developers to build live, interactive applications and sophisticated audio-centric experiences.

Ver mais

Principal Component Analysis (PCA) is a simple yet popular and useful linear transformation technique that is used in numerous applications, such as stock market predictions, the analysis of gene expression data, and many more. In this tutorial, we will see that PCA is not just a “black box”, and we are going to unravel its internals in 3 basic steps.

Ver mais

New data confirms Cato scholar David Bier’s report that DHS publicly dismissed as “made up”: 71% of ICE arrests in early October had no criminal convictions, and 45% had no convictions or even pending charges. lead , , The data—directly from ICE—shows arrests of non-criminals have surged 585% year-over-year while ICE ignores nearly 500,000 removable immigrants with actual convictions. You can read Bier’s full analysis here. His previous data can be found here. If you’d like to speak with Bier, […]

Ver mais

arXiv:2601.22328v1 Announce Type: new Abstract: Recovering governing equations from data is central to scientific discovery, yet existing methods often break down under noisy, partial observations, or rely on black-box latent dynamics that obscure mechanism. We introduce MAAT (Model Aware Approximation of Trajectories), a framework for symbolic discovery built on knowledge-informed Kernel State Reconstruction. MAAT formulates state reconstruction in a reproducing kernel Hilbert space and directly incorporates structural and semantic priors such as non-negativity, conservation laws, and domain-specific observation […]

Ver mais

arXiv:2601.15311v1 Announce Type: new Abstract: Large Language Models (LLMs) are fundamentally constrained by the quadratic computational cost of self-attention and the “Lost in the Middle” phenomenon, where reasoning capabilities degrade as context windows expand. Existing solutions, primarily “Flat RAG” architectures relying on vector databases, treat memory as an unstructured bag of embeddings. This approach fails to capture the hierarchical and temporal structure of long-horizon interactions, leading to “Vector Haze”, the retrieval of disjointed facts lacking episodic continuity. We […]

Ver mais

arXiv:2601.09001v1 Announce Type: new Abstract: Deploying LLMs raises two coupled challenges: (1) monitoring – estimating where a model underperforms as traffic and domains drift – and (2) improvement – prioritizing data acquisition to close the largest performance gaps. We test whether an inference-time signal can estimate slice-level accuracy under domain shift. For each response, we compute an output-entropy profile from final-layer next-token probabilities (from top-k logprobs) and summarize it with eleven statistics. A lightweight classifier predicts instance correctness, […]

Ver mais

arXiv:2602.16832v1 Announce Type: new Abstract: Safety alignment of large language models (LLMs) is mostly evaluated in English and contract-bound, leaving multilingual vulnerabilities understudied. We introduce textbf{Indic Jailbreak Robustness (IJR)}, a judge-free benchmark for adversarial safety across 12 Indic and South Asian languages (2.1 Billion speakers), covering 45216 prompts in JSON (contract-bound) and Free (naturalistic) tracks. IJR reveals three patterns. (1) Contracts inflate refusals but do not stop jailbreaks: in JSON, LLaMA and Sarvam exceed 0.92 JSR, and in […]

Ver mais

arXiv:2601.00175v1 Announce Type: new Abstract: Objective: Develop and evaluate machine learning (ML) models for predicting incident liver cirrhosis one, two, and three years prior to diagnosis using routinely collected electronic health record (EHR) data, and to benchmark their performance against the FIB-4 score. Methods: We conducted a retrospective cohort study using de-identified EHR data from a large academic health system. Patients with fatty liver disease were identified and categorized into cirrhosis and non-cirrhosis cohorts based on ICD-9/10 codes. […]

Ver mais