Why I ditched the standard Python stack for a Kotlin-C++ hybrid to achieve microsecond-level inference on the edge. Let’s be real for a second: the AI world is currently high on “clever prompts.” Everyone is a “Prompt Engineer” until they have to build a safety system for a warehouse robot or a real-time monitor for a smart city. In the high-stakes world of Industry 4.0, a prompt is just a string. To actually do something, you need a […]

Ver mais

Mesh-free numerical methods provide flexible discretisations for complex geometries; however, classical meshless discrete differential operators typically trade low computational cost for limited accuracy or high accuracy for substantial per-stencil computation. We introduce a parametrised framework for learning mesh-free discrete differential operators using a graph neural network trained via polynomial moment constraints derived from truncated Taylor expansions. The model maps local stencils relative positions directly to discrete operator weights. The current work demonstrates that neural networks can learn classical […]

Ver mais

Is it possible to train a DQN to solve a maze with non-convex obstacles in a long-horizon navigation task (in 10 minutes or less)? The rules are: You can not use old data except for the replay buffer The inputs are only the x and y coordinates of the state and the distance of the agent to the goal Step size should not exceed 2% of the total maze size You must start from the same initial state […]

Ver mais

Table of links Abstract 1 Introduction 2 Background and Related Work Software Security Coding Weaknesses Security Shift-Left Modern Code Review Code Review for Software Security Security Concern Handling Process in Code Review 3 Motivating Examples 4 Case Study Design Research Questions Studied Projects Data Collection Coding Weakness Taxonomy Study Overview Security Concern Identification Approach (RQ1) Alignment Analysis of Known Vulnerabilities (RQ2) Handling Process Identification (RQ3) 5 Preliminary Analysis PA1: Prevalence of Coding Weakness Comments PA2: Preliminary Evaluation of […]

Ver mais

arXiv:2602.13319v1 Announce Type: new Abstract: Perspective-Aware AI requires modeling evolving internal states–goals, emotions, contexts–not merely preferences. Progress is limited by a data bottleneck: digital footprints are privacy-sensitive and perspective states are rarely labeled. We propose Situation Graph Prediction (SGP), a task that frames perspective modeling as an inverse inference problem: reconstructing structured, ontology-aligned representations of perspective from observable multimodal artifacts. To enable grounding without real labels, we use a structure-first synthetic generation strategy that aligns latent labels and […]

Ver mais

arXiv:2502.18428v2 Announce Type: replace-cross Abstract: We study the asymptotic spectral distribution of the conjugate kernel random matrix $YY^top$, where $Y= f(WX)$ arises from a two-layer neural network model. We consider the setting where $W$ and $X$ are random rectangular matrices with i.i.d. entries, where the entries of $W$ follow a heavy-tailed distribution, while those of $X$ have light tails. Our assumptions on $W$ include a broad class of heavy-tailed distributions, such as symmetric $alpha$-stable laws with $alpha in […]

Ver mais

arXiv:2601.21067v1 Announce Type: new Abstract: Graphs are a fundamental data structure for representing relational information in domains such as social networks, molecular systems, and knowledge graphs. However, graph learning models often suffer from limited generalization when applied beyond their training distributions. In practice, distribution shifts may arise from changes in graph structure, domain semantics, available modalities, or task formulations. To address these challenges, graph foundation models (GFMs) have recently emerged, aiming to learn general-purpose representations through large-scale pretraining […]

Ver mais

arXiv:2601.22329v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly positioned as decision engines for hiring, healthcare, and economic judgment, yet real-world human judgment reflects a balance between rational deliberation and emotion-driven bias. If LLMs are to participate in high-stakes decisions or serve as models of human behavior, it is critical to assess whether they exhibit analogous patterns of (ir)rationalities and biases. To this end, we evaluate multiple LLM families on (i) benchmarks testing core axioms of […]

Ver mais

The Elephant in Every WordPress Agency’s Room There are roughly 835 million websites on the internet. According to W3Techs, WordPress powers about 43% of them. That is not a niche platform. That is the infrastructure layer of the modern web. But here is the uncomfortable part: a staggering number of those WordPress sites have not been meaningfully updated in years. Not the core software updates (most hosts handle those automatically now), but the actual design, content structure, and […]

Ver mais

arXiv:2604.15350v1 Announce Type: new Abstract: We discover that large language models exhibit emph{spectral phase transitions} in their hidden activation spaces when engaging in reasoning versus factual recall. Through systematic spectral analysis across textbf{11 models} spanning textbf{5 architecture families} (Qwen, Pythia, Phi, Llama, DeepSeek-R1), we identify textbf{seven} core phenomena: (1)~textbf{Reasoning Spectral Compression} — 9/11 models show significantly lower $alpha$ for reasoning ($p < 0.05$), with larger effects in stronger models; (2)~textbf{Instruction Tuning Spectral Reversal} — base models show reasoning […]

Ver mais