The WordPress Theme Problem Nobody Warned You About WordPress powers roughly 43% of all websites on the internet, according to W3Techs’ latest data. That number sounds impressive until you realize what it actually means for anyone trying to build AI tooling on top of it: there is no single “WordPress” to target. There are thousands of variations, each one a unique snowflake of themes, page builders, custom post types, and plugin interactions. If you have ever tried to […]

Ver mais

arXiv:2603.02255v1 Announce Type: new Abstract: We propose MEBM-Speech, a multi-scale enhanced neural decoder for speech activity detection from non-invasive magnetoencephalography (MEG) signals. Built upon the BrainMagic backbone, MEBM-Speech integrates three complementary temporal modeling mechanisms: a multi-scale convolutional module for short-term pattern extraction, a bidirectional LSTM (BiLSTM) for long-range context modeling, and a depthwise separable convolutional layer for efficient cross-scale feature fusion. A lightweight temporal jittering strategy and average pooling further improve onset robustness and boundary stability. The model […]

Ver mais

The evolution of large language models into autonomous agents introduces adversarial failures that exploit legitimate tool privileges, transforming safety evaluation in tool-augmented environments from a subjective NLP task into an objective control problem. We formalize this threat model as Tag-Along Attacks: a scenario where a tool-less adversary "tags along" on the trusted privileges of a safety-aligned Operator to induce prohibited tool use through conversation alone. To validate this threat, we present Slingshot, a ‘cold-start’ reinforcement learning framework that […]

Ver mais

arXiv:2603.26778v1 Announce Type: new Abstract: Knowledge distillation is typically realized by transferring a teacher model’s knowledge into a student’s parameters through supervised or reinforcement-based optimization. While effective, such approaches require repeated parameter updates and large-scale training data, limiting their applicability in resource-constrained environments. In this work, we propose TED, a training-free, context-based distillation framework that shifts the update target of distillation from model parameters to an in-context experience injected into the student’s prompt. For each input, the student […]

Ver mais

Online financial services constitute an essential component of contemporary web ecosystems, yet their openness introduces substantial exposure to fraud that harms vulnerable users and weakens trust in digital finance. Such threats have become a significant web harm that erodes societal fairness and affects the well being of online communities. However, existing detection methods based on graph neural networks (GNNs) struggle with two persistent challenges: (1) fraud camouflage, where malicious transactions mimic benign behaviors to evade detection, and (2) […]

Ver mais

arXiv:2601.03378v1 Announce Type: new Abstract: Repository-level code completion benefits from retrieval-augmented generation (RAG). However, controlling cross-file evidence is difficult because chunk utility is often interaction-dependent: some snippets help only when paired with complementary context, while others harm decoding when they conflict. We propose RepoShapley, a coalition-aware context filtering framework supervised by Shapley-style marginal contributions. Our module ChunkShapley constructs offline labels by (i) single-chunk probing with teacher-forced likelihood to estimate signed, weighted effects, (ii) a surrogate game that captures […]

Ver mais

arXiv:2602.06179v1 Announce Type: new Abstract: Pelvic diseases in women of reproductive age represent a major global health burden, with diagnosis frequently delayed due to high anatomical variability, complicating MRI interpretation. Existing AI approaches are largely disease-specific and lack real-time compatibility, limiting generalizability and clinical integration. To address these challenges, we establish a benchmark framework for disease- and parameter-agnostic, real-time-compatible unsupervised anomaly detection in pelvic MRI. The method uses a residual variational autoencoder trained exclusively on healthy sagittal T2-weighted […]

Ver mais

New research cut the qubit threshold by 50x. Here’s what that actually means for your wallet. For years, the standard line was reassuring: breaking Bitcoin’s encryption would require hundreds of thousands — maybe millions — of stable quantum bits. On March 31, 2026, that comfortable margin shrank significantly. A joint paper from Caltech and quantum startup Oratomic posted to arXiv argued that a neutral-atom quantum computer with around 26,000 qubits could crack ECC-256 — the elliptic curve cryptography […]

Ver mais

Reinforcement Learning (RL) has enabled Large Language Models (LLMs) to acquire increasingly complex reasoning and agentic behaviors. In this work, we propose two simple techniques to improve policy gradient algorithms for LLMs. First, we replace the fixed anchor policy during RL with an Exponential Moving Average (EMA), similar to a target network in deep Q-learning. Second, we introduce Top-k KL estimator, which allows for flexible interpolation between exact KL and sampled KL. We derive the stability conditions for […]

Ver mais

AI-assisted coding has changed software development faster than most developers expected. In just a short time, many developers went from experimenting with prompting an AI to generate small snippets of code to attempting to build entire applications with AI agents. Two major approaches have emerged from this shift: Vibe Coding — directly prompting an AI model and iterating quickly Spec-Driven Development — using structured frameworks that break requirements into specifications, user stories, and tasks before the AI writes […]

Ver mais