February 2026

Energy theft poses a significant threat to the stability and efficiency of smart grids, leading to substantial economic losses and operational challenges. Traditional centralized machine learning approaches for theft detection require aggregating user data, raising serious concerns about privacy and data security. These issues are further exacerbated in smart meter environments, where devices are often resource-constrained and lack the capacity to run heavy models. In this work, we propose a privacy-preserving federated learning framework for energy theft detection […]

Ver mais

In this work, we propose a notion of practical learnability grounded in finite sample settings, and develop a conjugate learning theoretical framework based on convex conjugate duality to characterize this learnability property. Building on this foundation, we demonstrate that training deep neural networks (DNNs) with mini-batch stochastic gradient descent (SGD) achieves global optima of empirical risk by jointly controlling the extreme eigenvalues of a structure matrix and the gradient energy, and we establish a corresponding convergence theorem. We […]

Ver mais

In this work, we propose a notion of practical learnability grounded in finite sample settings, and develop a conjugate learning theoretical framework based on convex conjugate duality to characterize this learnability property. Building on this foundation, we demonstrate that training deep neural networks (DNNs) with mini-batch stochastic gradient descent (SGD) achieves global optima of empirical risk by jointly controlling the extreme eigenvalues of a structure matrix and the gradient energy, and we establish a corresponding convergence theorem. We […]

Ver mais

Modern AI agents are powerful but often fail to align with the idiosyncratic, evolving preferences of individual users. Prior approaches typically rely on static datasets, either training implicit preference models on interaction history or encoding user profiles in external memory. However, these approaches struggle with new users and with preferences that change over time. We introduce Personalized Agents from Human Feedback (PAHF), a framework for continual personalization in which agents learn online from live interaction using explicit per-user […]

Ver mais

The Subscription Creep Problem Nobody Talks About I pulled my bank statements last November and counted 14 recurring subscriptions. Google One for storage. iCloud for family photos. 1Password. Three streaming services. A VPN. Backblaze for backups. Two productivity tools I barely used. Total monthly damage: $103. According to Deloitte’s 2025 Digital Media Trends report, the average U.S. streaming household pays $69/month across four video services alone, a 13% year-over-year increase. Add cloud storage, password management, and backup services, […]

Ver mais

Most common-sense explanations of time quietly assume what they are supposed to explain. We say time moves forward because clocks tick. But clocks only measure something, they do not explain why it has a direction. n We say time moves forward because the universe started in a special state. But that just pushes the mystery to the beginning and calls it a solution. The arrow of time still looks like a narrative patch. A story we tell to […]

Ver mais

If I asked a hundred people to define twenty words, no two persons would give identical definitions for all twenty. If each word has just three possible interpretations (the actual number is far higher), that’s 3^20 = 3.4 billion possible combinations. Your definition of “intelligence” was shaped by every smart and stupid person you’ve met, every test you’ve taken, every moment you felt quick or slow. Mine was shaped by different people, different tests, different moments. When you […]

Ver mais

I do not think I would hire a butler who’s hypnotizable. The idea of a butler is a pretty strange thing. What if someone hypnotized the butler to do something ? I think it would be better to have a butler who can think for themselves and make choices. A hypnotizable butler would not be very good, at keeping secrets or taking care of things. I would want a butler who’s smart and can stay in control not […]

Ver mais

Manual image editing for product retail often bottlenecks creative teams with repetitive tasks like background removal and resizing. This article introduces Combo Banana, a prototype that automates these workflows by allowing designers to define reusable “combos”—sequences of AI-driven operations executed in seconds. Built on a modern stack featuring Gradio for the interface, Nano Banana for advanced AI processing, and Google Cloud Run for serverless scalability, the tool demonstrates how powerful models can be abstracted into practical, user-friendly solutions. […]

Ver mais

Physics-informed neural networks and neural operators often suffer from severe optimization difficulties caused by ill-conditioned gradients, multi-scale spectral behavior, and stiffness induced by physical constraints. Recently, the Muon optimizer has shown promise by performing orthogonalized updates in the singular-vector basis of the gradient, thereby improving geometric conditioning. However, its unit-singular-value updates may lead to overly aggressive steps and lack explicit stability guarantees when applied to physics-informed learning. In this work, we propose SpecMuon, a spectral-aware optimizer that integrates […]

Ver mais