arXiv:2604.09717v1 Announce Type: new Abstract: Character recognition is the fundamental part of an optical character recognition (OCR) system. Word recognition, sentence transcription, document digitization, and language processing are some of the higher-order activities that can be done accurately through character recognition. Nonetheless, recognizing handwritten Bangla characters is not an easy task because they are written in different styles with inconsistent stroke patterns and a high degree of visual character resemblance. The datasets available are usually limited in intra-class […]

Ver mais

This work constructs, analyzes and simulates a modified SIR epidemiological model for the spread of a generic long-time disease, in which the coefficients of infectivity and death rate are system variables. Diseases, such as COVID-19, have demonstrated very clearly that infectivity and death rates can change over time, even for the same variant of the virus, due to vaccination, improved treatments, better analysis, better medications, etc. This motivates us to model a generic disease where the infectivity and […]

Ver mais

Both Google and Apple are cramming new AI features into their phones and other devices, and neither company has offered clear ways to control which apps those AI systems can access. Recent issues around WhatsApp on both Android and iPhone demonstrate how these interactions can go sideways, risking revealing chat conversations beyond what you intend. Users deserve better controls and clearer documentation around what these AI features can access. After diving into how Google Gemini and Apple Intelligence […]

Ver mais

I have just recently released a free-to-use open source, local python implementation of a Multi Method Reinforcement Learning pipeline with no 3rd party paid requirements or sign-ups. It’s as simple as clone, configure, run. The repo contains full documentation and pipeline explanations, is made purely for consumer hardware compatibility, and works with any existing codebase or projects.Setup is as straightforward with extremely customizable configurations alongside the entire pipeline is one python file. Context and Motivations: I’m doing this […]

Ver mais

arXiv:2602.10332v1 Announce Type: cross Abstract: In the partially-observed outcome setting, a recent set of proposals known as “prediction-powered inference” (PPI) involve (i) applying a pre-trained machine learning model to predict the response, and then (ii) using these predictions to obtain an estimator of the parameter of interest with asymptotic variance no greater than that which would be obtained using only the labeled observations. While existing PPI proposals consider estimators arising from M-estimation, in this paper we generalize PPI […]

Ver mais

I’ve been learning to code my whole life. I’ve mastered several programming languages, including C++, Delphi, C#, JavaScript, Java, and Go. I’ve created numerous software projects in different domains. Learning is always part of any programming language, platform, or framework. The learning process has changed over the past 20 years. I used to spend a lot of time searching for good books on C++ or Delphi in a bookstore. Then I’d googled problems that weren’t covered in the […]

Ver mais

arXiv:2511.22442v2 Announce Type: replace-cross Abstract: Ranking methods or models based on their performance is of prime importance but is tricky because performance is fundamentally multidimensional. In the case of classification, precision and recall are scores with probabilistic interpretations that are both important to consider and complementary. The rankings induced by these two scores are often in partial contradiction. In practice, therefore, it is extremely useful to establish a compromise between the two views to obtain a single, global […]

Ver mais

The sample complexity of multi-group learning is shown to improve in the group-realizable setting over the agnostic setting, even when the family of groups is infinite so long as it has finite VC dimension. The improved sample complexity is obtained by empirical risk minimization over the class of group-realizable concepts, which itself could have infinite VC dimension. Implementing this approach is also shown to be computationally intractable, and an alternative approach is suggested based on improper learning.

Ver mais

arXiv:2602.17809v1 Announce Type: new Abstract: Parameter-efficient fine-tuning methods such as LoRA enable practical adaptation of large language models but provide no principled uncertainty estimates, leading to poorly calibrated predictions and unreliable behavior under domain shift. We introduce Stiefel-Bayes Adapters (SBA), a Bayesian PEFT framework that places a Matrix Langevin prior over orthonormal adapter factors on the Stiefel manifold $St$ and performs approximate posterior inference via tangent space Laplace approximation with geodesic retraction. Unlike Gaussian priors in flat space […]

Ver mais

Deep Reinforcement Learning (DRL) has achieved remarkable success in domains requiring sequential decision-making, motivating its application to cybersecurity problems. However, transitioning DRL from laboratory simulations to bespoke cyber environments can introduce numerous issues. This is further exacerbated by the often adversarial, non-stationary, and partially-observable nature of most cybersecurity tasks. In this paper, we identify and systematize 11 methodological pitfalls that frequently occur in DRL for cybersecurity (DRL4Sec) literature across the stages of environment modeling, agent training, performance evaluation, […]

Ver mais