Tree-based models are widely recognized for their interpretability and have proven effective in various application domains, particularly in high-stakes domains. However, learning decision trees (DTs) poses a significant challenge due to their combinatorial complexity and discrete, non-differentiable nature. As a result, traditional methods such as CART, which rely on greedy search procedures, remain the most widely used approaches. These methods make locally optimal decisions at each node, constraining the search space and often leading to suboptimal tree structures. […]

Ver mais

arXiv:2604.09829v1 Announce Type: new Abstract: Gaze-following in child-robot interaction improves attention, recall, and learning, but requires expensive platforms ($30,000+), sensors, algorithms, and raises privacy concerns. We propose a framework that avoids sensors and computation entirely, instead relying on the human visual system’s assumption of convexity to produce perceptual gaze-following between a robot and its viewer. Specifically, we motivate sub-dollar cardboard robot design that directly implements the brain’s own gaze computation pipeline in reverse, making the viewer’s perceptual system […]

Ver mais

arXiv:2602.06155v1 Announce Type: cross Abstract: Diffusion models rely on a high-dimensional latent space of initial noise seeds, yet it remains unclear whether this space contains sufficient structure to predict properties of the generated samples, such as their classes. In this work, we investigate the emergence of latent structure through the lens of confidence scores assigned by a pre-trained classifier to generated samples. We show that while the latent space appears largely unstructured when considering all noise realizations, restricting […]

Ver mais

Abstract: Classical Design by Contract (DbC) implicitly relies on the “Memory Axiom”—the assumption that human collaborators possess persistent contextual memory. The emergence of stateless AI agents as primary code-producers invalidates this axiom. We propose that in an agentic workflow, the contract must transcend its role as a correctness specification and become a complete, self-contained reconstruction of system intent. :::tip This is Part 5 of my contract-style-comments (CSC) series. Part 4: Why Agentic Software Development Needs Documentation Stewardship Part 6: How to […]

Ver mais

Reinforcement learning algorithms are typically designed for generic Markov Decision Processes (MDPs), where any state-action pair can lead to an arbitrary transition distribution. In many practical systems, however, only a subset of the state variables is directly influenced by the agent’s actions, while the remaining components evolve according to exogenous dynamics and account for most of the stochasticity. In this work, we study a structured class of MDPs characterized by exogenous state components whose transitions are independent of […]

Ver mais

arXiv:2604.05115v1 Announce Type: new Abstract: Artificial intelligence applications in autonomous driving, medical diagnostics, and financial systems increasingly demand machine learning models that can provide robust uncertainty quantification, interpretability, and noise resilience. Bayesian decision trees (BDTs) are attractive for these tasks because they combine probabilistic reasoning, interpretable decision-making, and robustness to noise. However, existing hardware implementations of BDTs based on CPUs and GPUs are limited by memory bottlenecks and irregular processing patterns, while multi-platform solutions exploiting analog content-addressable memory […]

Ver mais

arXiv:2604.08612v1 Announce Type: new Abstract: This study aims to enhance the bidirectional authentication capability of ML-KEM (Module-Lattice-Based Key-Encapsulation Mechanism) by proposing the post-quantum cryptography-based (PQC-based) bidirectional authentication key exchange protocol. Furthermore, it introduces dual-usage certificates combining PQC-based DSA (Digital Signature Algorithm) and PQC-based KEM, which include composite schemes, catalyst schemes, and chameleon schemes. These dual-usage certificates utilize the PQC-based DSA public key and PQC-based KEM public key within the certificate to meet the requirements for bidirectional authentication and […]

Ver mais

Engineering orgs still assume they must choose: move fast and risk defects, or slow down to ensure software quality. Modern reality breaks this binary. AI-generation tools multiply code output, microservices create complexity, and distributed teams increase context gaps across growing codebases. What once worked for small teams no longer holds as systems and organizations scale. As Maria Vinokurskaya, Founding Engineer (AI) at PlayerZero, puts it: “When you’re early, you ship something as fast as you can, see how […]

Ver mais