arXiv:2601.22256v1 Announce Type: new Abstract: Monitoring in-class programming exercises can help instructors identify struggling students and common challenges. However, understanding students’ progress can be prohibitively difficult, particularly for multi-faceted problems that include multiple steps with complex interdependencies, have no predictable completion order, or involve evaluation criteria that are difficult to summarize across many students (e.g., exercises building interactive web-based user interfaces). We introduce SPARK, a coding exercise monitoring dashboard designed to address these challenges. SPARK allows instructors to […]

Ver mais

We study the complexity of smoothed agnostic learning, recently introduced by~cite{CKKMS24}, in which the learner competes with the best classifier in a target class under slight Gaussian perturbations of the inputs. Specifically, we focus on the prototypical task of agnostically learning halfspaces under subgaussian distributions in the smoothed model. The best known upper bound for this problem relies on $L_1$-polynomial regression and has complexity $d^{tilde{O}(1/σ^2) log(1/ε)}$, where $σ$ is the smoothing parameter and $ε$ is the excess error. […]

Ver mais

We propose a structural framework for organizing the submanifold content of compact Calabi–Yau manifolds through the notion of a {Topological Slice Structure} (TSS), a coherent collection of calibrated submanifolds compatible with the Ricci-flat metric data. The central result is a decomposition principle asserting that, under mild conditions on the K”ahler polarization, such a structure exists, its cohomology classes span the full integer homology, and it is covariant with respect to mirror symmetry. Special cases recover special Lagrangian torus […]

Ver mais

For over a decade, the “PHP stack” has been synonymous with a specific architecture: Nginx or Apache acting as a reverse proxy, speaking FastCGI to a pool of PHP-FPM workers. It’s battle-tested, reliable and — let’s be honest — architecturally stagnant. FrankenPHP isn’t just another server; it is a fundamental shift in how we serve PHP applications. Built on top of Caddy (written in Go), it embeds the PHP interpreter directly. No more FastCGI overhead. No more Nginx config hell. And […]

Ver mais

Although deep neural networks perform extremely well in controlled environments, they fail in real-world scenarios where data isn’t available all at once, and the model must adapt to a new data distribution that may or may not follow the initial distribution. Previously acquired knowledge is lost during subsequent updates based on new data. a phenomenon commonly known as catastrophic forgetting. In contrast, the brain can learn without such catastrophic forgetting, irrespective of the number of tasks it encounters. […]

Ver mais

Efficient representation learning is essential for optimal information storage and classification. However, it is frequently overlooked in artificial neural networks (ANNs). This neglect results in networks that can become overparameterized by factors of up to 13, increasing redundancy and energy consumption. As the demand for large language models (LLMs) and their scale increase, these issues are further highlighted, raising significant ethical and environmental concerns. We analyze our previously developed biologically inspired learning rule using information-theoretic concepts, evaluating its […]

Ver mais

arXiv:2602.10905v2 Announce Type: replace-cross Abstract: In this work, we propose Natural Hypergradient Descent (NHGD), a new method for solving bilevel optimization problems. To address the computational bottleneck in hypergradient estimation–namely, the need to compute or approximate Hessian inverse–we exploit the statistical structure of the inner optimization problem and use the empirical Fisher information matrix as an asymptotically consistent surrogate for the Hessian. This design enables a parallel optimize-and-approximate framework in which the Hessian-inverse approximation is updated synchronously with […]

Ver mais

arXiv:2603.12510v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have significant potential to enable general-purpose robotic systems for a range of vision-language tasks. However, the performance of VLA-based robots is highly sensitive to the precise wording of language instructions, and it remains difficult to predict when such robots will fail. To improve the robustness of VLAs to different wordings, we present Q-DIG (Quality Diversity for Diverse Instruction Generation), which performs red-teaming by scalably identifying diverse natural language task descriptions […]

Ver mais