Generalizing across disparate physical laws remains a fundamental challenge for artificial intelligence in science. Existing deep-learning solvers are largely confined to single-equation settings, limiting transfer across physical regimes and inference tasks. Here we introduce pADAM, a unified generative framework that learns a shared probabilistic prior across heterogeneous partial differential equation families. Through a learned joint distribution of system states and, where applicable, physical parameters, pADAM supports forward prediction and inverse inference within a single architecture without retraining. Across […]

Ver mais

Traditional defenses against Deep Leakage (DL) attacks in Federated Learning (FL) primarily focus on obfuscation, introducing noise, transformations or encryption to degrade an attacker’s ability to reconstruct private data. While effective to some extent, these methods often still leak high-level information such as class distributions or feature representations, and are frequently broken by increasingly powerful denoising attacks. We propose a fundamentally different perspective on FL defense: framing it as a spoofing problem.We introduce SpooFL (Figure 1), a spoofing-based […]

Ver mais

I studied law. Seven years later, I did an MBA. At no point during either degree or in my work in between did anyone pull me aside and say, “Hey, you should probably learn to write a ‘for loop’.” And yet here I am, running a legaltech startup, shipping production code, and mass-texting my cofounder screenshots of features at 2 am. I’ve been chewing on the idea of the “Humanities Engineer” since about 2018-2020, back when I first […]

Ver mais

Self-supervised learning (SSL) has revolutionized representation learning, with Joint-Embedding Architectures (JEAs) emerging as an effective approach for capturing semantic features. Existing JEAs rely on implicit or explicit batch interaction — via negative sampling or statistical regularization — to prevent representation collapse. This reliance becomes problematic in regimes where batch sizes must be small, such as high-dimensional scientific data, where memory constraints and class imbalance make large, well-balanced batches infeasible. We introduce IConE (Instance-Contrasted Embeddings), a framework that decouples […]

Ver mais

arXiv:2604.08593v1 Announce Type: new Abstract: We consider two variations of the classical secretary problem. * A variation of the returning secretary problem where each interviewee may appear a second time with a fixed probability p. The decision-maker observes interviewees sequentially and must choose whether to accept or reject each appearance. We characterize the optimal threshold rule and examine its dependence on the reappearance probability p, highlighting how additional information from repeated appearances improves selection performance. * A variation […]

Ver mais

An agent that operates sequentially must incorporate new experience without forgetting old experience, under a fixed memory budget. We propose a framework in which memory is not a parameter vector but a stochastic process: a Bridge Diffusion on a replay interval $[0,1]$, whose terminal marginal encodes the present and whose intermediate marginals encode the past. New experience is incorporated via a three-step emph{Compress–Add–Smooth} (CAS) recursion. We test the framework on the class of models with marginal probability densities […]

Ver mais

The modern platform engineering mandate is clear: adopt Kubernetes, embrace microservices, and accelerate velocity. In theory, this leads to efficiency; in practice, if you operate within highly regulated sectors — Finance, Utilities, Defense, Healthcare, etc. — the journey often slows down due to significant networking and compliance requirements. While the wider developer community utilizes fully managed queues and streaming services (like AWS SQS or Confluent Cloud), enterprise architects in regulated spaces are confronted with a fundamental modernization challenge: How do you leverage […]

Ver mais