technocracy

I’ve watched this pattern unfold a few times now in my career: a breakthrough technology emerges, fragments into competing implementations, consolidates around a dominant standard, and finally it becomes so ubiquitous that no one gets excited about it anymore. It happened with relational databases. It happened with message queues. It happened with Linux. And in 2026, it’s happening with Apache Kafka. If you’re building data infrastructure today, you’ve probably noticed something curious. The major streaming vendors – the […]

Ver mais

arXiv:2604.18615v1 Announce Type: new Abstract: We study the communication complexity of distributed offline dynamic programming, where a fixed batch dataset is partitioned across (M) machines connected by the data-induced dependency graph. We compare two paradigms: direct boundary-value propagation, which follows Bellman dependencies, and gossip averaging, which mixes local estimates. Our results show that **locality** is the fundamental driver of round complexity. In particular, we prove that no method can achieve (varepsilon)-accuracy in fewer than (L_varepsilon = leftlfloor log(1/2varepsilon) […]

Ver mais

Accurately forecasting long-term atmospheric variables remains a defining challenge in meteorological science due to the chaotic nature of atmospheric systems. Temperature data represents a complex superposition of deterministic cyclical climate forces and stochastic, short-term fluctuations. While planetary mechanics drive predictable seasonal periodicities, rapid meteorological changes such as thermal variations, pressure anomalies, and humidity shifts introduce nonlinear volatilities that defy simple extrapolation. Historically, the Seasonal Autoregressive Integrated Moving Average (SARIMA) model has been the standard for modeling historical weather […]

Ver mais

Continual Learning (CL) aims to enable models to sequentially learn multiple tasks without forgetting previous knowledge. Recent studies have shown that optimizing towards flatter loss minima can improve model generalization. However, existing sharpness-aware methods for CL suffer from two key limitations: (1) they treat sharpness regularization as a unified signal without distinguishing the contributions of its components. and (2) they introduce substantial computational overhead that impedes practical deployment. To address these challenges, we propose FLAD, a novel optimization […]

Ver mais

arXiv:2602.13291v1 Announce Type: new Abstract: Artificial Intelligence (AI) has transformed robotics, healthcare, industry, and scientific discovery, yet a major frontier may lie beyond Earth. Space exploration and settlement offer vast environments and resources, but impose constraints unmatched on Earth: delayed/intermittent communications, extreme resource scarcity, heterogeneous expertise, and strict safety, accountability, and command authority. The key challenge is auditable coordination among specialised humans, robots, and digital services in a safety-critical system-of-systems. We introduce Agent Mars, an open, end-to-end multi-agent […]

Ver mais

We demonstrate that modern machine-learning methods can autonomously reconstruct several flagship analytic structures in scattering amplitudes directly from numerical on-shell data. In particular, we show that the Kawai–Lewellen–Tye (KLT) relations can be rediscovered using symbolic regression applied to colour-ordered Yang–Mills amplitudes with Mandelstam invariants as input features. Using standard feature-selection techniques, specifically column-pivoted QR factorisation, we simultaneously recover the Kleiss–Kuijf and Bern–Carrasco–Johansson (BCJ) relations, identifying a minimal basis of partial amplitudes without any group-theoretic input. We obtain the […]

Ver mais

arXiv:2507.07981v3 Announce Type: replace-cross Abstract: Reward models are key to language model post-training and inference pipelines. Conveniently, recent work showed that every language model defines an implicit reward model (IM-RM), without requiring any architectural changes. However, such IM-RMs tend to generalize worse, especially out-of-distribution, compared to explicit reward models (EX-RMs) that apply a dedicated linear head over the hidden representations of a language model. The existence of a generalization gap is puzzling, as EX-RMs and IM-RMs are nearly […]

Ver mais

I recently submitted Nullmail to Proof of Usefulness, and it scored +76 – officially “in business”! Here’s why this project matters. What It Is Nullmail is a verifiable, open-source privacy tool with active development and organic traction. While early-stage (approx. 10,000 monthly inboxes), the project’s ‘privacy-first’ architecture is validated by its open GitHub repository and recent ‘battle-testing’ against domain flagging (Cloudflare). It effectively solves a specific problem (disposable email) without data collection, positioning it as a high-utility tool […]

Ver mais

arXiv:2603.00618v1 Announce Type: new Abstract: Multi-domain graph pre-training integrates knowledge from diverse domains to enhance performance in the target domains, which is crucial for building graph foundation models. Despite initial success, existing solutions often fall short of answering a fundamental question: how is knowledge integrated or transferred across domains? This theoretical limitation motivates us to rethink the consistency and transferability between model pre-training and domain adaptation. In this paper, we propose a fresh Riemannian geometry perspective, whose core […]

Ver mais

arXiv:2601.04254v1 Announce Type: new Abstract: We present a controlled study of multi-hop contextual reasoning in large language models, providing a clean demonstration of the task-method dissociation: rule-based pattern matching achieves 100% success on structured information retrieval but only 6.7% on tasks requiring cross-document reasoning, while LLM-based multi-agent systems show the inverse pattern, achieving up to 80% on reasoning tasks where rule-based methods fail. Using a synthetic evaluation framework with 120 trials across four models (LLaMA-3 8B, LLaMA-2 13B, […]

Ver mais