technocracy

Photo by Barrett Ward on Unsplash This project was presented as the final project to obtain the Founderz AI Business School + Microsoft certificate in AI and Innovation 2025. Summary In contemporary logistics, punctuality has emerged as a fundamental pillar for customer loyalty and business competitiveness. However, a significant part of supply chains continue to operate under reactive paradigms, limiting themselves to managing delays only when they have already materialized. This project addresses this inefficiency by developing a comprehensive […]

Ver mais

Noisy labels in distributed datasets induce severe local overfitting and consequently compromise the global model in federated learning (FL). Most existing solutions rely on selecting clean devices or aligning with public clean datasets, rather than endowing the model itself with robustness. In this paper, we propose FedCova, a dependency-free federated covariance learning framework that eliminates such external reliances by enhancing the model’s intrinsic robustness via a new perspective on feature covariances. Specifically, FedCova encodes data into a discriminative […]

Ver mais

arXiv:2601.03435v1 Announce Type: new Abstract: We introduce ASPECTSIM, a simple and interpretable framework that requires conditioning document similarity on an explicitly specified aspect, which is different from the traditional holistic approach in measuring document similarity. Experimenting with a newly constructed benchmark of 26K aspect-document pairs, we found that ASPECTSIM, when implemented with direct GPT-4o prompting, achieves substantially higher human-machine agreement ($approx$80% higher) than the same for holistic similarity without explicit aspects. These findings underscore the importance of explicitly […]

Ver mais

Constitutional AI is a method to oversee and control LLMs based on a set of rules written in natural language. These rules are typically written by human experts, but could in principle be learned automatically given sufficient training data for the desired behavior. Existing LLM-based prompt optimizers attempt this but are ineffective at learning constitutions since (i) they require many labeled examples and (ii) lack structure in the optimized prompts, leading to diminishing improvements as prompt size grows. […]

Ver mais

arXiv:2504.14094v3 Announce Type: replace-cross Abstract: Concept-based Models aim to improve interpretability by predicting high-level intermediate concepts, representing a promising approach for deployment in high-risk scenarios. However, they are known to suffer from information leakage, whereby models exploit unintended information encoded within the learned concepts. We introduce an information-theoretic framework to rigorously characterise and quantify leakage, and define two complementary measures: the concepts-task leakage (CTL) and interconcept leakage (ICL) scores. We show that these measures are strongly predictive of […]

Ver mais

In this tutorial: You will understand that Exploration vs Exploitation is not a button, it is not “epsilon“, but a real data collection strategy, which decides what the agent can learn and how good it can become. You will see why the training reward can lie to you, why an agent without exploration can look “better” on the graph, but actually be weaker in reality. You will learn where exploration actually occurs in an Markov Decision Process(MDP), not […]

Ver mais

In this tutorial, we build a complete and practical Crawl4AI workflow and explore how modern web crawling goes far beyond simply downloading page HTML. We set up the full environment, configure browser behavior, and work through essential capabilities such as basic crawling, markdown generation, structured CSS-based extraction, JavaScript execution, session handling, screenshots, link analysis, concurrent crawling, and deep multi-page exploration. We also examine how Crawl4AI can be extended with LLM-based extraction to transform raw web content into structured, […]

Ver mais

arXiv:2604.13076v1 Announce Type: new Abstract: We investigate the robustness of value alignment via finetuning with synthetic documents, using animal compassion as a value that is both important in its own right and orthogonal to existing alignment efforts. To evaluate compassionate reasoning, we develop and publicly release the Animal Harm Benchmark (AHB), a 26-question evaluation spanning 13 ethical dimensions, publicly available as a dataset and Inspect evaluation. On the AHB, training with 3000 documents achieves 77% compared to 40% […]

Ver mais

Creators often have to parse through charts and dashboards to understand their performance, but with the new AI assistant, they can get quick answers to questions like “When should I post?” and “What are people saying in my comments?”

Ver mais