arXiv:2510.03131v3 Announce Type: replace-cross Abstract: Modern regression analyses are often undermined by covariate measurement error, misspecification of the regression model, and misspecification of the measurement error distribution. We present, to the best of our knowledge, the first Bayesian nonparametric learning framework targeting total robustness to all three challenges in general nonlinear regression. Our framework places a joint Dirichlet process prior on the latent covariate–response distribution and updates it with posterior pseudo-samples of the latent covariates, so that inference […]

Ver mais

Reinforcement learning algorithms assume that observations satisfy the Markov property, yet real-world sensors frequently violate this assumption through correlated noise, latency, or partial observability. Standard performance metrics conflate Markov breakdowns with other sources of suboptimality, leaving practitioners without diagnostic tools for such violations. This paper introduces a prediction-based scoring method that quantifies non-Markovian structure in observation trajectories. A random forest first removes nonlinear Markov-compliant dynamics; ridge regression then tests whether historical observations reduce prediction error on the residuals […]

Ver mais

The New Career Moat Isn’t Depth. It’s Composition For decades, the career advice was clean: Pick a lane. Go deep. Become the expert. That strategy still works—sometimes. But AI changed the payoff curve. When models can draft, analyze, code, summarize, design, and debug at near-zero marginal cost, “being good at one isolated thing” stops being rare. It becomes a commodity input you can rent. What stays rare is the person (or team) who can combine: domain understanding, tool […]

Ver mais

I’ve been on-and-off working on this project for a few months, just wanted to share it: https://www.2drl.com/ TLDR – It’s kinda like Unity but for reinforcement learning and much more lightweight. It lets you visually design Box2D (2D rigid body physics) gym environments using a drag-and-drop interface. It also has scripting support, so in principle you can define any environment with any custom behaviour. From your scene and script, it will automatically generate the full environment code, which […]

Ver mais

arXiv:2601.22169v1 Announce Type: new Abstract: Humans are susceptible to undesirable behaviours and privacy leaks under the influence of alcohol. This paper investigates drunk language, i.e., text written under the influence of alcohol, as a driver for safety failures in large language models (LLMs). We investigate three mechanisms for inducing drunk language in LLMs: persona-based prompting, causal fine-tuning, and reinforcement-based post-training. When evaluated on 5 LLMs, we observe a higher susceptibility to jailbreaking on JailbreakBench (even in the presence […]

Ver mais

Hyperparameter optimization (HPO) is known to be costly in deep learning, especially when leveraging automated approaches. Most of the existing automated HPO methods are accuracy-based, i.e., accuracy metrics are used to guide the trials of different hyperparameter configurations amongst a specific search space. However, many trials may encounter severe training problems, such as vanishing gradients and insufficient convergence, which can hardly be reflected by accuracy metrics in the early stages of the training and often result in poor […]

Ver mais

arXiv:2603.06599v1 Announce Type: new Abstract: Artificial intelligence pipelines — spanning data collection, model training, deployment, and post-deployment monitoring — concentrate ethical risks that intensify with multimodal and agentic systems. Existing governance instruments, including the EU AI Act, the IEEE 7000 series, and the NIST AI Risk Management Framework, provide high-level guidance but often lack enforceable, end-to-end operational controls. This paper presents an ethics-by-design control architecture that embeds consequentialist, deontological, and virtue-ethical reasoning into stage-specific enforcement mechanisms across the […]

Ver mais

For linear partial differential equations with known fundamental solutions, this work introduces a novel operator learning framework that relies exclusively on domain boundary data, including solution values and normal derivatives, rather than full-domain sampling. By integrating the previously developed Mathematical Artificial Data (MAD) method, which enforces physical consistency, all training data are synthesized directly from the fundamental solutions of the target problems, resulting in a fully data-driven pipeline without the need for external measurements or numerical simulations. We […]

Ver mais