arXiv:2602.11160v1 Announce Type: new Abstract: Lack of data is a recurring problem in Artificial Intelligence, as it is essential for training and validating models. This is particularly true in the field of cultural heritage, where the number of open datasets is relatively limited and where the data collected does not always allow for holistic modeling of visitors’ experience due to the fact that data are ad hoc (i.e. restricted to the sole characteristics required for the evaluation of […]

Ver mais

In many scientific and data-driven applications, machine learning models are increasingly used as measurement instruments, rather than merely as predictors of predefined labels. When the measurement function is learned from data, the mapping from observations to quantities is determined implicitly by the training distribution and inductive biases, allowing multiple inequivalent mappings to satisfy standard predictive evaluation criteria. We formalize learned measurement functions as a distinct focus of evaluation and introduce measurement stability, a property capturing invariance of the […]

Ver mais

arXiv:2602.21701v1 Announce Type: cross Abstract: A central challenge in scientific machine learning (ML) is the correct representation of physical systems governed by multi-regime behaviours. In these scenarios, standard data analysis techniques often fail to capture the nature of the data, as the system’s response varies significantly across the state space due to its stochasticity and the different physical regimes. Uncertainty quantification (UQ) should thus not be viewed merely as a safety assessment, but as a support to the […]

Ver mais

In this work, we present OCLADS, a novel communication framework with continual learning (CL) for Internet of Things (IoT) anomaly detection (AD) when operating in non-stationary environments. As the statistical properties of the observed data change with time, the on-device inference model becomes obsolete, which necessitates strategic model updating. OCLADS keeps track of data distribution shifts to timely update the on-device IoT AD model. To do so, OCLADS introduces two mechanisms during the interaction between the resource-constrained IoT […]

Ver mais

Key Highlights – Sam Altman led OpenAI has more often than not been in a rather grim light with incidents regarding ChatGPT’s alleged contribution in teen suicide and mental health. While the AI company has rolled out updates to ensure that the chatbot avoid repeating these, it has recently added a new feature which will predict users’ age and impose ‘extra safety settings.’ How Does ChatGPT’s Age Prediction Feature Really Work All users are required to submit their […]

Ver mais

Machine unlearning aims to remove the influence of specific training data from a learned model without full retraining. While recent work has begun to explore unlearning in quantum machine learning, existing approaches largely rely on fixed, uniform target distributions and do not explicitly control the trade-off between forgetting and retained model behaviour. In this work, we propose a distribution-guided framework for class-level quantum machine unlearning that treats unlearning as a constrained optimization problem. Our method introduces a tunable […]

Ver mais

arXiv:2601.15498v1 Announce Type: new Abstract: Speculative Decoding (SD) accelerates autoregressive large language model (LLM) inference by decoupling generation and verification. While recent methods improve draft quality by tightly coupling the drafter with the target model, the verification mechanism itself remains largely unchanged, relying on strict token-level rejection sampling. In practice, modern LLMs frequently operate in low-margin regimes where the target model exhibits weak preference among top candidates. In such cases, rejecting plausible runner-up tokens yields negligible information gain […]

Ver mais

arXiv:2602.11246v1 Announce Type: new Abstract: We introduce a mathematical framework for the linear representation hypothesis (LRH), which asserts that intermediate layers of language models store features linearly. We separate the hypothesis into two claims: linear representation (features are linearly embedded in neuron activations) and linear accessibility (features can be linearly decoded). We then ask: How many neurons $d$ suffice to both linearly represent and linearly access $m$ features? Classical results in compressed sensing imply that for $k$-sparse inputs, […]

Ver mais

Modern marketing faces a subtle but significant challenge. Not a lack of tools. Not a lack of ideas. But a lack of memory. Campaigns are launched, data is collected, and insights are discussed, but are often forgotten. Teams move on, repeat mistakes, and relearn lessons that have already been addressed. This is where the concept of a second brain becomes valuable. It serves not as a productivity gimmick, but as a fundamental improvement to marketing decision-making. With AI […]

Ver mais