Systematic literature reviews (SLRs) are fundamental to evidence-based research, but manual screening is an increasing bottleneck as scientific output grows. Screening features low prevalence of relevant studies and scarce, costly expert decisions. Traditional active learning (AL) systems help, yet typically rely on fixed query strategies for selecting the next unlabeled documents. These static strategies do not adapt over time and ignore the relational structure of scientific literature networks. This thesis introduces AutoDiscover, a framework that reframes AL as […]

Ver mais

arXiv:2601.16403v1 Announce Type: new Abstract: Reinforcement Learning from Human Feedback (RLHF) and its variants have emerged as the dominant approaches for aligning Large Language Models with human intent. While empirically effective, the theoretical generalization properties of these methods in high-dimensional settings remain to be explored. To this end, we build the generalization theory on RLHF of LLMs under the linear reward model, through the framework of algorithmic stability. In contrast to the existing works built upon the consistency […]

Ver mais

arXiv:2601.00065v1 Announce Type: new Abstract: The open-weight LLM ecosystem is increasingly defined by model composition techniques (such as weight merging, speculative decoding, and vocabulary expansion) that remix capabilities from diverse sources. A critical prerequisite for applying these methods across different model families is tokenizer transplant, which aligns incompatible vocabularies to a shared embedding space. We demonstrate that this essential interoperability step introduces a supply-chain vulnerability: we engineer a single “breaker token” that is functionally inert in a donor […]

Ver mais

Maia 200 is Microsoft’s new in house AI accelerator designed for inference in Azure datacenters. It targets the cost of token generation for large language models and other reasoning workloads by combining narrow precision compute, a dense on chip memory hierarchy and an Ethernet based scale up fabric. Why Microsoft built a dedicated inference chip? Training and inference stress hardware in different ways. Training needs very large all to all communication and long running jobs. Inference cares about […]

Ver mais

Background: Sensor-based systems and virtual reality (VR) technologies provide new opportunities for the objective, technology-driven assessment and training of visuo-motor performance in applied contexts such as sport. Methods: This study examined the effects of an integrated visual training program combining stroboscopic stimula-tion, VR-based vergence exercises, and instrumented reaction-light tasks in adolescent handball players. Twenty-eight youth athletes completed two baseline assessments separated by six weeks, followed by a six-session training program integrated into reg-ular team practice. Sensor-derived outcome measures […]

Ver mais

Self-supervised pre-training with contrastive learning is a powerful method for learning from sparsely labeled data. However, performance can drop considerably when there is a shift in the distribution of data from training to test time. We study this phenomenon in a setting in which the training data come from multiple domains, and the test data come from a domain not seen at training that is subject to significant covariate shift. We present a new method for contrastive learning […]

Ver mais

This study develops a fairness-calibrated credit-scoring method that combines counterfactual perturbation with group-wise regularization. Using 3.1 million credit files with demographic annotations, the model evaluates whether score outputs remain stable when protected attributes are perturbed in a causal graph. A fairness-adjusted gradient-boosting model is then trained with penalties on group-level prediction disparities. The final model reduces demographic disparity in predicted default probability from 0.112 to 0.034 while maintaining an ROC-AUC of 0.89. Counterfactual-stability checks show that 94.6% of […]

Ver mais

arXiv:2601.20528v1 Announce Type: cross Abstract: We develop a fully intrinsic Bayesian framework for nonparametric regression on the unit sphere based on isotropic Gaussian field priors and the harmonic structure induced by the Laplace-Beltrami operator. Under uniform random design, the regression model admits an exact diagonalization in the spherical harmonic basis, yielding a Gaussian sequence representation with frequency-dependent multiplicities. Exploiting this structure, we derive closed-form posterior distributions, optimal spectral truncation schemes, and sharp posterior contraction rates under integrated squared […]

Ver mais

arXiv:2602.00912v1 Announce Type: new Abstract: Recent initiatives advocating responsible, transparent research assessment have intensified the call to use open research information rather than proprietary databases. This study evaluates the coverage and citation representation of publications recorded in the Current Research Information Systems (CRIS), all instances of the IRIS software platform, of six Italian universities within OpenCitations, a community-owned open infrastructure. Using persistent identifiers (DOIs, PMIDs, and ISBNs) specified in the IRIS installations involved, we matched the publications recorded […]

Ver mais

In this paper, we develop a novel online algorithm based on the Sequential Monte Carlo(SMC) samplers framework for posterior inference in Dirichlet Process Mixtures (DPM). Our method generalizes many sequential importance sampling approaches. It provides a computationally efficient improvement to particle filtering that is less prone to getting stuck in isolated modes. The proposed method is a particular SMC sampler that enables us to design sophisticated clustering update schemes, such as updating past trajectories of the particles in […]

Ver mais