在计算和数据方面，大型语言模型的预培训通常需要大量资源。经常使用的Web源（例如Common Crawl）可能包含足够的噪声，以使这种预训练的亚地区。在这项工作中，我们尝试了西班牙语版本的MC4的不同采样方法，并提出了一种新颖的以数据为中心的技术，我们将其命名为$ \ textit {Perplexity sampling} $，该技术可实现大约一半的语言模型的预培训步骤并使用五分之一的数据。最终的模型与当前的最新机构相当，甚至可以为某些任务获得更好的结果。我们的工作证明了变形金刚的多功能性，并为小型团队以有限的预算培训模型铺平了道路。我们的型号可在此$ \ href {https://huggingface.co/bertin-project} {url} $中获得。

我们介绍了一种确定全局特征解耦的方法，并显示其适用于提高数据分析性能的适用性，并开放了新的场所以进行功能传输。我们提出了一种新的形式主义，该形式主义是基于沿特征梯度遵循轨迹来定义对子曼群的转换的。通过这些转换，我们定义了一个归一化，我们证明，它允许解耦可区分的特征。通过将其应用于采样矩，我们获得了用于正骨的准分析溶液，正尾肌肉是峰度的归一化版本，不仅与平均值和方差相关，而且还与偏度相关。我们将此方法应用于原始数据域和过滤器库的输出中，以基于全局描述符的回归和分类问题，与使用经典（未删除）描述符相比，性能得到一致且显着的改进。

贝叶斯正交（BQ）是一种基于型号的数值集成方法，可以通过编码和利用手头的集成任务的已知结构来提高样本效率。在本文中，我们探讨了在输入域中的一组基本变换下编码积分的不变性，特别是一些酉变换，例如旋转，轴翻转或点对称。与若干合成和一个现实世界应用相比，我们展示了卓越的性能的初步结果。

目的：要开发CADIA，一种基于区域提案网络的监督深度学习模型，耦合具有针对计算机断层造影（CTA）颅内动脉瘤（IA）的假阳性减少模块，并评估我们的模型的性能到类似的检测网络。方法：在此回顾性研究中，我们评估了来自两种独立的疾病患者的两种单独的患者患者的囊性IA> = 2.5mm。实施了两步模型：用于初始动脉瘤检测的3D区域提案网络，以及3D DENSENETSFOR虚假阳性降低以及对可疑IA的进一步确定。还进行了自由响应接收器操作特征（FROC）曲线和患者级性能，在既定的假每体积（FPPV）时呈现出误报。 Fisher的确切测试用于与类似的可用模型进行比较。结果：0.25和1 FPPV的Cadia的敏感性分别为63.9％和77.5％。我们的模型的性能随着尺寸和位置而变化，最佳性能是在5-10毫米和前沟通动脉的含量，敏感性分别为95.8％和94％的敏感性。与0.25 FPPV的可用型号相比，我们的模型显示出统计学上更高的患者级精度，灵敏度和特异性。在1 FPPV阈值下，我们的模型显示出更好的准确性和特异性（P <= 0.001）和等效灵敏度。结论：CADIA在IA的检测任务中表现出可比网络。添加假阳性还原模块是改善IA检测模型的可行步骤。

Neural network pruning-the task of reducing the size of a network by removing parameters-has been the subject of a great deal of work in recent years. We provide a meta-analysis of the literature, including an overview of approaches to pruning and consistent findings in the literature. After aggregating results across 81 papers and pruning hundreds of models in controlled conditions, our clearest finding is that the community suffers from a lack of standardized benchmarks and metrics. This deficiency is substantial enough that it is hard to compare pruning techniques to one another or determine how much progress the field has made over the past three decades. To address this situation, we identify issues with current practices, suggest concrete remedies, and introduce ShrinkBench, an open-source framework to facilitate standardized evaluations of pruning methods. We use ShrinkBench to compare various pruning techniques and show that its comprehensive evaluation can prevent common pitfalls when comparing pruning methods.

Modelling and forecasting real-life human behaviour using online social media is an active endeavour of interest in politics, government, academia, and industry. Since its creation in 2006, Twitter has been proposed as a potential laboratory that could be used to gauge and predict social behaviour. During the last decade, the user base of Twitter has been growing and becoming more representative of the general population. Here we analyse this user base in the context of the 2021 Mexican Legislative Election. To do so, we use a dataset of 15 million election-related tweets in the six months preceding election day. We explore different election models that assign political preference to either the ruling parties or the opposition. We find that models using data with geographical attributes determine the results of the election with better precision and accuracy than conventional polling methods. These results demonstrate that analysis of public online data can outperform conventional polling methods, and that political analysis and general forecasting would likely benefit from incorporating such data in the immediate future. Moreover, the same Twitter dataset with geographical attributes is positively correlated with results from official census data on population and internet usage in Mexico. These findings suggest that we have reached a period in time when online activity, appropriately curated, can provide an accurate representation of offline behaviour.

Content moderation is the process of screening and monitoring user-generated content online. It plays a crucial role in stopping content resulting from unacceptable behaviors such as hate speech, harassment, violence against specific groups, terrorism, racism, xenophobia, homophobia, or misogyny, to mention some few, in Online Social Platforms. These platforms make use of a plethora of tools to detect and manage malicious information; however, malicious actors also improve their skills, developing strategies to surpass these barriers and continuing to spread misleading information. Twisting and camouflaging keywords are among the most used techniques to evade platform content moderation systems. In response to this recent ongoing issue, this paper presents an innovative approach to address this linguistic trend in social networks through the simulation of different content evasion techniques and a multilingual Transformer model for content evasion detection. In this way, we share with the rest of the scientific community a multilingual public tool, named "pyleetspeak" to generate/simulate in a customizable way the phenomenon of content evasion through automatic word camouflage and a multilingual Named-Entity Recognition (NER) Transformer-based model tuned for its recognition and detection. The multilingual NER model is evaluated in different textual scenarios, detecting different types and mixtures of camouflage techniques, achieving an overall weighted F1 score of 0.8795. This article contributes significantly to countering malicious information by developing multilingual tools to simulate and detect new methods of evasion of content on social networks, making the fight against information disorders more effective.

In this paper, we present an evolved version of the Situational Graphs, which jointly models in a single optimizable factor graph, a SLAM graph, as a set of robot keyframes, containing its associated measurements and robot poses, and a 3D scene graph, as a high-level representation of the environment that encodes its different geometric elements with semantic attributes and the relational information between those elements. Our proposed S-Graphs+ is a novel four-layered factor graph that includes: (1) a keyframes layer with robot pose estimates, (2) a walls layer representing wall surfaces, (3) a rooms layer encompassing sets of wall planes, and (4) a floors layer gathering the rooms within a given floor level. The above graph is optimized in real-time to obtain a robust and accurate estimate of the robot's pose and its map, simultaneously constructing and leveraging the high-level information of the environment. To extract such high-level information, we present novel room and floor segmentation algorithms utilizing the mapped wall planes and free-space clusters. We tested S-Graphs+ on multiple datasets including, simulations of distinct indoor environments, on real datasets captured over several construction sites and office environments, and on a real public dataset of indoor office environments. S-Graphs+ outperforms relevant baselines in the majority of the datasets while extending the robot situational awareness by a four-layered scene model. Moreover, we make the algorithm available as a docker file.

There has been significant work recently in developing machine learning models in high energy physics (HEP), for tasks such as classification, simulation, and anomaly detection. Typically, these models are adapted from those designed for datasets in computer vision or natural language processing without necessarily incorporating inductive biases suited to HEP data, such as respecting its inherent symmetries. Such inductive biases can make the model more performant and interpretable, and reduce the amount of training data needed. To that end, we develop the Lorentz group autoencoder (LGAE), an autoencoder model equivariant with respect to the proper, orthochronous Lorentz group $\mathrm{SO}^+(3,1)$, with a latent space living in the representations of the group. We present our architecture and several experimental results on jets at the LHC and find it significantly outperforms a non-Lorentz-equivariant graph neural network baseline on compression and reconstruction, and anomaly detection. We also demonstrate the advantage of such an equivariant model in analyzing the latent space of the autoencoder, which can have a significant impact on the explainability of anomalies found by such black-box machine learning models.

System identification, also known as learning forward models, transfer functions, system dynamics, etc., has a long tradition both in science and engineering in different fields. Particularly, it is a recurring theme in Reinforcement Learning research, where forward models approximate the state transition function of a Markov Decision Process by learning a mapping function from current state and action to the next state. This problem is commonly defined as a Supervised Learning problem in a direct way. This common approach faces several difficulties due to the inherent complexities of the dynamics to learn, for example, delayed effects, high non-linearity, non-stationarity, partial observability and, more important, error accumulation when using bootstrapped predictions (predictions based on past predictions), over large time horizons. Here we explore the use of Reinforcement Learning in this problem. We elaborate on why and how this problem fits naturally and sound as a Reinforcement Learning problem, and present some experimental results that demonstrate RL is a promising technique to solve these kind of problems.