The complete list may be seen in Table 8. Here are a few general notes about these strings: 1. Based on their recommendations, we did the following: 1. zh, zh_Latn: This resulted in the special filters described below. URLs) the corpora were in languages different from the LangID predictions. This is mainly mis-rendered PDFs and may have practical applications for denoising, or for decoding such garbled PDFs.

Automatic speech recognition (ASR) has advanced in high-resource languages, but most of the world's 7,000+ languages remain unsupported, leaving thousands of long-tail languages behind. Expanding ASR coverage has been costly and limited by architectures that restrict language support, making extension inaccessible to most--all while entangled with ethical concerns when pursued without community collaboration. To transcend these limitations, we introduce Omnilingual ASR, the first large-scale ASR system designed for extensibility. Omnilingual ASR enables communities to introduce unserved languages with only a handful of data samples. It scales self-supervised pre-training to 7B parameters to learn robust speech representations and introduces an encoder-decoder architecture designed for zero-shot generalization, leveraging a LLM-inspired decoder. This capability is grounded in a massive and diverse training corpus; by combining breadth of coverage with linguistic variety, the model learns representations robust enough to adapt to unseen languages. Incorporating public resources with community-sourced recordings gathered through compensated local partnerships, Omnilingual ASR expands coverage to over 1,600 languages, the largest such effort to date--including over 500 never before served by ASR. Automatic evaluations show substantial gains over prior systems, especially in low-resource conditions, and strong generalization. We release Omnilingual ASR as a family of models, from 300M variants for low-power devices to 7B for maximum accuracy. We reflect on the ethical considerations shaping this design and conclude by discussing its societal impact. In particular, we highlight how open-sourcing models and tools can lower barriers for researchers and communities, inviting new forms of participation. Open-source artifacts are available at https://github.com/facebookresearch/omnilingual-asr.

The rapid escalation of computational requirements for training large-scale language models has reinforced structural asymmetries between high-capacity jurisdictions and countries in the Global South. This paper examines the technical and fiscal feasibility of sovereign-scale language model training in Brazil and Mexico under conditions of constrained hardware access, energy availability, and fiscal ceilings. Using a dual-axis design that varies accelerator generation (NVIDIA H100 vs. A100) and training duration (90 vs. 150 days), we estimate compute demand, energy consumption, capital expenditures, and regulatory compatibility for the training of a 10-trillion-token model. Our findings show that while all configurations remain below export-control and electrical infrastructure thresholds, fiscal viability is determined by hardware efficiency. H100-based scenarios achieve training feasibility at a total cost of 8-14 million USD, while A100 deployments require 19-32 million USD due to higher energy and hardware demand. We argue that extending training timelines should be treated as a policy lever to mitigate hardware constraints, enabling the production of usable, auditable, and locally aligned models without competing at the global frontier. This study contributes to the discourse on AI compute governance and technological sovereignty by highlighting context-sensitive strategies that allow middle-income countries to establish sustainable and strategically sufficient AI capabilities.

The complete list may be seen in Table 8. Here are a few general notes about these strings: 1. Based on their recommendations, we did the following: 1. zh, zh_Latn: This resulted in the special filters described below. URLs) the corpora were in languages different from the LangID predictions. This is mainly mis-rendered PDFs and may have practical applications for denoising, or for decoding such garbled PDFs.

Affordable desktop CNC routers are common in education, prototyping, and makerspaces, but most lack a rotary axis, limiting fabrication of rotationally symmetric or multi - sided parts. Existing solutions often require hardware retrofits, alternative control lers, or commercial CAM software, raising cost and complexity. This work presents a software - only framework for indexed rotary machining on GRBL - based CNCs. A custom post - processor converts planar toolpaths into discrete rotary steps, executed through a br owser - based interface. While not equivalent to continuous 4 - axis machining, the method enables practical rotary - axis fabrication using only standard, off - the - shelf mechanics, without firmware modification. By reducing technical and financial barriers, the framework expands access to multi - axis machining in classrooms, makerspaces, and small workshops, supporting hands - on learning and rapid prototyping.

This paper presents the analytic modeling of mobile heavy-duty manipulators with actively articulated suspension and its optimal control to maximize its static and dynamic stabilization. By adopting the screw theory formalism, we consider the suspension mechanism as a rigid multibody composed of two closed kinematic chains. This mechanical modeling allows us to compute the spatial inertial parameters of the whole platform as a function of the suspension's linear actuators through the articulated-body inertia method. Our solution enhances the computation accuracy of the wheels' reaction normal forces by providing an exact solution for the center of mass and inertia tensor of the mobile manipulator. Moreover, these inertial parameters and the normal forces are used to define metrics of both static and dynamic stability of the mobile manipulator and formulate a nonlinear programming problem that optimizes such metrics to generate an optimal stability motion that prevents the platform's overturning, such optimal position of the actuator is tracked with a state-feedback hydraulic valve control. We demonstrate our method's efficiency in terms of C++ computational speed, accuracy and performance improvement by simulating a 7 degrees-of-freedom heavy-duty parallel-serial mobile manipulator with four wheels and actively articulated suspension.

In this paper, we present a high-performance, compact electrocardiogram (ECG)-based system for automatic classification of arrhythmias, integrating machine learning approaches to achieve robust cardiac diagnostics. Our method combines a compact artificial neural network with feature enhancement techniques, including mathematical transformations, signal analysis and data extraction algorithms, to capture both morphological and time-frequency features from ECG signals. A novel aspect of this work is the addition of 17 newly engineered features, which complement the algorithm's capability to extract significant data and physiological patterns from the ECG signal. This combination enables the classifier to detect multiple arrhythmia types, such as atrial fibrillation, sinus tachycardia, ventricular flutter, and other common arrhythmic disorders. The system achieves an accuracy of 97.36% on the MIT-BIH arrhythmia database, using a lower complexity compared to state-of-the-art models. This compact tool shows potential for clinical deployment, as well as adaptation for portable devices in long-term cardiac health monitoring applications.

The lack of specialized personnel and assistive technology to assist in rehabilitation therapies is one of the challenges facing the health sector today, and it is projected to increase. For researchers and engineers, it represents an opportunity to innovate and develop devices that improve and optimize rehabilitation services for the benefit of society. Among the different types of injuries, hand injuries occur most frequently. These injuries require a rehabilitation process in order for the hand to regain its functionality. This article presents the fabrication and instrumentation of an end-effector prototype, based on a five-bar configuration, for finger rehabilitation that executes a natural flexion-extension movement. The dimensions were obtained through the gradient method optimization and evaluated through Matlab. Experimental tests were carried out to demonstrate the prototype's functionality and the effectiveness of a five-bar mechanism acting in a vertical plane, where gravity influences the mechanism's performance. Position control using fifth-order polynomials with via points was implemented in the joint space. The design of the end-effector was also evaluated by performing a theoretical comparison, calculated as a function of a real flexion-extension trajectory of the fingers and the angle of rotation obtained through an IMU. As a result, controlling the two degrees of freedom of the mechanism at several points of the trajectory assures the end-effector trajectory and therefore the fingers' range of motion, which helps for full patient recovery.

For many low-resource languages, the only available language models are large multilingual models trained on many languages simultaneously. However, using FLORES perplexity as a metric, we find that these models perform worse than bigrams for many languages (e.g. 24% of languages in XGLM 4.5B; 43% in BLOOM 7.1B). To facilitate research that focuses on low-resource languages, we pre-train and release Goldfish, a suite of monolingual autoregressive Transformer language models up to 125M parameters for 350 languages. The Goldfish reach lower FLORES perplexities than BLOOM, XGLM, and MaLA-500 on 98 of 204 FLORES languages, despite each Goldfish model being over 10x smaller. However, the Goldfish significantly underperform larger multilingual models on reasoning benchmarks, suggesting that for low-resource languages, multilinguality primarily improves general reasoning abilities rather than basic text generation. We release models trained on 5MB (350 languages), 10MB (288 languages), 100MB (166 languages), and 1GB (83 languages) of text data where available. The Goldfish models are available as baselines, fine-tuning sources, or augmentations to existing models in low-resource NLP research, and they are further useful for crosslinguistic studies requiring maximally comparable models across languages.

This thesis is a corpus-based, quantitative, and typological analysis of the functions of Early Slavic participle constructions and their finite competitors ($jegda$-'when'-clauses). The first part leverages detailed linguistic annotation on Early Slavic corpora at the morphosyntactic, dependency, information-structural, and lexical levels to obtain indirect evidence for different potential functions of participle clauses and their main finite competitor and understand the roles of compositionality and default discourse reasoning as explanations for the distribution of participle constructions and $jegda$-clauses in the corpus. The second part uses massively parallel data to analyze typological variation in how languages express the semantic space of English $when$, whose scope encompasses that of Early Slavic participle constructions and $jegda$-clauses. Probabilistic semantic maps are generated and statistical methods (including Kriging, Gaussian Mixture Modelling, precision and recall analysis) are used to induce cross-linguistically salient dimensions from the parallel corpus and to study conceptual variation within the semantic space of the hypothetical concept WHEN.