Search

In this study, we develop and assess new corpus selection and training methodologies to improve the effectiveness of Turkish language models. Specifically, we adapted Large Language Model generated datasets and translated English datasets into Turkish, integrating these resources into the training process. This approach led to substantial enhancements in model accuracy for both few-shot and zero-shot learning scenarios. Furthermore, the merging of these adapted models was found to markedly improve their performance. Human evaluative metrics, including task-specific performance assessments, further demonstrated that these adapted models possess a greater aptitude for comprehending the Turkish language and addressing logic-based queries. This research underscores the importance of refining corpus selection strategies to optimize the performance of multilingual models, particularly for under-resourced languages like Turkish., Comment: 2024 Innovations in Intelligent Systems and Applications Conference (ASYU)

In this study, a Turkish visual instruction model was developed and various model architectures and dataset combinations were analysed to improve the performance of this model. The Cosmos-LLaVA model, which is built by combining different large language models and image coders, is designed to overcome the deficiencies in the Turkish language. In the experiments, the effects of fine-tuning with various datasets on the model performance are analysed in detail. The results show that model architecture and dataset selection have a significant impact on performance. Bu \c{c}al{\i}\c{s}mada bir T\"urk\c{c}e g\"orsel talimat modeli geli\c{s}tirilerek bu modelin performans{\i}n{\i} art{\i}rmaya y\"onelik \c{c}e\c{s}itli model mimarileri ve veri k\"umesi kombinasyonlar{\i} derinlemesine incelenmi\c{s}tir. Farkl{\i} b\"uy\"uk dil modelleri ve g\"or\"unt\"u kodlay{\i}c{\i}lar{\i}n{\i}n bir araya getirilmesiyle olu\c{s}turulan Cosmos-LLaVA modeli, T\"urk\c{c}e dilindeki eksiklikleri gidermeye y\"onelik olarak tasarlanm{\i}\c{s}t{\i}r. Yap{\i}lan deneylerde, \c{c}e\c{s}itli veri k\"umeleri ile yap{\i}lan ince ayarlar{\i}n model performans{\i}n{\i} nas{\i}l etkiledi\u{g}i detayl{\i} olarak ele al{\i}nm{\i}\c{s}t{\i}r. Sonu\c{c}lar, model mimarisi ve veri k\"umesi se\c{c}iminin performans \"uzerinde \"onemli bir etkiye sahip oldu\u{g}unu g\"ostermektedir., Comment: in Turkish language, 2024 8th International Artificial Intelligence and Data Processing Symposium (IDAP)

This paper investigates the effectiveness of BERT based models for automated punctuation and capitalization corrections in Turkish texts across five distinct model sizes. The models are designated as Tiny, Mini, Small, Medium, and Base. The design and capabilities of each model are tailored to address the specific challenges of the Turkish language, with a focus on optimizing performance while minimizing computational overhead. The study presents a systematic comparison of the performance metrics precision, recall, and F1 score of each model, offering insights into their applicability in diverse operational contexts. The results demonstrate a significant improvement in text readability and accuracy as model size increases, with the Base model achieving the highest correction precision. This research provides a comprehensive guide for selecting the appropriate model size based on specific user needs and computational resources, establishing a framework for deploying these models in real-world applications to enhance the quality of written Turkish., Comment: 2024 Innovations in Intelligent Systems and Applications Conference (ASYU)

As robotics continue to enter various sectors beyond traditional industrial applications, the need for intuitive robot training and interaction systems becomes increasingly more important. This paper introduces Robotic Augmented Reality for Machine Programming (RAMPA), a system that utilizes the capabilities of state-of-the-art and commercially available AR headsets, e.g., Meta Quest 3, to facilitate the application of Programming from Demonstration (PfD) approaches on industrial robotic arms, such as Universal Robots UR10. Our approach enables in-situ data recording, visualization, and fine-tuning of skill demonstrations directly within the user's physical environment. RAMPA addresses critical challenges of PfD, such as safety concerns, programming barriers, and the inefficiency of collecting demonstrations on the actual hardware. The performance of our system is evaluated against the traditional method of kinesthetic control in teaching three different robotic manipulation tasks and analyzed with quantitative metrics, measuring task performance and completion time, trajectory smoothness, system usability, user experience, and task load using standardized surveys. Our findings indicate a substantial advancement in how robotic tasks are taught and refined, promising improvements in operational safety, efficiency, and user engagement in robotic programming., Comment: This work has been submitted to the IEEE for possible publication

The number of open source language models that can produce Turkish is increasing day by day, as in other languages. In order to create the basic versions of such models, the training of multilingual models is usually continued with Turkish corpora. The alternative is to train the model with only Turkish corpora. In this study, we first introduce the cosmosGPT models that we created with this alternative method. Then, we introduce new finetune datasets for basic language models to fulfill user requests and new evaluation datasets for measuring the capabilities of Turkish language models. Finally, a comprehensive comparison of the adapted Turkish language models on different capabilities is presented. The results show that the language models we built with the monolingual corpus have promising performance despite being about 10 times smaller than the others.

The developments that language models have provided in fulfilling almost all kinds of tasks have attracted the attention of not only researchers but also the society and have enabled them to become products. There are commercially successful language models available. However, users may prefer open-source language models due to cost, data privacy, or regulations. Yet, despite the increasing number of these models, there is no comprehensive comparison of their performance for Turkish. This study aims to fill this gap in the literature. A comparison is made among seven selected language models based on their contextual learning and question-answering abilities. Turkish datasets for contextual learning and question-answering were prepared, and both automatic and human evaluations were conducted. The results show that for question-answering, continuing pretraining before fine-tuning with instructional datasets is more successful in adapting multilingual models to Turkish and that in-context learning performances do not much related to question-answering performances., Comment: in Turkish language. Baz{\i} \c{c}al{\i}\c{s}malar{\i} i\c{c}ermedi\u{g}ini s\"oyleyen hakem yorumu nedeniyle bir konferanstan kabul almad{\i}. Ancak hakemin bahsetti\u{g}i \c{c}al{\i}\c{s}malar bildiri g\"onderme son tarihinde yay{\i}nlanmam{\i}\c{s}t{\i}

In this work, a cell agglomeration strategy for the cut cells arising in the extended discontinuous Galerkin (XDG) method is presented. Cut cells are a fundamental aspect of unfitted mesh approaches where complex geometries or interfaces separating sub-domains are embedded into Cartesian background grids to facilitate the mesh generation process. In such methods, arbitrary small cells occur due to the intersections of background cells with embedded geometries and lead to discretization difficulties due to their diminutive sizes. Furthermore, temporal evolutions of these geometries may lead to topological changes across different time steps. Both of these issues, i.e., small-cut cells and topological changes, can be addressed with a cell agglomeration technique. In this work, a comprehensive strategy for the typical issues associated with cell agglomeration in three-dimensional and multiprocessor simulations is provided. The proposed strategy is implemented into the open-source software package BoSSS and tested with 2- and 3-dimensional simulations of immersed boundary flows., Comment: 30 pages, 19 figures

This study conducts a thorough evaluation of text augmentation techniques across a variety of datasets and natural language processing (NLP) tasks to address the lack of reliable, generalized evidence for these methods. It examines the effectiveness of these techniques in augmenting training sets to improve performance in tasks such as topic classification, sentiment analysis, and offensive language detection. The research emphasizes not only the augmentation methods, but also the strategic order in which real and augmented instances are introduced during training. A major contribution is the development and evaluation of Modified Cyclical Curriculum Learning (MCCL) for augmented datasets, which represents a novel approach in the field. Results show that specific augmentation methods, especially when integrated with MCCL, significantly outperform traditional training approaches in NLP model performance. These results underscore the need for careful selection of augmentation techniques and sequencing strategies to optimize the balance between speed and quality improvement in various NLP tasks. The study concludes that the use of augmentation methods, especially in conjunction with MCCL, leads to improved results in various classification tasks, providing a foundation for future advances in text augmentation strategies in NLP.

Foundation models have recently expanded into robotics after excelling in computer vision and natural language processing. The models are accessible in two ways: open-source or paid, closed-source options. Users with access to both face a problem when deciding between effective yet costly closed-source models and free but less powerful open-source alternatives. We call it the model selection problem. Existing supervised-learning methods are impractical due to the high cost of collecting extensive training data from closed-source models. Hence, we focus on the online learning setting where algorithms learn while collecting data, eliminating the need for large pre-collected datasets. We thus formulate a user-centric online model selection problem and propose a novel solution that combines an open-source encoder to output context and an online learning algorithm that processes this context. The encoder distills vast data distributions into low-dimensional features, i.e., the context, without additional training. The online learning algorithm aims to maximize a composite reward that includes model performance, execution time, and costs based on the context extracted from the data. It results in an improved trade-off between selecting open-source and closed-source models compared to non-contextual methods, as validated by our theoretical analysis. Experiments across language-based robotic tasks such as Waymo Open Dataset, ALFRED, and Open X-Embodiment demonstrate real-world applications of the solution. The results show that the solution significantly improves the task success rate by up to 14%.

Using large training datasets enhances the generalization capabilities of neural networks. Semi-supervised learning (SSL) is useful when there are few labeled data and a lot of unlabeled data. SSL methods that use data augmentation are most successful for image datasets. In contrast, texts do not have consistent augmentation methods as images. Consequently, methods that use augmentation are not as effective in text data as they are in image data. In this study, we compared SSL algorithms that do not require augmentation; these are self-training, co-training, tri-training, and tri-training with disagreement. In the experiments, we used 4 different text datasets for different tasks. We examined the algorithms from a variety of perspectives by asking experiment questions and suggested several improvements. Among the algorithms, tri-training with disagreement showed the closest performance to the Oracle; however, performance gap shows that new semi-supervised algorithms or improvements in existing methods are needed., Comment: Innovations in Intelligent Systems and Applications Conference (ASYU)

Data augmentation is an effective technique for improving the performance of machine learning models. However, it has not been explored as extensively in natural language processing (NLP) as it has in computer vision. In this paper, we propose a novel text augmentation method that leverages the Fill-Mask feature of the transformer-based BERT model. Our method involves iteratively masking words in a sentence and replacing them with language model predictions. We have tested our proposed method on various NLP tasks and found it to be effective in many cases. Our results are presented along with a comparison to existing augmentation methods. Experimental results show that our proposed method significantly improves performance, especially on topic classification datasets., Comment: Published in International Conference on Advanced Engineering, Technology and Applications (ICAETA 2023). The final version is available online at https://link.springer.com/chapter/10.1007/978-3-031-50920-9_35

Urban environments are characterized by complex structures and diverse features, making accurate segmentation of point cloud data a challenging task. This paper presents a comprehensive study on the application of RandLA-Net, a state-of-the-art neural network architecture, for the 3D segmentation of large-scale point cloud data in urban areas. The study focuses on three major Chinese cities, namely Chengdu, Jiaoda, and Shenzhen, leveraging their unique characteristics to enhance segmentation performance. To address the limited availability of labeled data for these specific urban areas, we employed transfer learning techniques. We transferred the learned weights from the Sensat Urban and Toronto 3D datasets to initialize our RandLA-Net model. Additionally, we performed class remapping to adapt the model to the target urban areas, ensuring accurate segmentation results. The experimental results demonstrate the effectiveness of the proposed approach achieving over 80\% F1 score for each areas in 3D point cloud segmentation. The transfer learning strategy proves to be crucial in overcoming data scarcity issues, providing a robust solution for urban point cloud analysis. The findings contribute to the advancement of point cloud segmentation methods, especially in the context of rapidly evolving Chinese urban areas.

Extracellular vesicles (EVs) and plasma membrane-derived exosome-mimetic nanovesicles demonstrate significant potential for drug delivery. Latter synthetic provides higher throughput over physiological EVs. However they face size-stability and self-agglomeration challenges in physiological solutions to be properly characterized and addressed. Here we demonstrate a fast and high-throughput nanovesicle screening methodology relying on dynamic light scattering (DLS) complemented by atomic force microscopy (AFM) measurements, suitable for the evaluation of hydrodynamic size instabilities and aggregation effects in nanovesicle solutions under varying experimental conditions and apply it to the analysis of bio-engineered nanovesicles derived from erythrocytes as well as physiological extracellular vesicles isolated from animal seminal plasma. The synthetic vesicles exhibit a significantly higher degree of agglomeration, with only 8 % of them falling within the typical extracellular vesicle size range (30-200 nm) in their original preparation conditions. Concurrent zeta potential measurements performed on both physiological and synthetic nanovesicles yielded values in the range of -17 to -22 mV, with no apparent correlation to their agglomeration tendencies. However, mild sonication and dilution were found to be effective means to restore the portion of EVs-like nanovesicles in synthetic preparations to values of 54% and 63%, respectively, The results illustrate the capability of this DLS-AFM-based analytical method for real-time, high-throughput and quantitative assessments of agglomeration effects and size instabilities in bioengineered nanovesicle solutions, providing a powerful and easy-to-use tool to gain insights to overcome such deleterious effects and leverage the full potential of this promising biocompatible drug-delivery carriers for a broad range of pharmaceutical applications.

We study the long-time behavior of solutions to the Schr\"odinger equation with a repulsive Coulomb potential on $\mathbb{R}^3$ for spherically symmetric initial data. Our approach involves computing the distorted Fourier transform of the action of the associated Hamiltonian $H=-\Delta+\frac{q}{|x|}$ on radial data $f$, which allows us to explicitly write the evolution $e^{itH}f$. A comprehensive analysis of the kernel is then used to establish that, for large times, $\|e^{i t H}f\|_{L^{\infty}} \leq C t^{-\frac{3}{2}}\|f\|_{L^1}$. Our analysis of the distorted Fourier transform is expected to have applications to other long-range repulsive problems., Comment: 60 pages