Search

Falconry, an ancient practice of training and hunting with falcons, emphasizes the need for vigilant health monitoring to ensure the well-being of these highly valued birds, especially during hunting activities. This research paper introduces a cutting-edge approach, which leverages the power of Concatenated ConvNeXt and EfficientNet AI models for falcon disease classification. Focused on distinguishing 'Normal,' 'Liver,' and 'Aspergillosis' cases, the study employs a comprehensive dataset for model training and evaluation, utilizing metrics such as accuracy, precision, recall, and f1-score. Through rigorous experimentation and evaluation, we demonstrate the superior performance of the concatenated AI model compared to traditional methods and standalone architectures. This novel approach contributes to accurate falcon disease classification, laying the groundwork for further advancements in avian veterinary AI applications., Comment: 5 pages

For a natural number $n$, denote by $B_n$ the braid group on $n$ strings and by $SM_n$ the singular braid monoid on $n$ strings. $SM_n$ is one of the most important extensions of $B_n$. In [13], Y. Mikhalchishina classified all homogeneous $2$-local representations of $B_n$ for all $n \geq 3$. In this article, we extend the result of Mikhalchishina in two ways. First, we classify all homogeneous $3$-local representations of $B_n$ for all $n \geq 4$. Second, we classify all homogeneous $2$-local representations of $SM_n$ for all $n\geq 2$ and all homogeneous $3$-local representations of $SM_n$ for all $n\geq 4$.

Emotion recognition is a critical task in human-computer interaction, enabling more intuitive and responsive systems. This study presents a multimodal emotion recognition system that combines low-level information from audio and text, leveraging both Convolutional Neural Networks (CNNs) and Bidirectional Long Short-Term Memory Networks (BiLSTMs). The proposed system consists of two parallel networks: an Audio Block and a Text Block. Mel Frequency Cepstral Coefficients (MFCCs) are extracted and processed by a BiLSTM network and a 2D convolutional network to capture low-level intrinsic and extrinsic features from speech. Simultaneously, a combined BiLSTM-CNN network extracts the low-level sequential nature of text from word embeddings corresponding to the available audio. This low-level information from speech and text is then concatenated and processed by several fully connected layers to classify the speech emotion. Experimental results demonstrate that the proposed EmoTech accurately recognizes emotions from combined audio and text inputs, achieving an overall accuracy of 84%. This solution outperforms previously proposed approaches for the same dataset and modalities.

Medical images acquired from standardized protocols show consistent macroscopic or microscopic anatomical structures, and these structures consist of composable/decomposable organs and tissues, but existing self-supervised learning (SSL) methods do not appreciate such composable/decomposable structure attributes inherent to medical images. To overcome this limitation, this paper introduces a novel SSL approach called ACE to learn anatomically consistent embedding via composition and decomposition with two key branches: (1) global consistency, capturing discriminative macro-structures via extracting global features; (2) local consistency, learning fine-grained anatomical details from composable/decomposable patch features via corresponding matrix matching. Experimental results across 6 datasets 2 backbones, evaluated in few-shot learning, fine-tuning, and property analysis, show ACE's superior robustness, transferability, and clinical potential. The innovations of our ACE lie in grid-wise image cropping, leveraging the intrinsic properties of compositionality and decompositionality of medical images, bridging the semantic gap from high-level pathologies to low-level tissue anomalies, and providing a new SSL method for medical imaging., Comment: Accepted by WACV 2025

Understanding how large language models (LLMs) grasp the historical context of concepts and their semantic evolution is essential in advancing artificial intelligence and linguistic studies. This study aims to evaluate the capabilities of various LLMs in capturing temporal dynamics of meaning, specifically how they interpret terms across different time periods. We analyze a diverse set of terms from multiple domains, using tailored prompts and measuring responses through both objective metrics (e.g., perplexity and word count) and subjective human expert evaluations. Our comparative analysis includes prominent models like ChatGPT, GPT-4, Claude, Bard, Gemini, and Llama. Findings reveal marked differences in each model's handling of historical context and semantic shifts, highlighting both strengths and limitations in temporal semantic understanding. These insights offer a foundation for refining LLMs to better address the evolving nature of language, with implications for historical text analysis, AI design, and applications in digital humanities.

The multifaceted challenge of accurately measuring gender stereotypical bias in language models is akin to discerning different segments of a broader, unseen entity. This short paper primarily focuses on intrinsic bias mitigation and measurement strategies for language models, building on prior research that demonstrates a lack of correlation between intrinsic and extrinsic approaches. We delve deeper into intrinsic measurements, identifying inconsistencies and suggesting that these benchmarks may reflect different facets of gender stereotype. Our methodology involves analyzing data distributions across datasets and integrating gender stereotype components informed by social psychology. By adjusting the distribution of two datasets, we achieve a better alignment of outcomes. Our findings underscore the complexity of gender stereotyping in language models and point to new directions for developing more refined techniques to detect and reduce bias.

Wearable, non-invasive glucose sensors capable of accurate and continuous monitoring are crucial for managing metabolic conditions yet achieving high sensitivity and stability in these devices remains challenging. In this work, we present a Black Phosphorus/Graphitic Carbon Nitride (BP/g-CN) heterostructure engineered to leverage phosphorus-nitrogen interactions for enhanced electrochemical glucose oxidation activity. Compared to pristine gCN, the BP-gCN heterostructure demonstrates a significantly improved electrochemical surface area (ECSA) and nearly two-fold reduction in charge transfer resistance (Rct), achieving remarkable glucose sensitivity of 1.1 uA mM(^-1) cm(^-2) at physiological pH. Density functional theory (DFT) calculations revealed stronger glucose adsorption and higher charge transfer on the BP-gCN heterostructure compared to pristine gCN surface. These theoretical insights complement the experimental findings, highlighting the superior electrocatalytic performance of the heterostructure and the role of oxidized BP surface. Furthermore, the BP-gCN sensor is integrated into a wearable device platform with microfluidic layers and a Near Field Communication (NFC) chip, forming a conformal skin patch that enables real-time sweat glucose monitoring. This demonstration of a high-performance, non-enzymatic wearable glucose sensor based on a heterostructure design underscores the potential of the device for seamless health management and paves the way for next generation biosensing platforms aimed at improving personalized and continuous health monitoring.

We introduce FarExStance, a new dataset for explainable stance detection in Farsi. Each instance in this dataset contains a claim, the stance of an article or social media post towards that claim, and an extractive explanation which provides evidence for the stance label. We compare the performance of a fine-tuned multilingual RoBERTa model to several large language models in zero-shot, few-shot, and parameter-efficient fine-tuned settings on our new dataset. On stance detection, the most accurate models are the fine-tuned RoBERTa model, the LLM Aya-23-8B which has been fine-tuned using parameter-efficient fine-tuning, and few-shot Claude-3.5-Sonnet. Regarding the quality of the explanations, our automatic evaluation metrics indicate that few-shot GPT-4o generates the most coherent explanations, while our human evaluation reveals that the best Overall Explanation Score (OES) belongs to few-shot Claude-3.5-Sonnet. The fine-tuned Aya-32-8B model produced explanations most closely aligned with the reference explanations., Comment: Accepted in COLING 2025

Nowadays, Natural Language Processing (NLP) is an important tool for most people's daily life routines, ranging from understanding speech, translation, named entity recognition (NER), and text categorization, to generative text models such as ChatGPT. Due to the existence of big data and consequently large corpora for widely used languages like English, Spanish, Turkish, Persian, and many more, these applications have been developed accurately. However, the Kurdish language still requires more corpora and large datasets to be included in NLP applications. This is because Kurdish has a rich linguistic structure, varied dialects, and a limited dataset, which poses unique challenges for Kurdish NLP (KNLP) application development. While several studies have been conducted in KNLP for various applications, Kurdish NER (KNER) remains a challenge for many KNLP tasks, including text analysis and classification. In this work, we address this limitation by proposing a methodology for fine-tuning the pre-trained RoBERTa model for KNER. To this end, we first create a Kurdish corpus, followed by designing a modified model architecture and implementing the training procedures. To evaluate the trained model, a set of experiments is conducted to demonstrate the performance of the KNER model using different tokenization methods and trained models. The experimental results show that fine-tuned RoBERTa with the SentencePiece tokenization method substantially improves KNER performance, achieving a 12.8% improvement in F1-score compared to traditional models, and consequently establishes a new benchmark for KNLP.

Stable distributions are a celebrated class of probability laws used in various fields. The $\alpha$-stable process, and its exponentially tempered counterpart, the Classical Tempered Stable (CTS) process, are also prominent examples of L\'evy processes. Simulating these processes is critical for many applications, yet it remains computationally challenging, due to their infinite jump activity. This survey provides an overview of the key properties of these objects offering a roadmap for practitioners. The first part is a review of the stability property, sampling algorithms are provided along with numerical illustrations. Then CTS processes are presented, with the Baeumer-Meerschaert algorithm for increment simulation, and a computational analysis is provided with numerical illustrations across different time scales., Comment: 25 pages, 6 figures

The Transformer architecture has emerged as the dominant choice for building large language models (LLMs). However, with new LLMs emerging on a frequent basis, it is important to consider the potential value of architecture-agnostic approaches that can provide interpretability across a variety of architectures. Despite recent successes in the interpretability of LLMs, many existing approaches rely on complex methods that are often tied to a specific model design and come with a significant computational cost. To address these limitations, we propose a novel technique, called NormXLogit, for assessing the significance of individual input tokens. This method operates based on the input and output representations associated with each token. First, we demonstrate that during the pre-training of LLMs, the norms of word embeddings capture the importance of input tokens. Second, we reveal a significant relationship between a token's importance and the extent to which its representation can resemble the model's final prediction. Through extensive analysis, we show that our approach consistently outperforms existing gradient-based methods in terms of faithfulness. Additionally, our method achieves better performance in layer-wise explanations compared to the most prominent architecture-specific methods.

Why do gradient-based explanations struggle with Transformers, and how can we improve them? We identify gradient flow imbalances in Transformers that violate FullGrad-completeness, a critical property for attribution faithfulness that CNNs naturally possess. To address this issue, we introduce LibraGrad -- a theoretically grounded post-hoc approach that corrects gradient imbalances through pruning and scaling of backward paths, without changing the forward pass or adding computational overhead. We evaluate LibraGrad using three metric families: Faithfulness, which quantifies prediction changes under perturbations of the most and least relevant features; Completeness Error, which measures attribution conservation relative to model outputs; and Segmentation AP, which assesses alignment with human perception. Extensive experiments across 8 architectures, 4 model sizes, and 4 datasets show that LibraGrad universally enhances gradient-based methods, outperforming existing white-box methods -- including Transformer-specific approaches -- across all metrics. We demonstrate superior qualitative results through two complementary evaluations: precise text-prompted region highlighting on CLIP models and accurate class discrimination between co-occurring animals on ImageNet-finetuned models -- two settings on which existing methods often struggle. LibraGrad is effective even on the attention-free MLP-Mixer architecture, indicating potential for extension to other modern architectures. Our code is freely available at https://github.com/NightMachinery/LibraGrad.

Continuous Integration and Continuous Delivery (CI/CD) is a well-established practice that automatically builds, tests, packages, and deploys software systems. To adopt CI/CD, software developers need to configure their projects using dedicated YML configuration files. Mobile applications have distinct characteristics when it comes to CI/CD practices, such as testing on various emulators and deploying to app stores. However, little is known about the challenges and added value of adopting CI/CD in mobile applications and how developers maintain such a practice. In this paper, we conduct an empirical study on CI/CD practices in 2,564 Android apps adopting four popular CI/CD services, namely GitHub Actions, Travis CI, CircleCI, and GitLab CI/CD. We observe a lack of commonality and standards across projects and services, leading to complex YML configurations and associated maintenance efforts. We also observe that CI/CD configurations focus primarily on the build setup, with around half of the projects performing standard testing and only 9% incorporating deployment. In addition, we find that CI/CD configurations are changed bi-monthly on average, with frequent maintenance correlating with active issue tracking, project size/age, and community engagement. Our qualitative analysis of commits uncovered 11 themes in CI/CD maintenance activities, with over a third of the changes focusing on improving workflows and fixing build issues, while another third involves updating the build environment, tools, and dependencies. Our study emphasizes the necessity for automation and AI-powered tools to improve CI/CD processes for mobile applications, and advocates for creating adaptable open-source tools to efficiently manage resources, especially in testing and deployment.

In this paper, we study the nonparametric estimation of the density $f_\Delta$ of an increment of a L\'evy process $X$ based on $n$ observations with a sampling rate $\Delta$. The class of L\'evy processes considered is broad, including both processes with a Gaussian component and pure jump processes. A key focus is on processes where $f_\Delta$ is smooth for all $\Delta$. We introduce a spectral estimator of $f_\Delta$ and derive both upper and lower bounds, showing that the estimator is minimax optimal in both low- and high-frequency regimes. Our results differ from existing work by offering weaker, easily verifiable assumptions and providing non-asymptotic results that explicitly depend on $\Delta$. In low-frequency settings, we recover parametric convergence rates, while in high-frequency settings, we identify two regimes based on whether the Gaussian or jump components dominate. The rates of convergence are closely tied to the jump activity, with continuity between the Gaussian case and more general jump processes. Additionally, we propose a fully data-driven estimator with proven simplicity and rapid implementation, supported by numerical experiments., Comment: 27 pages

The rapid evolution of Large Language Models (LLMs) offers promising potential to alleviate the global scarcity of mental health professionals. However, LLMs' alignment with essential mental health counseling competencies remains understudied. We introduce CounselingBench, a novel NCMHCE-based benchmark evaluating LLMs across five key mental health counseling competencies. Testing 22 general-purpose and medical-finetuned LLMs, we find frontier models exceed minimum thresholds but fall short of expert-level performance, with significant variations: they excel in Intake, Assessment & Diagnosis yet struggle with Core Counseling Attributes and Professional Practice & Ethics. Medical LLMs surprisingly underperform generalist models accuracy-wise, while at the same time producing slightly higher-quality justifications but making more context-related errors. Our findings highlight the complexities of developing AI systems for mental health counseling, particularly for competencies requiring empathy and contextual understanding. We found that frontier LLMs perform at a level exceeding the minimal required level of aptitude for all key mental health counseling competencies, but fall short of expert-level performance, and that current medical LLMs do not significantly improve upon generalist models in mental health counseling competencies. This underscores the critical need for specialized, mental health counseling-specific fine-tuned LLMs that rigorously aligns with core competencies combined with appropriate human supervision before any responsible real-world deployment can be considered., Comment: 9 Pages, In Submission to NAACL 2025

The availability of highly accurate urban airborne laser scanning (ALS) data will increase rapidly in the future, especially as acquisition costs decrease, for example through the use of drones. Current challenges in data processing are related to the limited spectral information and low point density of most ALS datasets. Another challenge will be the growing need for annotated training data, frequently produced by manual processes, to enable semantic interpretation of point clouds. This study proposes to semantically segment new high-density (1200 points per square metre on average) multispectral ALS data with an unsupervised ground-aware deep clustering method GroupSP inspired by the unsupervised GrowSP algorithm. GroupSP divides the scene into superpoints as a preprocessing step. The neural network is trained iteratively by grouping the superpoints and using the grouping assignments as pseudo-labels. The predictions for the unseen data are given by over-segmenting the test set and mapping the predicted classes into ground truth classes manually or with automated majority voting. GroupSP obtained an overall accuracy (oAcc) of 97% and a mean intersection over union (mIoU) of 80%. When compared to other unsupervised semantic segmentation methods, GroupSP outperformed GrowSP and non-deep K-means. However, a supervised random forest classifier outperformed GroupSP. The labelling efforts in GroupSP can be minimal; it was shown, that the GroupSP can semantically segment seven urban classes (building, high vegetation, low vegetation, asphalt, rock, football field, and gravel) with oAcc of 95% and mIoU of 75% using only 0.004% of the available annotated points in the mapping assignment. Finally, the multispectral information was examined; adding each new spectral channel improved the mIoU. Additionally, echo deviation was valuable, especially when distinguishing ground-level classes., Comment: 22 pages, 11 figures

Advances in dataset analysis techniques have enabled more sophisticated approaches to analyzing and characterizing training data instances, often categorizing data based on attributes such as ``difficulty''. In this work, we introduce RepMatch, a novel method that characterizes data through the lens of similarity. RepMatch quantifies the similarity between subsets of training instances by comparing the knowledge encoded in models trained on them, overcoming the limitations of existing analysis methods that focus solely on individual instances and are restricted to within-dataset analysis. Our framework allows for a broader evaluation, enabling similarity comparisons across arbitrary subsets of instances, supporting both dataset-to-dataset and instance-to-dataset analyses. We validate the effectiveness of RepMatch across multiple NLP tasks, datasets, and models. Through extensive experimentation, we demonstrate that RepMatch can effectively compare datasets, identify more representative subsets of a dataset (that lead to better performance than randomly selected subsets of equivalent size), and uncover heuristics underlying the construction of some challenge datasets.

AA is the process of attributing an unidentified document to its true author from a predefined group of known candidates, each possessing multiple samples. The nature of AA necessitates accommodating emerging new authors, as each individual must be considered unique. This uniqueness can be attributed to various factors, including their stylistic preferences, areas of expertise, gender, cultural background, and other personal characteristics that influence their writing. These diverse attributes contribute to the distinctiveness of each author, making it essential for AA systems to recognize and account for these variations. However, current AA benchmarks commonly overlook this uniqueness and frame the problem as a closed-world classification, assuming a fixed number of authors throughout the system's lifespan and neglecting the inclusion of emerging new authors. This oversight renders the majority of existing approaches ineffective for real-world applications of AA, where continuous learning is essential. These inefficiencies manifest as current models either resist learning new authors or experience catastrophic forgetting, where the introduction of new data causes the models to lose previously acquired knowledge. To address these inefficiencies, we propose redefining AA as CIL, where new authors are introduced incrementally after the initial training phase, allowing the system to adapt and learn continuously. To achieve this, we briefly examine subsequent CIL approaches introduced in other domains. Moreover, we have adopted several well-known CIL methods, along with an examination of their strengths and weaknesses in the context of AA. Additionally, we outline potential future directions for advancing CIL AA systems. As a result, our paper can serve as a starting point for evolving AA systems from closed-world models to continual learning through CIL paradigms., Comment: Submitted to IEEE CogMI 2024 Conference

Many real-world networks are characterized by directionality; however, the absence of an appropriate Fourier basis hinders the effective implementation of graph signal processing techniques. Inspired by discrete signal processing, where embedding a line digraph into a cycle digraph facilitates the powerful Discrete Fourier Transform for signal analysis, addressing the structural complexities of general digraphs can help overcome the limitations of the Graph Fourier Transform (GFT) and unlock its potential. The Discrete Fourier Transform (DFT) serves as a Graph Fourier Transform for both cycle graphs and Cayley digraphs on the finite cyclic groups $\mathbb{Z}_N$. We propose a systematic method to identify a class of such Cayley digraphs that can encompass a given directed graph. By embedding the directed graph into these Cayley digraphs and opting for envelope extensions that naturally support the Graph Fourier Transform, the GFT functionalities of these extensions can be harnessed for signal analysis. Among the potential envelopes, optimal performance is achieved by selecting one that meets key properties. This envelope's structure closely aligns with the characteristics of the original digraph. The Graph Fourier Transform of this envelope is reliable in terms of numerical stability, and its columns approximately form an eigenbasis for the adjacency matrix associated with the original digraph. It is shown that the envelope extensions possess a convolution product, with their GFT fulfilling the convolution theorem. Additionally, shift-invariant graph filters (systems) are described as the convolution operator, analogous to the classical case. This allows the utilization of systems for signal analysis., Comment: 14 pages, 16 figures, 3 tables

This paper introduces a pioneering English-Azerbaijani (Arabic Script) parallel corpus, designed to bridge the technological gap in language learning and machine translation (MT) for under-resourced languages. Consisting of 548,000 parallel sentences and approximately 9 million words per language, this dataset is derived from diverse sources such as news articles and holy texts, aiming to enhance natural language processing (NLP) applications and language education technology. This corpus marks a significant step forward in the realm of linguistic resources, particularly for Turkic languages, which have lagged in the neural machine translation (NMT) revolution. By presenting the first comprehensive case study for the English-Azerbaijani (Arabic Script) language pair, this work underscores the transformative potential of NMT in low-resource contexts. The development and utilization of this corpus not only facilitate the advancement of machine translation systems tailored for specific linguistic needs but also promote inclusive language learning through technology. The findings demonstrate the corpus's effectiveness in training deep learning MT systems and underscore its role as an essential asset for researchers and educators aiming to foster bilingual education and multilingual communication. This research covers the way for future explorations into NMT applications for languages lacking substantial digital resources, thereby enhancing global language education frameworks. The Python package of our code is available at https://pypi.org/project/chevir-kartalol/, and we also have a website accessible at https://translate.kartalol.com/., Comment: This paper is accepted and published at NeTTT 2024 Conf

Automatic cell tracking in dense environments is plagued by inaccurate correspondences and misidentification of parent-offspring relationships. In this paper, we introduce a novel cell tracking algorithm named DenseTrack, which integrates deep learning with mathematical model-based strategies to effectively establish correspondences between consecutive frames and detect cell division events in crowded scenarios. We formulate the cell tracking problem as a deep learning-based temporal sequence classification task followed by solving a constrained one-to-one matching optimization problem exploiting the classifier's confidence scores. Additionally, we present an eigendecomposition-based cell division detection strategy that leverages knowledge of cellular geometry. The performance of the proposed approach has been evaluated by tracking densely packed cells in 3D time-lapse image sequences of bacterial biofilm development. The experimental results on simulated as well as experimental fluorescence image sequences suggest that the proposed tracking method achieves superior performance in terms of both qualitative and quantitative evaluation measures compared to recent state-of-the-art cell tracking approaches.

Since their inception, superconducting nanowire single-photon detectors have been enabling quantum optical applications and the rise of the photonic quantum industry. The evolution in the detector design and read-out strategies has led to the introduction of devices with a plurality of independent pixels, which have been able to operate with high system detection efficiency at high speed while also supporting photon number resolution capabilities. However, this comes at the cost of a complex readout that requires one coaxial cable for each pixel of the array. Here, we report a 28-pixel SNSPD with a dedicated parallel architecture that, while maintaining a simple readout with a single coaxial line, enables the detector to operate at high speed with low-performance degradation. The device shows a maximum single-photon efficiency of 88% and is able to maintain its efficiency above 50%, coupled with a timing jitter lower than 80 ps, up to a detection rate of 200 million counts per second. The detector also provides state-of-the-art photon-number-resolving performances with a 2-photon efficiency of 75% and a 3-photon efficiency of 62%.

Large language models (LLMs) often lack culture-specific knowledge of daily life, especially across diverse regions and non-English languages. Existing benchmarks for evaluating LLMs' cultural sensitivities are limited to a single language or collected from online sources such as Wikipedia, which do not reflect the mundane everyday lifestyles of diverse regions. That is, information about the food people eat for their birthday celebrations, spices they typically use, musical instruments youngsters play, or the sports they practice in school is common cultural knowledge but uncommon in easily collected online sources, especially for underrepresented cultures. To address this issue, we introduce BLEnD, a hand-crafted benchmark designed to evaluate LLMs' everyday knowledge across diverse cultures and languages. BLEnD comprises 52.6k question-answer pairs from 16 countries/regions, in 13 different languages, including low-resource ones such as Amharic, Assamese, Azerbaijani, Hausa, and Sundanese. We construct the benchmark to include two formats of questions: short-answer and multiple-choice. We show that LLMs perform better for cultures that are highly represented online, with a maximum 57.34% difference in GPT-4, the best-performing model, in the short-answer format. For cultures represented by mid-to-high-resource languages, LLMs perform better in their local languages, but for cultures represented by low-resource languages, LLMs perform better in English than the local languages. We make our dataset publicly available at: https://github.com/nlee0212/BLEnD., Comment: Accepted to NeurIPS 2024 Datasets & Benchmark Track