CybAI news

arXiv:2411.13716v1 Announce Type: new Abstract: Gait analysis using computer vision is an emerging field in AI, offering clinicians an objective, multi-feature approach to analyse complex movements. Despite its promise, current applications using RGB video data alone are limited in measuring clinically relevant spatial and temporal kinematics and establishing normative parameters essential for identifying movement abnormalities within a gait cycle. This paper presents a data-driven method using RGB video data and 2D human pose estimation for developing normative kinematic gait parameters. By analysing joint angles, an established kinematic measure in biomechanics and clinical practice, we aim to enhance gait analysis capabilities…

[Submitted on 9 Oct 2022 (v1), last revised 21 Nov 2024 (this version, v3)] View a PDF of the paper titled Fine-Grained Detection of Solidarity for Women and Migrants in 155 Years of German Parliamentary Debates, by Aida Kostikova and 5 other authors View PDF HTML (experimental) Abstract:Solidarity is a crucial concept to understand social relations in societies. In this paper, we explore fine-grained solidarity frames to study solidarity towards women and migrants in German parliamentary debates between 1867 and 2022. Using 2,864 manually annotated text snippets (with a cost exceeding 18k Euro), we evaluate large language models (LLMs) like…

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Source link lol

[Submitted on 20 Nov 2024 (v1), last revised 21 Nov 2024 (this version, v2)] View a PDF of the paper titled Pushing the Limits of Sparsity: A Bag of Tricks for Extreme Pruning, by Andy Li and 3 other authors View PDF HTML (experimental) Abstract:Pruning of deep neural networks has been an effective technique for reducing model size while preserving most of the performance of dense networks, crucial for deploying models on memory and power-constrained devices. While recent sparse learning methods have shown promising performance up to moderate sparsity levels such as 95% and 98%, accuracy quickly deteriorates when pushing…

arXiv:2411.14258v1 Announce Type: new Abstract: Large Language Models (LLMs) have revolutionized Natural Language Processing (NLP) based applications including automated text generation, question answering, chatbots, and others. However, they face a significant challenge: hallucinations, where models produce plausible-sounding but factually incorrect responses. This undermines trust and limits the applicability of LLMs in different domains. Knowledge Graphs (KGs), on the other hand, provide a structured collection of interconnected facts represented as entities (nodes) and their relationships (edges). In recent research, KGs have been leveraged to provide context that can fill gaps in an LLM understanding of certain topics offering a promising approach…

[Submitted on 24 Jan 2024 (v1), last revised 21 Nov 2024 (this version, v3)] View a PDF of the paper titled Uncertainty-Guided Alignment for Unsupervised Domain Adaptation in Regression, by Ismail Nejjar and 3 other authors View PDF HTML (experimental) Abstract:Unsupervised Domain Adaptation for Regression (UDAR) aims to adapt models from a labeled source domain to an unlabeled target domain for regression tasks. Traditional feature alignment methods, successful in classification, often prove ineffective for regression due to the correlated nature of regression features. To address this challenge, we propose Uncertainty-Guided Alignment (UGA), a novel method that integrates predictive uncertainty into…