Viral News

arXiv:2408.05285v1 Announce Type: new Abstract: One-shot Imitation Learning~(OSIL) aims to imbue AI agents with the ability to learn a new task from a single demonstration. To supervise the learning, OSIL typically requires a prohibitively large number of paired expert demonstrations -- i.e. trajectories corresponding to different variations of the same semantic task. To overcome this limitation, we introduce the semi-supervised OSIL problem setting, where the learning agent is presented with a large dataset of trajectories with no task labels (i.e. an unpaired dataset), along with a small dataset of multiple demonstrations per semantic task (i.e. a paired dataset). This presents…

arXiv:2408.05364v1 Announce Type: new Abstract: Egocentric videos provide comprehensive contexts for user and scene understanding, spanning multisensory perception to behavioral interaction. We propose Spherical World-Locking (SWL) as a general framework for egocentric scene representation, which implicitly transforms multisensory streams with respect to measurements of head orientation. Compared to conventional head-locked egocentric representations with a 2D planar field-of-view, SWL effectively offsets challenges posed by self-motion, allowing for improved spatial synchronization between input modalities. Using a set of multisensory embeddings on a worldlocked sphere, we design a unified encoder-decoder transformer architecture that preserves the spherical structure of the scene representation, without requiring…

[Submitted on 9 Aug 2024] View a PDF of the paper titled FiST-Financial Style Transfer with Hallucination and Creativity Control Framework, by Sohini Roychowdhury and 5 other authors View PDF HTML (experimental) Abstract:Financial report generation using general purpose large language models pose two major challenges, including the lack of compound sentences and hallucinations. Advanced prompt engineering and retrieval augmented generation (RAG) techniques are incapable of curing the writing style discrepancies. In this work we propose a novel two-stage fine-tuning process wherein public domain financial reports are processed into prompt-completions and augmented using simple LLM prompts to then enable sectional financial…

This website uses Google Analytics to collect anonymous information such as the number of visitors to the site, and the most popular pages. Keeping this cookie enabled helps us to improve our website. Please enable Strictly Necessary Cookies first so that we can save your preferences! Source link lol

arXiv:2408.05249v1 Announce Type: new Abstract: Federated Learning (FL) has emerged as a promising solution to address the limitations of centralised machine learning (ML) in oncology, particularly in overcoming privacy concerns and harnessing the power of diverse, multi-center data. This systematic review synthesises current knowledge on the state-of-the-art FL in oncology, focusing on breast, lung, and prostate cancer. Distinct from previous surveys, our comprehensive review critically evaluates the real-world implementation and impact of FL on cancer care, demonstrating its effectiveness in enhancing ML generalisability, performance and data privacy in clinical settings and data. We evaluated state-of-the-art advances in FL, demonstrating its…

arXiv:2408.05363v1 Announce Type: new Abstract: Object detection on the edge (Edge-OD) is in growing demand thanks to its ever-broad application prospects. However, the development of this field is rigorously restricted by the deployment dilemma of simultaneously achieving high accuracy, excellent power efficiency, and meeting strict real-time requirements. To tackle this dilemma, we propose AyE-Edge, the first-of-this-kind development tool that explores automated algorithm-device deployment space search to realize Accurate yet power-Efficient real-time object detection on the Edge. Through a collaborative exploration of keyframe selection, CPU-GPU configuration, and DNN pruning strategy, AyE-Edge excels in extensive real-world experiments conducted on a mobile device.…

[Submitted on 9 Aug 2024] View a PDF of the paper titled DataNarrative: Automated Data-Driven Storytelling with Visualizations and Texts, by Mohammed Saidul Islam and 4 other authors View PDF HTML (experimental) Abstract:Data-driven storytelling is a powerful method for conveying insights by combining narrative techniques with visualizations and text. These stories integrate visual aids, such as highlighted bars and lines in charts, along with textual annotations explaining insights. However, creating such stories requires a deep understanding of the data and meticulous narrative planning, often necessitating human intervention, which can be time-consuming and mentally taxing. While Large Language Models (LLMs) excel…

While the ongoing generative AI boom has captivated countless industries worldwide, it's actually machine learning (ML) that stands to have a major impact on recruitment over the coming years. The global ML market is expected to reach a value of $209.91 billion by 2029, representing a CAGR of 38.8%. This swift rate of growth will bring a hatful of benefits to digital transformation throughout the recruitment landscape. Machine learning can use its experiences to make recruitment more accurate and efficient without further programming. Instead, the technology learns from data like text, images, or numbers. You've probably already witnessed ML in…

arXiv:2408.05245v1 Announce Type: new Abstract: This paper explores an improved Adaboost algorithm based on Long Short-Term Memory Networks (LSTMs), which aims to improve the prediction accuracy of user clicks on web page advertisements. By comparing it with several common machine learning algorithms, the paper analyses the advantages of the new model in ad click prediction. It is shown that the improved algorithm proposed in this paper performs well in user ad click prediction with an accuracy of 92%, which is an improvement of 13.6% compared to the highest of 78.4% among the other three base models. This significant improvement indicates…

arXiv:2408.05350v1 Announce Type: new Abstract: In order to assess damage and properly allocate relief efforts, mapping the extent of flood events is a necessary and important aspect of disaster management. In recent years, deep learning methods have evolved as an effective tool to quickly label high-resolution imagery and provide necessary flood extent mappings. These methods, though, require large amounts of annotated training data to create models that are accurate and robust to new flooded imagery. In this work, we provide FloodTrace, an application that enables effective crowdsourcing for flooded region annotation for machine learning training data, removing the requirement for…