Viral News

Better Not to Propagate: Understanding Edge Uncertainty and Over-smoothing in Signed Graph Neural Networks

Better Not to Propagate: Understanding Edge Uncertainty and Over-smoothing in Signed Graph Neural Networks

arXiv:2408.04895v1 Announce Type: new Abstract: Traditional Graph Neural Networks (GNNs) rely on network homophily, which can lead to performance degradation due to over-smoothing in many real-world heterophily scenarios. Recent studies analyze the smoothing effect (separability) after message-passing (MP), depending on the expectation of node features. Regarding separability gain, they provided theoretical backgrounds on over-smoothing caused by various propagation schemes, including positive, signed, and blocked MPs. More recently, by extending these theorems, some works have suggested improvements in signed propagation under multiple classes. However, prior works assume that the error ratio of all propagation schemes is fixed, failing to investigate this…
Read More
LLaVA-VSD: Large Language-and-Vision Assistant for Visual Spatial Description

LLaVA-VSD: Large Language-and-Vision Assistant for Visual Spatial Description

arXiv:2408.04957v1 Announce Type: new Abstract: Visual Spatial Description (VSD) aims to generate texts that describe the spatial relationships between objects within images. Traditional visual spatial relationship classification (VSRC) methods typically output the spatial relationship between two objects in an image, often neglecting world knowledge and lacking general language capabilities. In this paper, we propose a Large Language-and-Vision Assistant for Visual Spatial Description, named LLaVA-VSD, which is designed for the classification, description, and open-ended description of visual spatial relationships. Specifically, the model first constructs a VSD instruction-following dataset using given figure-caption pairs for the three tasks. It then employs LoRA to…
Read More
MaterioMiner — An ontology-based text mining dataset for extraction of process-structure-property entities

MaterioMiner — An ontology-based text mining dataset for extraction of process-structure-property entities

arXiv:2408.04661v1 Announce Type: new Abstract: While large language models learn sound statistical representations of the language and information therein, ontologies are symbolic knowledge representations that can complement the former ideally. Research at this critical intersection relies on datasets that intertwine ontologies and text corpora to enable training and comprehensive benchmarking of neurosymbolic models. We present the MaterioMiner dataset and the linked materials mechanics ontology where ontological concepts from the mechanics of materials domain are associated with textual entities within the literature corpus. Another distinctive feature of the dataset is its eminently fine-granular annotation. Specifically, 179 distinct classes are manually annotated…
Read More
UCB Exploration for Fixed-Budget Bayesian Best Arm Identification

UCB Exploration for Fixed-Budget Bayesian Best Arm Identification

arXiv:2408.04869v1 Announce Type: new Abstract: We study best-arm identification (BAI) in the fixed-budget setting. Adaptive allocations based on upper confidence bounds (UCBs), such as UCBE, are known to work well in BAI. However, it is well-known that its optimal regret is theoretically dependent on instances, which we show to be an artifact in many fixed-budget BAI problems. In this paper we propose an UCB exploration algorithm that is both theoretically and empirically efficient for the fixed budget BAI problem under a Bayesian setting. The key idea is to learn prior information, which can enhance the performance of UCB-based BAI algorithm…
Read More
Capsule Vision 2024 Challenge: Multi-Class Abnormality Classification for Video Capsule Endoscopy

Capsule Vision 2024 Challenge: Multi-Class Abnormality Classification for Video Capsule Endoscopy

arXiv:2408.04940v1 Announce Type: new Abstract: We present the Capsule Vision 2024 Challenge: Multi-Class Abnormality Classification for Video Capsule Endoscopy. It is being virtually organized by the Research Center for Medical Image Analysis and Artificial Intelligence (MIAAI), Department of Medicine, Danube Private University, Krems, Austria and Medical Imaging and Signal Analysis Hub (MISAHUB) in collaboration with the 9th International Conference on Computer Vision & Image Processing (CVIP 2024) being organized by the Indian Institute of Information Technology, Design and Manufacturing (IIITDM) Kancheepuram, Chennai, India. This document describes the overview of the challenge, its registration and rules, submission format, and the description…
Read More
XMainframe: A Large Language Model for Mainframe Modernization

XMainframe: A Large Language Model for Mainframe Modernization

[Submitted on 5 Aug 2024 (v1), last revised 12 Aug 2024 (this version, v2)] View a PDF of the paper titled XMainframe: A Large Language Model for Mainframe Modernization, by Anh T. V. Dau and 5 other authors View PDF HTML (experimental) Abstract:Mainframe operating systems, despite their inception in the 1940s, continue to support critical sectors like finance and government. However, these systems are often viewed as outdated, requiring extensive maintenance and modernization. Addressing this challenge necessitates innovative tools that can understand and interact with legacy codebases. To this end, we introduce XMainframe, a state-of-the-art large language model (LLM) specifically…
Read More
An Evaluation of Standard Statistical Models and LLMs on Time Series Forecasting

An Evaluation of Standard Statistical Models and LLMs on Time Series Forecasting

arXiv:2408.04867v1 Announce Type: new Abstract: This research examines the use of Large Language Models (LLMs) in predicting time series, with a specific focus on the LLMTIME model. Despite the established effectiveness of LLMs in tasks such as text generation, language translation, and sentiment analysis, this study highlights the key challenges that large language models encounter in the context of time series prediction. We assess the performance of LLMTIME across multiple datasets and introduce classical almost periodic functions as time series to gauge its effectiveness. The empirical results indicate that while large language models can perform well in zero-shot forecasting for…
Read More
UAV-Enhanced Combination to Application: Comprehensive Analysis and Benchmarking of a Human Detection Dataset for Disaster Scenarios

UAV-Enhanced Combination to Application: Comprehensive Analysis and Benchmarking of a Human Detection Dataset for Disaster Scenarios

[Submitted on 9 Aug 2024] View a PDF of the paper titled UAV-Enhanced Combination to Application: Comprehensive Analysis and Benchmarking of a Human Detection Dataset for Disaster Scenarios, by Ragib Amin Nihal and 3 other authors View PDF HTML (experimental) Abstract:Unmanned aerial vehicles (UAVs) have revolutionized search and rescue (SAR) operations, but the lack of specialized human detection datasets for training machine learning models poses a significant this http URL address this gap, this paper introduces the Combination to Application (C2A) dataset, synthesized by overlaying human poses onto UAV-captured disaster scenes. Through extensive experimentation with state-of-the-art detection models, we demonstrate…
Read More
Winning Amazon KDD Cup’24

Winning Amazon KDD Cup’24

arXiv:2408.04658v1 Announce Type: new Abstract: This paper describes the winning solution of all 5 tasks for the Amazon KDD Cup 2024 Multi Task Online Shopping Challenge for LLMs. The challenge was to build a useful assistant, answering questions in the domain of online shopping. The competition contained 57 diverse tasks, covering 5 different task types (e.g. multiple choice) and across 4 different tracks (e.g. multi-lingual). Our solution is a single model per track. We fine-tune Qwen2-72B-Instruct on our own training dataset. As the competition released only 96 example questions, we developed our own training dataset by processing multiple public datasets…
Read More
High dimensional Bayesian Optimization via Condensing-Expansion Projection

High dimensional Bayesian Optimization via Condensing-Expansion Projection

arXiv:2408.04860v1 Announce Type: new Abstract: In high-dimensional settings, Bayesian optimization (BO) can be expensive and infeasible. The random embedding Bayesian optimization algorithm is commonly used to address high-dimensional BO challenges. However, this method relies on the effective subspace assumption on the optimization problem's objective function, which limits its applicability. In this paper, we introduce Condensing-Expansion Projection Bayesian optimization (CEPBO), a novel random projection-based approach for high-dimensional BO that does not reply on the effective subspace assumption. The approach is both simple to implement and highly practical. We present two algorithms based on different random projection matrices: the Gaussian projection matrix…
Read More
No widgets found. Go to Widget page and add the widget in Offcanvas Sidebar Widget Area.