Viral News

PRTGS: Precomputed Radiance Transfer of Gaussian Splats for Real-Time High-Quality Relighting

PRTGS: Precomputed Radiance Transfer of Gaussian Splats for Real-Time High-Quality Relighting

arXiv:2408.03538v1 Announce Type: new Abstract: We proposed Precomputed RadianceTransfer of GaussianSplats (PRTGS), a real-time high-quality relighting method for Gaussian splats in low-frequency lighting environments that captures soft shadows and interreflections by precomputing 3D Gaussian splats' radiance transfer. Existing studies have demonstrated that 3D Gaussian splatting (3DGS) outperforms neural fields' efficiency for dynamic lighting scenarios. However, the current relighting method based on 3DGS still struggles to compute high-quality shadow and indirect illumination in real time for dynamic light, leading to unrealistic rendering results. We solve this problem by precomputing the expensive transport simulations required for complex transfer functions like shadowing, the…
Read More
CARE: A Clue-guided Assistant for CSRs to Read User Manuals

CARE: A Clue-guided Assistant for CSRs to Read User Manuals

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
Read More
LLM Evaluation Metrics: Benchmarks, Protocols & Best Practices

LLM Evaluation Metrics: Benchmarks, Protocols & Best Practices

Source: AuthorWhat are LLM Evaluation Metrics?Large Language Models (LLMs) have revolutionized the field of Natural Language Processing (NLP) due to their ability to understand and generate human language with remarkable proficiency. These models like GPT-4, BERT, T5, etc. are being utilized in a variety of applications ranging from automated text generation and translation to conversational agents, and content recommendation systems. Evaluating these LLMs has become critical to ensure their effectiveness and reliability.Evaluation with the help of various evaluation metrics helps developers understand how a model is performing in different contexts and tasks. Moreover, effective evaluation plays a pivotal role in…
Read More
Can LLMs Serve As Time Series Anomaly Detectors?

Can LLMs Serve As Time Series Anomaly Detectors?

arXiv:2408.03475v1 Announce Type: new Abstract: An emerging topic in large language models (LLMs) is their application to time series forecasting, characterizing mainstream and patternable characteristics of time series. A relevant but rarely explored and more challenging question is whether LLMs can detect and explain time series anomalies, a critical task across various real-world applications. In this paper, we investigate the capabilities of LLMs, specifically GPT-4 and LLaMA3, in detecting and explaining anomalies in time series. Our studies reveal that: 1) LLMs cannot be directly used for time series anomaly detection. 2) By designing prompt strategies such as in-context learning and…
Read More
SwinShadow: Shifted Window for Ambiguous Adjacent Shadow Detection

SwinShadow: Shifted Window for Ambiguous Adjacent Shadow Detection

arXiv:2408.03521v1 Announce Type: new Abstract: Shadow detection is a fundamental and challenging task in many computer vision applications. Intuitively, most shadows come from the occlusion of light by the object itself, resulting in the object and its shadow being contiguous (referred to as the adjacent shadow in this paper). In this case, when the color of the object is similar to that of the shadow, existing methods struggle to achieve accurate detection. To address this problem, we present SwinShadow, a transformer-based architecture that fully utilizes the powerful shifted window mechanism for detecting adjacent shadows. The mechanism operates in two steps.…
Read More
PAGED: A Benchmark for Procedural Graphs Extraction from Documents

PAGED: A Benchmark for Procedural Graphs Extraction from Documents

arXiv:2408.03630v1 Announce Type: new Abstract: Automatic extraction of procedural graphs from documents creates a low-cost way for users to easily understand a complex procedure by skimming visual graphs. Despite the progress in recent studies, it remains unanswered: whether the existing studies have well solved this task (Q1) and whether the emerging large language models (LLMs) can bring new opportunities to this task (Q2). To this end, we propose a new benchmark PAGED, equipped with a large high-quality dataset and standard evaluations. It investigates five state-of-the-art baselines, revealing that they fail to extract optimal procedural graphs well because of their heavy…
Read More
Integrating HCI Datasets in Project-Based Machine Learning Courses: A College-Level Review and Case Study

Integrating HCI Datasets in Project-Based Machine Learning Courses: A College-Level Review and Case Study

arXiv:2408.03472v1 Announce Type: new Abstract: This study explores the integration of real-world machine learning (ML) projects using human-computer interfaces (HCI) datasets in college-level courses to enhance both teaching and learning experiences. Employing a comprehensive literature review, course websites analysis, and a detailed case study, the research identifies best practices for incorporating HCI datasets into project-based ML education. Key f indings demonstrate increased student engagement, motivation, and skill development through hands-on projects, while instructors benefit from effective tools for teaching complex concepts. The study also addresses challenges such as data complexity and resource allocation, offering recommendations for future improvements. These insights…
Read More
Leveraging LLMs for Enhanced Open-Vocabulary 3D Scene Understanding in Autonomous Driving

Leveraging LLMs for Enhanced Open-Vocabulary 3D Scene Understanding in Autonomous Driving

arXiv:2408.03516v1 Announce Type: new Abstract: This paper introduces a novel method for open-vocabulary 3D scene understanding in autonomous driving by combining Language Embedded 3D Gaussians with Large Language Models (LLMs) for enhanced inference. We propose utilizing LLMs to generate contextually relevant canonical phrases for segmentation and scene interpretation. Our method leverages the contextual and semantic capabilities of LLMs to produce a set of canonical phrases, which are then compared with the language features embedded in the 3D Gaussians. This LLM-guided approach significantly improves zero-shot scene understanding and detection of objects of interest, even in the most challenging or unfamiliar environments.…
Read More
Improving the quality of Persian clinical text with a novel spelling correction system

Improving the quality of Persian clinical text with a novel spelling correction system

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
Read More
Collibra Survey: US Tech Executives Don’t Trust U.S. Government Approach to AI Regulation

Collibra Survey: US Tech Executives Don’t Trust U.S. Government Approach to AI Regulation

A survey by Collibra, a data intelligence company, has revealed that an overwhelming majority (84%) of tech executives support an overhaul of US copyright laws to protect against AI.  The survey, conducted online by The Harris Poll on behalf of Collibra, offers insights into how businesses are managing the complexities of AI adoption and regulation. Over 300 full-time decision-makers in data management or AI roles at their companies participated in the survey. All the respondents were director-level or higher.  Rising concerns about AI ethics, security risks, and data privacy have driven U.S. business leaders to call for robust AI regulations…
Read More
No widgets found. Go to Widget page and add the widget in Offcanvas Sidebar Widget Area.