检索结果-内蒙古大学图书馆

Groundbreaking taxonomy of metaverse characteristics

学校读者我要写书评

暂无评论

Artificial Intelligence Review 2025年第8期58卷 1-50页

作者： Sadeghi-Niaraki, Abolghasem Rahimi, Fatema Azlan, Nur Alya Emanuelle Binti Song, Houbing Ali, Farman Choi, Soo-Mi Department of Computer Science and Engineering and Convergence Engineering for Intelligent Drone XR Research Center Sejong University Seoul Korea Republic of BaltimoreMD21250 United States Department of Applied AI School of Convergence College of Computing and Informatics Sungkyunkwan University Seoul03063 Korea Republic of

The Metaverse, a dynamic and immersive virtual realm, has captured the imagination of researchers and enthusiasts worldwide. This survey paper aims to introduce a groundbreaking taxonomy for the characteristics of the Metaverse offering a structured and adaptable framework that extends beyond existing categorizations by incorporating dynamic transformations. Unlike prior taxonomies, which often focus on fixed attributes, our approach emphasizes the dynamic evolution of Metaverse characteristics. Through an extensive review of published literature, this study explores key technological, social, economic, and ethical dimensions of the Metaverse. It introduces a process-oriented classification based on 23 distinct characteristics, including immersification, spatiotemporalification, interactification, persistentification, presentification, personification, unification, imaginification, economification, uncertaintification, and credification. By mapping these evolving aspects, we provide a structured and future-proof foundation for understanding the Metaverse’s continuous development. This survey establishes a new standard for comprehensiveness and innovation, shedding light on the diverse facets that have been explored in literature. Through this novel taxonomy, we provide a detailed map of the current landscape and offer insights that pave the way for future research and development in this burgeoning digital frontier. © The Author(s) 2025.

关键词： Comprehensive analysis Futuristic exploration Metaverse characteristics Paradigm-shifting taxonomy Revolutionary categorization

High Performance computing Framework for Variable Selection on Genome-wide Association Studies

学校读者我要写书评

暂无评论

High Performance Computing Framework for Variable Selection ...

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Liu, Xiang Liu, Xueling Diao, Jing Zheng, Mengyao Li, Jihe Wei, Dehui Xie, Qipeng Li, Xia Jiang, Linshan National University Health System Group Technology Office Singapore National University of Singapore School of Computing Singapore Peking University School Hospital of Stomatology National Center for Stomatology National Clinical Research Center for Oral Diseases Department of Preventive Dentistry China Harvard University Harvard T.H. Chan School of Public Health United States Peking University School of Software and Microelectronics China Hong Kong University of Science and Technology IoT Thrust Information Hub Guangzhou China Eth Zurich Department of Computer Science Switzerland National University of Singapore Institute of Data Science Singapore

ISBN: (纸本)9798350386226

Variable selection for genome-wide association studies (GWAS) has been a major research focus for decades. With the exponential growth of biological and biomedical data in the era of big data, scientists are confronted with the challenge of extracting meaningful information from vast datasets while managing the inherent heterogeneity in bioinformatics. To date, there are no highly effective tools that support high-dimensional datasets and achieve robust variable selection performance, all while accounting for the non-i.i.d. features and structured relatedness among explanatory and response *** address these challenges, we introduce the first high-performance computing framework for variable selection in GWAS. Our framework integrates various state-of-the-art methods, allowing researchers to easily combine different techniques and fully explore their potential. Additionally, our approach employs novel optimization strategies to solve the problem efficiently, even for high-dimensional data with sparse characteristics. By processing the data holistically, the framework delivers comprehensive analysis and accurate linkage mapping associations. Designed for ease of use, the framework is implemented in Python and offers seamless deployment, making it accessible to a wide range of researchers. © 2024 IEEE.

关键词： Confounding factors genome-wide association study structured relatedness variable selection

HAPIC: A Scalable, Lightweight and Reactive Cache for Persistent-Memory-Based Index

学校读者我要写书评

暂无评论

HAPIC: A Scalable, Lightweight and Reactive Cache for Persis...

IEEE International Conference on computer-Aided Design

作者： Chih-Ting Lo Yun-Chih Chen Yuan-Hao Chang Tei-Wei Kuo Department of Computer Science and Information Engineering National Taiwan University Academia Sinica Institute of Information Science Taiwan Department of Computer Science Mohamed bin Zayed University of Artificial Intelligence NTU High Performance and Scientific Computing Center National Taiwan University

In-memory index delivers low-latency responses for data services. It has been ported to high-capacity persistent memory (PM) to accommodate more data. However, read-heavy, extremely-skewed, and highly-dynamic workloads can suffer from degraded performance on PM-based indexes. We present HAPIC, a scalable cache over PM-based indexes to capture the constantly-changing query hotspots in skewed workloads. HAPIC embodies the data access frequency gradient in a hierarchy of hash tables to efficiently identify hotspots and reacts quickly to workload changes with epoch-based promotion. Compared with the state-of-the-art strategy, HAPIC reacts to hotspot shifts significantly faster, with up to 14% higher stable read throughput, 26% lower median latency, and 13% lower P99 latency.

关键词：

Provably Transformers Harness Multi-Concept Word Semantics for Efficient In-Context Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Bu, Dake Huang, Wei Han, Andi Nitanda, Atsushi Suzuki, Taiji Zhang, Qingfu Wong, Hau-San Department of Computer Science City University of Hong Kong Hong Kong Center for Advanced Intelligence Project RIKEN Japan Singapore College of Computing and Data Science Nanyang Technological University Singapore Department of Mathematical Informatics The University of Tokyo Japan

Transformer-based large language models (LLMs) have displayed remarkable creative prowess and emergence capabilities. Existing empirical studies have revealed a strong connection between these LLMs' impressive emergence abilities and their in-context learning (ICL) capacity, allowing them to solve new tasks using only task-specific prompts without further fine-tuning. On the other hand, existing empirical and theoretical studies also show that there is a linear regularity of the multi-concept encoded semantic representation behind transformer-based LLMs. However, existing theoretical work fail to build up an understanding of the connection between this regularity and the innovative power of ICL. Additionally, prior work often focuses on simplified, unrealistic scenarios involving linear transformers or unrealistic loss functions, and they achieve only linear or sub-linear convergence rates. In contrast, this work provides a fine-grained mathematical analysis to show how transformers leverage the multi-concept semantics of words to enable powerful ICL and excellent out-of-distribution ICL abilities, offering insights into how transformers innovate solutions for certain unseen tasks encoded with multiple cross-concept semantics. Inspired by empirical studies on the linear latent geometry of LLMs, the analysis is based on a concept-based low-noise sparse coding prompt model. Leveraging advanced techniques, this work showcases the exponential 0-1 loss convergence over the highly non-convex training dynamics, which pioneeringly incorporates the challenges of softmax self-attention, ReLU-activated MLPs, and cross-entropy loss. Empirical simulations corroborate the theoretical findings. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

SMOTE Oversampling and Near Miss Undersampling Based Diabetes Diagnosis from Imbalanced Dataset with XAI visualization

学校读者我要写书评

暂无评论

SMOTE Oversampling and Near Miss Undersampling Based Diabete...

IEEE Symposium on computers and Communications (ISCC)

作者： Nasim Mahmud Nayan Ashraful Islam Muhammad Usama Islam Eshtiak Ahmed Mohammad Mobarak Hossain Md Zahangir Alam Department of Computer Science and Engineering University of Information Technology and Sciences Bangladesh Center for Computational and Data Sciences Independent University Bangladesh Department of Computer Science and Engineering Independent University Bangladesh School of Computing and Informatics University of Louisiana at Lafayette USA Department of Computer Science and Engineering Daffodil International University Bangladesh

This study investigated the predictive ability of ten different machine learning (ML) models for diabetes using a dataset that was not evenly distributed. Additionally, the study evaluated the effectiveness of two oversampling and undersampling methods, namely the Synthetic Minority Oversampling Technique (SMOTE) and the Near-Miss algorithm. Explainable Artificial Intelligence (XAI) techniques were employed to enhance the interpretability of the model's predictions. The results indicate that the extreme gradient boosting (XGB) model combined with SMOTE oversampling technique exhibited the highest accuracy and an F1-score of 99% and 1.00 respectively. Furthermore, the utilization of XAI methods increased the dependability of the model's decision-making process, rendering it more appropriate for clinical use. These results imply that integrating XAI with ML and oversampling techniques can enhance the early detection and management of diabetes, leading to better diagnosis and intervention.

关键词：

Deep Video Representation Learning: A Survey

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ravanbakhsh, Elham Liang, Yongqing Ramanujam, J. Li, Xin Division of Electrical & Computer Engineering Center for Computation & Technology Louisiana State University Baton RougeLA70803 United States Department of Computer Science and Engineering Texas A&M University College StationTX77843 United States Section of Visual Computing and Interactive Media Texas A&M University College StationTX77843 United States

This paper provides a review on representation learning for videos. We classify recent spatio-temporal feature learning methods for sequential visual data and compare their pros and cons for general video analysis. Building effective features for videos is a fundamental problem in computer vision tasks involving video analysis and understanding. Existing features can be generally categorized into spatial and temporal features. Their effectiveness under variations of illumination, occlusion, view and background are discussed. Finally, we discuss the remaining challenges in existing deep video representation learning studies. © 2024, CC BY-NC-ND.

关键词： Deep learning

On Statistical Rates and Provably Efficient Criteria of Latent Diffusion Transformers (DiTs)

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Hu, Jerry Yao-Chieh Wu, Weimin Song, Zhao Liu, Han Center for Foundation Models Generative AI Department of Computer Science Department of Statistics and Data Science Northwestern University EvanstonIL60208 United States Simons Institute for the Theory of Computing UC Berkeley BerkeleyCA94720 United States

We investigate the statistical and computational limits of latent Diffusion Transformers (DiTs) under the low-dimensional linear latent space assumption. Statistically, we study the universal approximation and sample complexity of the DiTs score function, as well as the distribution recovery property of the initial data. Specifically, under mild data assumptions, we derive an approximation error bound for the score network of latent DiTs, which is sub-linear in the latent space dimension. Additionally, we derive the corresponding sample complexity bound and show that the data distribution generated from the estimated score function converges toward a proximate area of the original one. Computationally, we characterize the hardness of both forward inference and backward computation of latent DiTs, assuming the Strong Exponential Time Hypothesis (SETH). For forward inference, we identify efficient criteria for all possible latent DiTs inference algorithms and showcase our theory by pushing the efficiency toward almost-linear time inference. For backward computation, we leverage the low-rank structure within the gradient computation of DiTs training for possible algorithmic speedup. Specifically, we show that such speedup achieves almost-linear time latent DiTs training by casting the DiTs gradient as a series of chained low-rank approximations with bounded error. Under the low-dimensional assumption, we show that the statistical rates and the computational efficiency are all dominated by the dimension of the subspace, suggesting that latent DiTs have the potential to bypass the challenges associated with the high dimensionality of initial data. © 2024, CC BY-NC-SA.

关键词： Distribution transformers

The Hidden Dimensions of LLM Alignment: A Multi-Dimensional Safety Analysis

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Pan, Wenbo Liu, Zhichao Chen, Qiguang Zhou, Xiangyang Yu, Haining Jia, Xiaohua Department of Computer Science City University of Hong Kong Hong Kong School of Cyberspace Science Harbin Institute of Technology China Research Center for Social Computing and Information Retrieval Harbin Institute of Technology China Microsoft United States

Large Language Models’ safety-aligned behaviors, such as refusing harmful queries, can be represented by linear directions in activation space. Previous research modeled safety behavior with a single direction, limiting mechanistic understanding to an isolated safety feature. In this work, we discover that safety-aligned behavior is jointly controlled by multi-dimensional directions. Namely, we study the vector space of representation shifts during safety fine-tuning on Llama 3 8B for refusing jailbreaks. By studying orthogonal directions in the space, we first find that a dominant direction governs the model’s refusal behavior, while multiple smaller directions represent distinct and interpretable features like hypothetical narrative and role-playing. We then measure how different directions promote or suppress the dominant direction, showing the important role of secondary directions in shaping the model’s refusal representation. Finally, we demonstrate that removing certain trigger tokens in harmful queries can mitigate these directions to bypass the learned safety capability, providing new insights on understanding safety alignment vulnerability from a multi-dimensional perspective. Code and artifacts are available at https://***/BMPixel/safety-residual-space. © 2025, CC BY.

关键词： Safety engineering

computing and Compressing Electron Repulsion Integrals on FPGAs

学校读者我要写书评

暂无评论

Computing and Compressing Electron Repulsion Integrals on FP...

Annual IEEE Symposium on Field-Programmable Custom computing Machines (FCCM)

作者： Xin Wu Tobias Kenter Robert Schade Thomas D. Kühne Christian Plessl Paderborn Center for Parallel Computing Paderborn University Paderborn Germany Department of Computer Science Paderborn University Paderborn Germany Department of Chemistry Paderborn University Paderborn Germany

The computation of electron repulsion integrals (ERIs) over Gaussian-type orbitals (GTOs) is a challenging problem in quantum-mechanics-based atomistic simulations. In practical simulations, several trillions of ERIs may have to be computed for every time step. In this work, we investigate FPGAs as accelerators for the ERI computation. We use template parameters, here within the Intel oneAPI tool flow, to create customized designs for 256 different ERI quartet classes, based on their orbitals. To maximize data reuse, all intermediates are buffered in FPGA on-chip memory with customized layouts. The pre-calculation of intermediates also helps to overcome data dependencies caused by multi-dimensional recurrence relations. The involved loop structures are partially or even fully unrolled for high throughput of FPGA kernels. Furthermore, a lossy compression algorithm utilizing arbitrary bitwidth integers is integrated in the FPGA kernels. To our best knowledge, this is the first work on ERI computation on FPGAs that supports more than just the single most basic quartet class. Also, the integration of ERI computation and compression is a novelty that is not even covered by CPU or GPU libraries so far. Our evaluation shows that using 16-bit integer for the ERI compression, the fastest FPGA kernels exceed the performance of 10 GERIS ( $10\times 10^{9}$ ERIs per second) on one Intel Stratix 10 GX 2800 FPGA, with maximum absolute errors around 10 −7 - 10 −5 Hartree. The measured throughput can be accurately explained by a performance model. The FPGA kernels deployed on 2 FPGAs outperform similar computations using the widely used libint reference on a two-socket server with 40 Xeon Gold 6148 CPU cores of the same process technology by factors up to 6.0x and on a new two-socket server with 128 EPYC 7713 CPU cores by up to 1.9x.

关键词：