计算机科学最新文献

筛选
英文 中文
Continuous Game of Life: Cell Emergence and Self-Organization at the Edge of Growth. 生命的连续游戏:生长边缘的细胞出现和自组织。
IF 1.8 4区 计算机科学
Artificial Life Pub Date : 2026-11-16 DOI: 10.1162/ARTL.a.501
Alexandre Guillet, Frank Jülicher
{"title":"Continuous Game of Life: Cell Emergence and Self-Organization at the Edge of Growth.","authors":"Alexandre Guillet, Frank Jülicher","doi":"10.1162/ARTL.a.501","DOIUrl":"https://doi.org/10.1162/ARTL.a.501","url":null,"abstract":"<p><p>Conway's Game of Life shows that simple rules can generate a rich diversity of emerging structures. This cellular automaton has been translated to continuous space by Rafler (2011) in a simulation called SmoothLife. The isotropic rule of this continuous Game of Life generates patterns whose beauty has attracted the attention of a growing community at the intersection of science and computer art. We study a minimal variant of this model, continuous in space and time, that generates cell-like patterns capable of self-replicating, gliding and disappearing. The phenomenology of these unit patterns is reported and related to homogeneous-state bifurcations, symmetry breaking, observed shape instabilities, finite-amplitude morphological changes, and a dilute-to-dense transition associated with cell proliferation. Its mapping onto a large reaction-diffusion system is interpreted in terms of homeostatic concentrations of morphogens, regulated by the nonlinear survival rule and generated through a cell-sourced cascade of auxiliary reactions. Introducing a global conservation law that limits resource availability causes the system to self-organize at this dilute-to-dense transition, which we call the edge of growth. A further exploration of parameter space reveals a variety of phases and the richness of life-like morphologies organized around this edge. Resemblance to biological processes such as division, motility, and death-together with a concise formulation and numerical implementation-makes the continuous Game of Life an appealing model system for investigating the emergence and self-organization of life-like patterns.</p>","PeriodicalId":55574,"journal":{"name":"Artificial Life","volume":" ","pages":"1-21"},"PeriodicalIF":1.8,"publicationDate":"2026-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149413160","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Fighting Fake News: A Survey of AI-based Models, Frameworks and Challenges 打击假新闻:基于人工智能的模型、框架和挑战的调查
IF 16.6 1区 计算机科学
ACM Computing Surveys Pub Date : 2026-11-14 DOI: 10.1145/3863938
Li Zeng, Yizheng Huang, Jimmy Xiangji Huang
{"title":"Fighting Fake News: A Survey of AI-based Models, Frameworks and Challenges","authors":"Li Zeng, Yizheng Huang, Jimmy Xiangji Huang","doi":"10.1145/3863938","DOIUrl":"https://doi.org/10.1145/3863938","url":null,"abstract":"Recently, the rapid growth of digital fake news has gained significant attention in both social media and artificial intelligence (AI) due to fake news can influence daily life deeply. This survey provides a review on AI-based fake news detection (FND), beginning by introducing the theoretical foundations like fake news definition, fake news ecosystem, related terms and fake news characteristics. Then, we introduce a taxonomy that separates AI-based FND methods into two categories which are model-centric models and process-centric frameworks. We then evaluate various model-centric models ranging from traditional models to machine learning, deep learning, and trending models. A significant portion of this work focuses on AI-based FND frameworks, which include dataset, data augmentation, information extraction, model validation and refinement, and results explanation and feedback. Finally, we discuss major challenges and trends to build more reliable information environments.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"16 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2026-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149397201","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
ClassifierAlign: Unsupervised multi-label image classification via training-free vision-language classifier alignment. ClassifierAlign:通过无训练的视觉语言分类器对齐进行无监督多标签图像分类。
IF 7.2 1区 计算机科学
Neural Networks Pub Date : 2026-11-14 DOI: 10.1016/j.neunet.2026.109901
Xili Deng, Yi Zhao, Nanqing Liu, Yaping Zhang, Chengfu Yang, Zhanxuan Hu
{"title":"ClassifierAlign: Unsupervised multi-label image classification via training-free vision-language classifier alignment.","authors":"Xili Deng, Yi Zhao, Nanqing Liu, Yaping Zhang, Chengfu Yang, Zhanxuan Hu","doi":"10.1016/j.neunet.2026.109901","DOIUrl":"https://doi.org/10.1016/j.neunet.2026.109901","url":null,"abstract":"<p><p>Existing vision-language models (VLMs) exhibit strong zero-shot generalization, yet remain fundamentally limited in Unsupervised Multi-label Image Classification (UMIC), primarily due to their inadequate multi-object perception and the intrinsic modality gap between vision and language. In particular, global representations tend to entangle multiple concepts, hindering accurate recognition of co-existing objects. To address these challenges, we revisit UMIC from a decomposition-then-classification perspective. Instead of predicting multiple concepts holistically, we first decompose an unlabeled multi-label image into multiple single-concept visual instances, thereby explicitly improving multi-object perception. We then perform classification based on aggregated predictions. Building upon this paradigm, we propose ClassifierAlign, a fully training-free framework that jointly leverages visual foundation models (VFMs) and VLMs. Specifically, we derive a lightweight visual classifier directly in the visual feature space, and semantically align it with CLIP's textual classifier, effectively bridging the vision-language modality gap without updating parameters of the pretrained foundation models. This design further enables seamless integration of powerful self-supervised VFMs (e.g., DINO), yielding robust and transferable representations without requiring spatial alignment. Extensive experiments demonstrate that ClassifierAlign achieves competitive performance with fine-tuning-based methods, while significantly reducing computational overhead and eliminating the need for costly annotated data. The source code for this work can be found at https://github.com/dengxili/ClassifierAlign.</p>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"206 Pt C","pages":"109901"},"PeriodicalIF":7.2,"publicationDate":"2026-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149412428","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
An Argumentation-Based System for Classifying Driving Behaviors 基于论证的驾驶行为分类系统
IF 7 2区 计算机科学
International Journal of Intelligent Systems Pub Date : 2026-11-14 DOI: 10.1155/int/7024855
B. Fazzinga,F. Furfaro,G. Monterosso
{"title":"An Argumentation-Based System for Classifying Driving Behaviors","authors":"B. Fazzinga,F. Furfaro,G. Monterosso","doi":"10.1155/int/7024855","DOIUrl":"https://doi.org/10.1155/int/7024855","url":null,"abstract":"","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"29 1","pages":""},"PeriodicalIF":7.0,"publicationDate":"2026-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149398572","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
End-to-End Differentiable Smoothed Particle Hydrodynamics for Fluid--Rigid Optimization with Gradient Stabilization 端到端可微光滑粒子流体动力学——梯度稳定下的流体刚性优化
IF 6.2 1区 计算机科学
ACM Transactions on Graphics Pub Date : 2026-11-14 DOI: 10.1145/3860999
Geng-Chen Cao, Bo Ren, Yanrui Xu, Zhe-Han Mo, Shi-min Hu
{"title":"End-to-End Differentiable Smoothed Particle Hydrodynamics for Fluid--Rigid Optimization with Gradient Stabilization","authors":"Geng-Chen Cao, Bo Ren, Yanrui Xu, Zhe-Han Mo, Shi-min Hu","doi":"10.1145/3860999","DOIUrl":"https://doi.org/10.1145/3860999","url":null,"abstract":"We introduce an end-to-end differentiable optimization framework for Smoothed Particle Hydrodynamics (SPH) with fluid–rigid body coupling. The central difficulty is not only to obtain local derivatives of SPH operators, but also to propagate useful sensitivities through long rollouts whose particle neighborhoods, contacts, and pressure responses change rapidly over time. These effects make reverse-mode gradients noisy and often cause adjoint variables to explode in long-horizon control and inverse-design tasks. We formulate an SPH-specific reverse-mode pipeline for IISPH-based fluid–rigid simulation and implement the required vector–Jacobian products within checkpointed simulation segments. To make the resulting gradients usable for optimization, we introduce a self-adaptive adjoint correction sequence that acts as a descent-preserving preconditioner: it bounds pathological adjoint amplification while keeping the update direction aligned with the original reverse-mode sensitivity. Our experiments cover a sequence of increasingly demanding tasks, from low-dimensional impulse and shape optimization to scalar-amplitude water actuation, multi-object water-jet balancing, and neural fluid-mediated pendulum control. These results demonstrate that stabilized reverse-mode differentiation can support challenging SPH-based optimization problems involving indirect momentum transfer, long-horizon event timing, and high-dimensional control.","PeriodicalId":50913,"journal":{"name":"ACM Transactions on Graphics","volume":"27 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149397199","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A 360° Survey on Reconfigurability of HPC Storage Systems for Efficient I/O 面向高效I/O的高性能计算存储系统可重构性的360°研究
IF 16.6 1区 计算机科学
ACM Computing Surveys Pub Date : 2026-11-14 DOI: 10.1145/3863974
Amir Salimiparsa, Noah Lewis, Jean Luca Bez, Surendra Byna
{"title":"A 360° Survey on Reconfigurability of HPC Storage Systems for Efficient I/O","authors":"Amir Salimiparsa, Noah Lewis, Jean Luca Bez, Surendra Byna","doi":"10.1145/3863974","DOIUrl":"https://doi.org/10.1145/3863974","url":null,"abstract":"High-performance computing (HPC) storage and I/O software stacks have been challenging to configure due to multiple software layers, interdependencies among those layers, and the number of parameters to tune within each layer. The storage stack has become increasingly complex with the ever-growing sets of new software and hardware. In addition, there is a shift in HPC applications from modeling and simulations (mod-sim) to AI training and inference. While several efforts focused on tuning I/O parameters of write-heavy simulation workloads, configuring I/O for random and read-heavy AI applications has still been in progress. Although the HPC storage stack could be reconfigured to meet these diverse write and read requirements, finding optimal I/O configurations for even a single application is a challenging task. This survey proposes a taxonomy of HPC storage and I/O system configurations and reconfigurability for bringing a consensus to the I/O parameters that are tunable by clients (i.e., users and applications). In this paper, we survey I/O tuning and optimization, harnessing the HPC I/O system configuration knowledge from the past decade. This paper can serve as a primary source of information for HPC I/O researchers and developers to design and optimize novel tuning strategies that improve storage and I/O system reconfigurability and performance.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"1 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2026-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149397200","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Modality-Aware Feature Matching in Visual and Vision-Language Applications: A Comprehensive Survey 在视觉和视觉语言应用中的形态感知特征匹配:一个综合调查
IF 16.6 1区 计算机科学
ACM Computing Surveys Pub Date : 2026-11-14 DOI: 10.1145/3863939
Weide Liu, Wei Zhou, Jun Liu, Ping Hu, Jun Cheng, Jungong Han, Weisi Lin
{"title":"Modality-Aware Feature Matching in Visual and Vision-Language Applications: A Comprehensive Survey","authors":"Weide Liu, Wei Zhou, Jun Liu, Ping Hu, Jun Cheng, Jungong Han, Weisi Lin","doi":"10.1145/3863939","DOIUrl":"https://doi.org/10.1145/3863939","url":null,"abstract":"Feature matching is a cornerstone task in computer vision, essential for applications such as image retrieval, stereo matching, 3D reconstruction, and SLAM. This survey comprehensively reviews modality-aware feature matching, exploring traditional handcrafted methods and emphasizing contemporary deep learning approaches across various modalities, including RGB images, depth images, 3D point clouds, LiDAR scans, medical images, and vision-language interactions. Traditional methods, leveraging detectors like Harris corners and descriptors such as SIFT and ORB, demonstrate robustness under moderate intra-modality variations but struggle with significant modality gaps. Contemporary deep learning-based methods, exemplified by learned detector-descriptors such as CNN-based SuperPoint and detector-free matchers such as transformer-based LoFTR, substantially improve robustness and adaptability across modalities. We highlight modality-aware advancements, such as geometric and depth-specific descriptors for depth images, sparse and dense learning methods for 3D point clouds, attention-enhanced neural networks for LiDAR scans, and specialized solutions like the MIND descriptor for complex medical image matching. Cross-modal applications, particularly in medical image registration and vision-language tasks, underscore the evolution of feature matching to handle increasingly diverse data interactions.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"8 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2026-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149397215","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Multiple Linear Regression Based on the Framework of Ordered Pair of Normalized Real Numbers 基于有序实数对框架的多元线性回归
IF 10.4 1区 计算机科学
IEEE transactions on neural networks and learning systems Pub Date : 2026-11-13 DOI: 10.1109/tnnls.2026.3746544
Yi Zheng, Yonglin Huang, Xiaoqin Pan, Hui Zhang, Lei Zhou
{"title":"Multiple Linear Regression Based on the Framework of Ordered Pair of Normalized Real Numbers","authors":"Yi Zheng, Yonglin Huang, Xiaoqin Pan, Hui Zhang, Lei Zhou","doi":"10.1109/tnnls.2026.3746544","DOIUrl":"https://doi.org/10.1109/tnnls.2026.3746544","url":null,"abstract":"","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"8 1","pages":"1-15"},"PeriodicalIF":10.4,"publicationDate":"2026-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149397145","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
UAV-Assisted LoRaWAN Connectivity for Vehicles on the Highway 无人机辅助LoRaWAN连接公路上的车辆
IF 10.6 1区 计算机科学
IEEE Internet of Things Journal Pub Date : 2026-11-13 DOI: 10.1109/jiot.2026.3753923
Zahra Mohtajollah, Jelena Mišić, Vojislav B. Mišić
{"title":"UAV-Assisted LoRaWAN Connectivity for Vehicles on the Highway","authors":"Zahra Mohtajollah, Jelena Mišić, Vojislav B. Mišić","doi":"10.1109/jiot.2026.3753923","DOIUrl":"https://doi.org/10.1109/jiot.2026.3753923","url":null,"abstract":"","PeriodicalId":54347,"journal":{"name":"IEEE Internet of Things Journal","volume":"24 1","pages":"1-1"},"PeriodicalIF":10.6,"publicationDate":"2026-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149397393","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
When Bandwidth Stops Buying Position Accuracy, and When It Starts Costing It 当带宽停止购买定位精度,当它开始花费它
IF 6.3 3区 计算机科学
IEEE Wireless Communications Letters Pub Date : 2026-11-13 DOI: 10.1109/lwc.2026.3753839
Unnikrishna Pillai
{"title":"When Bandwidth Stops Buying Position Accuracy, and When It Starts Costing It","authors":"Unnikrishna Pillai","doi":"10.1109/lwc.2026.3753839","DOIUrl":"https://doi.org/10.1109/lwc.2026.3753839","url":null,"abstract":"","PeriodicalId":13343,"journal":{"name":"IEEE Wireless Communications Letters","volume":"13 1","pages":"1-1"},"PeriodicalIF":6.3,"publicationDate":"2026-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149397624","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信
小红书