IEEE transactions on artificial intelligence最新文献

SMPL-GPTexture: Scalable, Training-Free SMPL Texture Synthesis With World Knowledge Transfer From GPT via Geometry-Aware Projection SMPL- gptexture：基于几何感知投影的GPT世界知识转移的可扩展、免训练的SMPL纹理合成

IEEE transactions on artificial intelligence Pub Date : 2026-10-01 Epub Date: 2026-04-28 DOI: 10.1109/TAI.2026.3688439

Mingxiao Tu;Shuchang Ye;Hoijoon Jung;Andre Kyme;Jinman Kim

{"title":"SMPL-GPTexture: Scalable, Training-Free SMPL Texture Synthesis With World Knowledge Transfer From GPT via Geometry-Aware Projection","authors":"Mingxiao Tu;Shuchang Ye;Hoijoon Jung;Andre Kyme;Jinman Kim","doi":"10.1109/TAI.2026.3688439","DOIUrl":"https://doi.org/10.1109/TAI.2026.3688439","url":null,"abstract":"Texturing 3-D human avatars from natural-language prompts remains challenging because generated UV texture maps must be both high-quality and semantically consistent with the prompt. Prior work typically retrains generative adversarial or diffusion models on curated datasets, which constrain generalization to clothing, stylistic, and cultural variations present in those datasets. To address these limitations, we present SMPL-GPTexture, a training-free pipeline that leverages the rich world knowledge of a pretrained GPT model to synthesize SMPL human textures. Given a tailored natural-language prompt, GPT-4o generates geometry-consistent front/back views; we fit SMPL to each view, and invert-rasterize colors into canonical UV space with a geometry-aware view-quality weight, and close remaining gaps with diffusion-based inpainting. On a 550-prompt benchmark, SMPL-GPTexture achieves +17.6% CLIP similarity and +22.4% BLIP improvement over state-of-the-art text-to-texture methods while reducing visible seam artifacts. It generalizes to diverse scenarios such as fantasy avatars, stylized body art, and specialized uniforms without domain-specific fine-tuning. This facilitates the generation of high-quality textures that surpass current text-to-texture pipelines for fashion prototyping, AR telepresence, and digital asset generation. We open-source a UV texture map dataset that covers 23 artistic styles, 49 professions, 19 ethnicities, and 67 clothing descriptors, and a set of easily adaptable prompt templates that can be repurposed to generate any desired texture, fostering research on prompt-driven avatar appearance.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"7 10","pages":"5551-5562"},"PeriodicalIF":0.0,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11495526","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097231","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Deep Learning-Guided Design of Optimal Sensor Networks for Accurate Pollutant Source Detection 基于深度学习的最优传感器网络精确污染源检测设计

IEEE transactions on artificial intelligence Pub Date : 2026-10-01 Epub Date: 2026-03-01 DOI: 10.1109/TAI.2026.3687177

Sidi Mohammed Alaoui;Khalifa Djemal;Amir Ali Feiz;Ehsan Sedgh Gooya

{"title":"Deep Learning-Guided Design of Optimal Sensor Networks for Accurate Pollutant Source Detection","authors":"Sidi Mohammed Alaoui;Khalifa Djemal;Amir Ali Feiz;Ehsan Sedgh Gooya","doi":"10.1109/TAI.2026.3687177","DOIUrl":"https://doi.org/10.1109/TAI.2026.3687177","url":null,"abstract":"Efficient sensor network design for atmospheric pollution source localization remains a major challenge in environmental monitoring. Selecting optimal sensor locations from numerous candidates is difficult under complex spatial and atmospheric conditions. Traditional methods, including trajectory-based metaheuristics and evolutionary algorithms, often entail high computational costs and limited scalability. To overcome these limitations, we propose the prediction of optimal sensor configurations (POSCs), a data-driven framework that reformulates sensor placement as a prediction problem. POSC operates in two stages. First, large-scale Gaussian plume simulations are performed to generate concentration maps. Then, a genetic algorithm (GA) is applied under varying atmospheric conditions to obtain multiple candidate optimal sensor configurations. The resulting supervised dataset pairs concentration fields with their corresponding optimal networks. Second, the data are used to predict new probability maps of sensor relevance, providing a framework that highlights the most informative sensor locations across scenarios through a convolutional self-attention residual network (CSAResNet). The model is first evaluated on its ability to predict probability maps of optimal sensor locations, reaching an AUC of 0.95. From these maps, a subset of sensors is selected, enabling source detection performance comparable to evolutionary methods (GA) while providing real-time prediction at negligible computational cost.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"7 10","pages":"5445-5456"},"PeriodicalIF":0.0,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097406","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Unifying Data, Memory, and Compute Efficiency in LLM Training: A Survey LLM训练中统一数据、内存和计算效率：综述

IEEE transactions on artificial intelligence Pub Date : 2026-10-01 Epub Date: 2026-06-11 DOI: 10.1109/TAI.2026.3702625

Vanessa Schmidt;Huy Hoang Nguyen;Cédric Jung;Shirin Salehi;Anke Schmeink

{"title":"Unifying Data, Memory, and Compute Efficiency in LLM Training: A Survey","authors":"Vanessa Schmidt;Huy Hoang Nguyen;Cédric Jung;Shirin Salehi;Anke Schmeink","doi":"10.1109/TAI.2026.3702625","DOIUrl":"https://doi.org/10.1109/TAI.2026.3702625","url":null,"abstract":"Resource constraints increasingly determine what can be trained, fine-tuned, and deployed in large language models (LLMs), yet efficiency is often studied through isolated techniques rather than as an interacting system of limits. This survey adopts a constraint-centric perspective and organizes recent progress around three coupled bottlenecks: 1) data efficiency (what to train on); 2) memory efficiency (how to fit training); and 3) compute budget awareness [when and where to spend floating-point operations (FLOPs)]. On the data axis, we review selection and pruning methods that maximize learning per token, ranging from scalable proxy signals based on learning dynamics to gradient- and influence-based scoring, as well as difficulty-aware and curriculum-style strategies. We highlight emerging evidence that different notions of “good data” dominate in different regimes, implying that optimal subsets depend on the task objective and resource budget rather than being universal. On the systems side, we show that GPU memory, not raw compute, is often the dominant bottleneck in fine-tuning, and that effective scaling requires jointly reducing weight storage, optimizer states, and activation memory rather than optimizing any single component in isolation. Beyond memory, we frame training and inference as compute-governed processes in which optimization, data selection, and decoding must explicitly account for finite FLOP budgets. We review evidence for compute-optimal allocation and stopping rules, where computation should be halted or reallocated once marginal performance gains fall below a budget-dependent threshold. Together, these results unify compute-aware data selection, scaling laws, and adaptive inference under a common principle of resource-conditioned decision-making.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"7 10","pages":"5338-5358"},"PeriodicalIF":0.0,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097717","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

MetaFusion: Instance-Aware Meta-Prompting and Token Refinement for VLMs Generalization 元融合：用于VLMs泛化的实例感知元提示和令牌细化

IEEE transactions on artificial intelligence Pub Date : 2026-10-01 Epub Date: 2026-04-28 DOI: 10.1109/TAI.2026.3686093

Mushui Liu;Fangtai Wu;Ziqian Lu;Zhao Wang;Yunlong Yu;Jungong Han;Zhongfei Zhang

{"title":"MetaFusion: Instance-Aware Meta-Prompting and Token Refinement for VLMs Generalization","authors":"Mushui Liu;Fangtai Wu;Ziqian Lu;Zhao Wang;Yunlong Yu;Jungong Han;Zhongfei Zhang","doi":"10.1109/TAI.2026.3686093","DOIUrl":"https://doi.org/10.1109/TAI.2026.3686093","url":null,"abstract":"The rapid advancement of vision-language models (VLMs) has highlighted challenges in efficiently adapting these models to downstream tasks, where existing prompt-based fine-tuning (PFT) methods suffer from limited generalization to unseen classes due to homogeneous prompt representations and superficial prompt-feature interactions. To address these issues, we propose MetaFusion, a plug-and-play adapter module that jointly optimizes context-aware meta-prompt generation and feature refinement for enhanced visual-language alignment. Our method introduces a MetaNet to dynamically produce instance-specific meta-prompts from visual features, coupled with token aggregation guided with meta prompts (TAMPs) that semantically clusters and selects discriminative visual tokens through meta-prompt-guided grouping. In addition, a feature refinement module (FRM) fuses meta-prompts with visual features via cross-attention to amplify task-critical regions while suppressing background noise. Extensive experiments on 11 datasets demonstrate that MetaFusion significantly improves generalization capabilities when integrated with existing PFT frameworks, achieving state-of-the-art performance across zero-shot, few-shot, and domain-shift scenarios.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"7 10","pages":"5404-5416"},"PeriodicalIF":0.0,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097224","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Fair Recourse for All: Ensuring Individual and Group Fairness in Counterfactual Explanations 人人享有公平追索权：在反事实解释中确保个人和群体的公平

IEEE transactions on artificial intelligence Pub Date : 2026-10-01 Epub Date: 2026-04-27 DOI: 10.1109/TAI.2026.3688207

Fatima Ezzeddine;Obaida Ammar;Silvia Giordano;Omran Ayoub

{"title":"Fair Recourse for All: Ensuring Individual and Group Fairness in Counterfactual Explanations","authors":"Fatima Ezzeddine;Obaida Ammar;Silvia Giordano;Omran Ayoub","doi":"10.1109/TAI.2026.3688207","DOIUrl":"https://doi.org/10.1109/TAI.2026.3688207","url":null,"abstract":"Explainable artificial intelligence (XAI) is becoming increasingly essential for enhancing the transparency of machine learning (ML) models. Among the various XAI techniques, counterfactual explanations (CFs) hold a pivotal role due to their ability to illustrate how changes in input features can alter an ML model’s decision, thereby offering actionable recourse to users. Ensuring that individuals with comparable attributes and those belonging to different protected groups (e.g., demographic) receive similar and actionable recourse options is essential for trustworthy and fair decision-making. In this work, we address this challenge directly by focusing on the generation of fair CFs. Specifically, we start by defining and formulating fairness at: 1) individual fairness, ensuring that similar individuals receive similar CFs; 2) group fairness, ensuring equitable CFs across different protected groups; and 3) hybrid fairness, which accounts for both individual and broader group-level fairness. We formulate the problem as an optimization task and propose a novel model-agnostic, reinforcement learning based approach to generate CFs that satisfy fairness constraints at both the individual and group levels, two objectives that are usually treated as orthogonal. As fairness metrics, we extend existing metrics commonly used for auditing ML models, such as equal choice of recourse and equal effectiveness across individuals and groups. We evaluate our approach on four benchmark datasets, showing that it effectively ensures individual and group fairness while preserving the quality of the generated CFs in terms of proximity and plausibility. Our work opens a broader discussion on hybrid fairness and its role and implications for XAI and beyond CFs.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"7 10","pages":"5496-5511"},"PeriodicalIF":0.0,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097411","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Fully Distributed Event-Triggered Secure Consensus of Multiagent Systems Under Hybrid Cyber-Attacks 混合网络攻击下多智能体系统的全分布式事件触发安全一致性

IEEE transactions on artificial intelligence Pub Date : 2026-10-01 Epub Date: 2026-04-20 DOI: 10.1109/TAI.2026.3685669

Xiaoyang Liu;Xiangqin Kong;Shaofu Yang;Wenwu Yu

引用次数: 0

PersoBench: Benchmarking Personalized Response Generation in Large Language Models personbench：对大型语言模型中的个性化响应生成进行基准测试

IEEE transactions on artificial intelligence Pub Date : 2026-10-01 Epub Date: 2026-04-30 DOI: 10.1109/TAI.2026.3689823

Saleh Afzoon;Zahra Jamali;Usman Naseem;Amin Beheshti

{"title":"PersoBench: Benchmarking Personalized Response Generation in Large Language Models","authors":"Saleh Afzoon;Zahra Jamali;Usman Naseem;Amin Beheshti","doi":"10.1109/TAI.2026.3689823","DOIUrl":"https://doi.org/10.1109/TAI.2026.3689823","url":null,"abstract":"While large language models (LLMs) have exhibited impressive conversational capabilities, their proficiency in delivering personalized responses remains unclear. Although recent benchmarks automatically evaluate persona consistency in role-playing contexts using LLM-based judgment, the evaluation of personalization in response generation remains underexplored. To address this gap, we present an automated benchmarking pipeline, PersoBench, to evaluate the personalization ability of LLMs in persona-aware dialogue generation within a zero-shot setting. Our framework employs a structured pipeline comprising speaker-aware annotation, task-specific and context-driven prompt construction, response postprocessing, and automated evaluation across multiple dimensions of generation quality. In particular, the pipeline performs text preprocessing and speaker labeling, constructs structured prompts with task instructions and LLM roles, validates response format, and evaluates valid outputs across fluency, personalization, diversity, and coherence. We assess the performance of four open-source and four closed-source LLMs using well-known datasets and a range of explicit metrics. Our findings reveal that while LLMs excel at generating fluent and diverse responses, they are far from satisfactory in delivering personalized and coherent responses, considering both the conversation context and the provided personas.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"7 10","pages":"5587-5596"},"PeriodicalIF":0.0,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097673","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Relational Feature Modeling: Enhancing Predictive Learning Through Network-Based Features Augmentation 关系特征建模：通过基于网络的特征增强增强预测学习

IEEE transactions on artificial intelligence Pub Date : 2026-10-01 Epub Date: 2026-04-27 DOI: 10.1109/TAI.2026.3687508

Ankur Kumar Singhal;Anurag Singh

{"title":"Relational Feature Modeling: Enhancing Predictive Learning Through Network-Based Features Augmentation","authors":"Ankur Kumar Singhal;Anurag Singh","doi":"10.1109/TAI.2026.3687508","DOIUrl":"https://doi.org/10.1109/TAI.2026.3687508","url":null,"abstract":"Feature representation and augmentation are central factors for improving predictive accuracy of the prediction model, particularly in domains constrained by limited data availability, such as agriculture and biological systems. Data scarcity, usually caused by annotation costs, variability in environmental factors, and the rarity of critical events, restricts the effectiveness of conventional models. While traditional prediction models perform well in data-rich scenarios, their performance degrades in small-data scenarios, leading to reduced predictive accuracy. To address limitations, a network-based feature augmentation prediction framework is proposed for small-data scenarios. An instance-specific parenclitic network is constructed for each data instance by modeling deviations among features, where nodes represent features and edges show the pairwise relationships. Further, three important structural descriptors edge count (global connectivity), entropy centrality (dispersion of influence), and clustering coefficient (local cohesiveness) are extracted and concatenated with the original feature vector to form an augmented representation. The augmented data are then modelled using a regularised multivariate Gaussian distribution, with class-conditional likelihoods. The framework is evaluated on three different datasets and performs better than the baseline methods, with accuracy improvements of 5.1%, 5.6%, and 4.0%. Additional analyses using residual and contour plots confirmed improved stability and interpretability, showing the proposed model is scalable and effective across domains with limited data.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"7 10","pages":"5472-5481"},"PeriodicalIF":0.0,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149096993","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Memristive Hopfield Bi-Neurons Under External Stimuli and Data Privacy Application 外部刺激下记忆Hopfield双神经元及其数据隐私应用

IEEE transactions on artificial intelligence Pub Date : 2026-10-01 Epub Date: 2025-11-06 DOI: 10.1109/TAI.2025.3630118

Bertrand Frederick Boui A Boya;Lyudmila Klimentyevna Babenko;Jacques Kengne;Joseph Mvogo Ngono;Jean de Dieu Nkapkop;Arnaud Nanfak;Joseph Yves Effa

{"title":"Memristive Hopfield Bi-Neurons Under External Stimuli and Data Privacy Application","authors":"Bertrand Frederick Boui A Boya;Lyudmila Klimentyevna Babenko;Jacques Kengne;Joseph Mvogo Ngono;Jean de Dieu Nkapkop;Arnaud Nanfak;Joseph Yves Effa","doi":"10.1109/TAI.2025.3630118","DOIUrl":"https://doi.org/10.1109/TAI.2025.3630118","url":null,"abstract":"As medical imaging technology improves, protecting sensitive biomedical images during transmission and storage is becoming more important. Traditional encryption methods often struggle with efficiency and flexibility, especially when dealing with the large datasets typical in this field. This study explores using memristive Hopfield networks for encrypting biomedical images, leveraging their natural abilities for memory and pattern recognition. We examine how electromagnetic radiation and stimulating currents influence the behavior of these networks. Our results show that the model can reach multiple stable and unstable states, producing different patterns, including limit cycles and chaotic structures with various forms (like two-scroll, three-scroll, and four-scroll chaos). Notably, stimulating currents create uneven dynamic behavior. The model also reveals various patterns related to synaptic connections, which could provide insights into neurological diseases. To confirm our findings, we built a digital hardware device that successfully replicated these patterns. We also used a compressive sensing (CS) method to compress and encrypt biomedical images with the chaotic sequences generated by the model. Our experiments show that this encryption method is robust against various attacks with high key space, making it a good option for secure communication.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"7 10","pages":"5359-5369"},"PeriodicalIF":0.0,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097386","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Explainable AI for Mental Disorder Detection on Social Media: A Survey and Outlook 社交媒体上可解释的人工智能精神障碍检测：调查与展望

IEEE transactions on artificial intelligence Pub Date : 2026-10-01 Epub Date: 2026-04-28 DOI: 10.1109/TAI.2026.3688443

Yusif Ibrahimov;Tarique Anwar;Tommy Yuan

{"title":"Explainable AI for Mental Disorder Detection on Social Media: A Survey and Outlook","authors":"Yusif Ibrahimov;Tarique Anwar;Tommy Yuan","doi":"10.1109/TAI.2026.3688443","DOIUrl":"https://doi.org/10.1109/TAI.2026.3688443","url":null,"abstract":"Mental health (MH) is a complex global challenge. The widespread use of online social media (OSM) provides a rich source of data for supporting MH analytics. This article presents a comprehensive review of AI- and data-driven approaches for mental disorder detection (MDD) using OSM, with a particular focus on explainable artificial intelligence (XAI). We summarize traditional diagnostic practices and provide an integrated overview of modern deep learning models, emphasizing how their growing complexity increases the need for transparent and trustworthy explanations. We review a wide range of explainability techniques applied in this domain, including interpretable models, post-hoc attribution methods, attention- and graph-based explanations, and emerging LLM-driven approaches, and outline commonly used datasets and evaluation practices. Finally, we identify key challenges such as data limitations, bias, and the need for clinically meaningful explanations, and propose directions for future research. This survey offers a comprehensive foundation for developing explainable, reliable, and ethically informed MDD systems for social media.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"7 10","pages":"5299-5319"},"PeriodicalIF":0.0,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097532","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0