Journal of Information and Intelligence最新文献_第2页

Distributed iterative learning control for heterogeneous parametric uncertain multi-agent systems with unknown control directions 控制方向未知的异构参数不确定多智能体系统的分布式迭代学习控制

Journal of Information and Intelligence Pub Date : 2026-05-01 Epub Date: 2025-03-25 DOI: 10.1016/j.jiixd.2025.02.005

Yingping Li , Jiaxi Chen , Junmin Li , Weisheng Chen , Shuai Zhang , Wensheng Chi

{"title":"Distributed iterative learning control for heterogeneous parametric uncertain multi-agent systems with unknown control directions","authors":"Yingping Li , Jiaxi Chen , Junmin Li , Weisheng Chen , Shuai Zhang , Wensheng Chi","doi":"10.1016/j.jiixd.2025.02.005","DOIUrl":"10.1016/j.jiixd.2025.02.005","url":null,"abstract":"<div><div>This paper addresses the challenge of achieving accurate consensus control in heterogeneous linear parametric uncertain multi-agent systems, particularly in the presence of unknown control directions. To tackle this issue, we propose a distributed consensus protocol that integrates adaptive iterative learning control with the characteristics of Nussbaum gain functions. This novel approach not only enhances the robustness of the control system but also ensures convergence in the presence of uncertainties. Building upon this foundation, we extend our study to address the consensus problem in heterogeneous multi-agent systems under actuator failures. To overcome the issue of matrix multiplication between agents with different dimensions, we introduce a matrix dimension expansion method, which allows us to design a new equivalent matrix relation. Additionally, to ensure that the energy function decays with the number of iterations, we reconstruct the quadratic function used in the theoretical analysis based on matrix analysis theory. Through simulation examples, we demonstrate the effectiveness of our proposed theoretical framework, highlighting its practical applicability and novelty in the field of multi-agent systems control.</div></div>","PeriodicalId":100790,"journal":{"name":"Journal of Information and Intelligence","volume":"4 3","pages":"Pages 236-250"},"PeriodicalIF":0.0,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148183586","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

Sinkhorn imputation-based deep reinforcement learning approach for radio frequency parameter optimizations 基于Sinkhorn的射频参数优化深度强化学习方法

Journal of Information and Intelligence Pub Date : 2026-03-01 Epub Date: 2025-12-29 DOI: 10.1016/j.jiixd.2025.12.006

Shihao Jia , Keqin Zhang , Zhiwei Chen , Xiaohu Ge

{"title":"Sinkhorn imputation-based deep reinforcement learning approach for radio frequency parameter optimizations","authors":"Shihao Jia , Keqin Zhang , Zhiwei Chen , Xiaohu Ge","doi":"10.1016/j.jiixd.2025.12.006","DOIUrl":"10.1016/j.jiixd.2025.12.006","url":null,"abstract":"<div><div>With the evolution of fifth-generation (5G) and upcoming sixth-generation (6G) mobile communication systems, the design of the air interface must take into account two primary objectives: flexibility and low power consumption. Under a flexible physical-layer architecture, the joint configuration of the associated communication parameters becomes increasingly complex. Traditional optimization methods often focus on a single parameter, which fail to capture the intricate coupling between the baseband and Radio Frequency (RF) parameters. To address this issue, the multiple RF parameter-aware power consumption minimization is formulated as a black-box nonlinear optimization problem. To solve the formulated problem, the RF data imputation-based Deep Reinforcement Learning (DRL) technique is proposed to reduce the power consumption by jointly optimizing the parameters of bandwidth, number of data streams, precoding scheme, number of RF chains, DAC resolution, and the transmit power. In particular, an optimal transport imputation technique is introduced to estimate the relationship between the mentioned RF parameters and the power consumption, data rate, and the adjacent channel leakage ratio, which will output a complete RF lookup table. Based on the estimated lookup table, the Deep Q-Network (DQN) is trained efficiently to output a flexible RF configuration policy. This procedure is summarized as a two-stage approach, referred to as the Sinkhorn imputation-based DRL method. Simulation results demonstrate that the proposed approaches achieve average power reductions of 60.8% and 59.3%, respectively, compared to typical 5G configurations. Moreover, relative to the RF switch-off scheme commonly used in practice, the proposed approaches still provide additional power savings of 47.7% and 46.6%, respectively.</div></div>","PeriodicalId":100790,"journal":{"name":"Journal of Information and Intelligence","volume":"4 2","pages":"Pages 87-106"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147636761","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

EMSTS-Pos: AI-driven indoor positioning with enhanced-multipath space-time structural features in O-RAN system EMSTS-Pos: O-RAN系统中具有增强多径时空结构特征的ai驱动室内定位

Journal of Information and Intelligence Pub Date : 2026-03-01 Epub Date: 2026-01-01 DOI: 10.1016/j.jiixd.2025.12.011

Anpei Li , Luhan Wang , Na Li , Bingxuan Li , Minchi Ruan , Zhaoming Lu , Jingguo Zhao , Raymond Knopp

{"title":"EMSTS-Pos: AI-driven indoor positioning with enhanced-multipath space-time structural features in O-RAN system","authors":"Anpei Li , Luhan Wang , Na Li , Bingxuan Li , Minchi Ruan , Zhaoming Lu , Jingguo Zhao , Raymond Knopp","doi":"10.1016/j.jiixd.2025.12.011","DOIUrl":"10.1016/j.jiixd.2025.12.011","url":null,"abstract":"<div><div>Driven by the integration of wider bandwidths and massive antenna arrays, mobile cellular networks demonstrate significant potential for supporting high-precision positioning functionalities. This article introduces the EMSTS (Enhanced-Multipath Space-Time Structural) feature set, which is a substantial extension of our prior conference work SPSTS (Strongest-Path Space-Time Structural) feature set. Our solution achieves robust and precise positioning in real-world indoor environments. The core methodology involves extracting the relative time-delay differences using uplink Sounding Reference Signals (SRS).</div><div>Although the baseline SPSTS-Pos achieved superior positioning accuracy on both validation datasets and real-time system, with 50th and 90th percentile Cumulative Distribution Function (CDF) errors of 0.054 m and 0.228 m, its sole reliance on the strongest Multipath Component (MPC) resulted in inadequate tail performance, leading to a Maximum Absolute Error (MAXE) reaching 2.743 m and the 95th percentile CDF error reaching approximately 0.7 m. To resolve this reliability issue, we propose the EMSTS-Pos method with three major technical enhancements: (1) The feature set is expanded to EMSTS by incorporating the relative indices of the 1st, 2nd, and 3rd strongest MPC to enhance spatial redundancy. (2) A custom, knowledge-driven channel attention mechanism is introduced to apply a non-random weight bias, prioritizing the most discriminative path information. (3) We utilize comprehensive data robustness methods, including temporal forward filling for raw data outlier suppression and Gaussian noise regularization on coordinates.</div><div>The EMSTS feature maintained the strong average performance of the SPSTS baseline while achieving a substantial enhancement in CDF95% of 0.45 m and MAXE of 1.10 m, resolving the critical “tail effect” issue.</div></div>","PeriodicalId":100790,"journal":{"name":"Journal of Information and Intelligence","volume":"4 2","pages":"Pages 122-135"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147636763","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

Two-timescale hierarchical DRL for resource allocation in UAV-assisted 6G edge networks 无人机辅助6G边缘网络资源分配的双时间尺度分层DRL

Journal of Information and Intelligence Pub Date : 2026-03-01 Epub Date: 2026-01-23 DOI: 10.1016/j.jiixd.2026.01.001

Jiaxin Liu , Kai Liang , Liqiang Zhao , Huixian Gu , Wei Guo

{"title":"Two-timescale hierarchical DRL for resource allocation in UAV-assisted 6G edge networks","authors":"Jiaxin Liu , Kai Liang , Liqiang Zhao , Huixian Gu , Wei Guo","doi":"10.1016/j.jiixd.2026.01.001","DOIUrl":"10.1016/j.jiixd.2026.01.001","url":null,"abstract":"<div><div>Integrating Unmanned Aerial Vehicles (UAVs) into Mobile Edge Computing (MEC) systems offers a promising solution to enhance coverage and flexibility in 6G edge networks. However, the dynamic and resource-limited nature of UAVs introduces strong cross-layer coupling between UAV-Access Point (AP) coordination and AP-user scheduling, making efficient resource allocation highly challenging. To address this issue, this paper proposes a unified two-timescale hierarchical Deep Reinforcement Learning (DRL) framework that jointly optimizes channel utilization and transmission latency. Unlike conventional hierarchical decompositions that separate large- and small-timescale decisions, the proposed method models UAV-AP interactions as an integrated optimization process to preserve global consistency and avoid local optima. A dual-layer architecture is designed, where the UAV-level agent performs large-timescale bandwidth allocation and the AP-level agents conduct fine-grained small-timescale scheduling. To mitigate the exponential complexity caused by nested DRL updates, an asynchronous cross-timescale coordination mechanism is introduced, enabling stable convergence and efficient learning. Simulation results demonstrate that the proposed framework achieves superior performance in channel utilization, delay reduction, and robustness under dynamic traffic conditions compared with single-agent, prediction-based, and heuristic baselines.</div></div>","PeriodicalId":100790,"journal":{"name":"Journal of Information and Intelligence","volume":"4 2","pages":"Pages 136-147"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147636757","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

Dynamic access strategy in integrated satellite-terrestrial networks using attention-based DRL 基于关注DRL的星地融合网络动态接入策略

Journal of Information and Intelligence Pub Date : 2026-03-01 Epub Date: 2026-02-10 DOI: 10.1016/j.jiixd.2026.01.002

Hao Qin, Haoyu Sun, Yaochen Liu, Quan Shi, Bin Song

{"title":"Dynamic access strategy in integrated satellite-terrestrial networks using attention-based DRL","authors":"Hao Qin, Haoyu Sun, Yaochen Liu, Quan Shi, Bin Song","doi":"10.1016/j.jiixd.2026.01.002","DOIUrl":"10.1016/j.jiixd.2026.01.002","url":null,"abstract":"<div><div>As the sixth-generation (6G) mobile communication network evolves toward a satellite-terrestrial integrated architecture, Low Earth Orbit (LEO) satellite systems have become a crucial component of Integrated Satellite-Terrestrial Networks (ISTNs) due to their cost efficiency and wide-area coverage. However, in the context of spectrum sharing, ISTNs face significant challenges, including complex Co-Channel Interference (CCI) and dynamically varying traffic demands. To address these issues, this paper proposes a satellite-terrestrial collaborative user access selection algorithm that combines Reverse Matching (RM) with Deep Reinforcement Learning (DRL). By incorporating an interference threshold within the scheduling framework, the algorithm effectively decouples the strong interdependencies between satellite and terrestrial resources. On the satellite system, a Transformer-based model employing multi-head attention is introduced to capture the spatiotemporal correlations between beams and users. On the terrestrial system, a user access scheme based on RM is proposed, which adjusts the uplink-downlink spectrum association between satellite and terrestrial systems to transform interference from base stations to satellite users into inter-user interference, thereby enhancing terrestrial communication performance. Simulation results demonstrate that the proposed algorithm significantly outperforms benchmark schemes in terms of system throughput and user satisfaction.</div></div>","PeriodicalId":100790,"journal":{"name":"Journal of Information and Intelligence","volume":"4 2","pages":"Pages 148-168"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147636758","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

GNN-SSER: Graph neural networks with self-attention and session enhanced representation for session-based recommendation GNN-SSER：基于会话推荐的自关注和会话增强表示的图神经网络

Journal of Information and Intelligence Pub Date : 2026-03-01 Epub Date: 2025-07-04 DOI: 10.1016/j.jiixd.2025.06.005

Qiang Tian , Caihong Mu , Yi Liu , Jialiang Zhou

{"title":"GNN-SSER: Graph neural networks with self-attention and session enhanced representation for session-based recommendation","authors":"Qiang Tian , Caihong Mu , Yi Liu , Jialiang Zhou","doi":"10.1016/j.jiixd.2025.06.005","DOIUrl":"10.1016/j.jiixd.2025.06.005","url":null,"abstract":"<div><div>Session-Based Recommendation (SBR) is a technically demanding task that aims to recommend items based on sequences of anonymous behaviors. Graph Neural Networks (GNNs) have demonstrated significant potential in SBR through constructing graphs from behavioral sequences. GNN-based recommendation models mainly involve message recursively passing along item-item interaction edges to refine encoded embeddings. While GNN-based methods have shown effectiveness, they face challenges such as constrained receptive fields and noisy, irrelevant connections. Transformer-based models are superior in adaptively and globally aggregating information. In addition, it is also critically important for SBR methods to leverage information beyond the current session. Navigating these challenges, we propose a novel model for SBR called Graph Neural Networks with Self-Attention and Session Enhanced Representation (GNN-SSER). GNN-SSER alternates between Transformer and GNN layers to enhance their capabilities mutually. In particular, GNN-SSER utilizes Transformer layers to expand the receptive field, allowing aggregation of information from more pertinent nodes, thus improving the message passing in GNNs. In addition, we propose a Session Enhanced Channel (SEC) to utilize the inter-session information. Comprehensive experiments show that GNN-SSER delivers better performance than other state-of-the-art models.</div></div>","PeriodicalId":100790,"journal":{"name":"Journal of Information and Intelligence","volume":"4 2","pages":"Pages 169-181"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147636759","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

Ellipse fitting meets AI-RAN: Robust non-parametric compensation of joint transmitter and receiver in-phase and quadrature imbalance 椭圆拟合满足AI-RAN：联合收发器相位和正交不平衡的鲁棒非参数补偿

Journal of Information and Intelligence Pub Date : 2026-03-01 Epub Date: 2025-12-30 DOI: 10.1016/j.jiixd.2025.12.007

Jiaye Li , Yun Liu , Ruiliang Song , Xiaoyi Yu , Zihan Cen , Xuebin Zhuang , Xiang Chen

{"title":"Ellipse fitting meets AI-RAN: Robust non-parametric compensation of joint transmitter and receiver in-phase and quadrature imbalance","authors":"Jiaye Li , Yun Liu , Ruiliang Song , Xiaoyi Yu , Zihan Cen , Xuebin Zhuang , Xiang Chen","doi":"10.1016/j.jiixd.2025.12.007","DOIUrl":"10.1016/j.jiixd.2025.12.007","url":null,"abstract":"<div><div>In-phase and Quadrature (IQ) modulation is a cornerstone of modern wireless communication systems, underpinning high-order modulation formats and spectrally efficient transmission. However, inevitable analog imperfections in RF front-ends introduce amplitude mismatches and phase deviations, leading to constellation distortion and severe degradation in demodulation performance. The challenge becomes particularly acute when IQ imbalances arise simultaneously at both the transmitter (Tx) and receiver (Rx), as conventional receiver-side compensation schemes are unable to cope with the compounded impairments. This problem is of growing significance in the emerging paradigm of AI-driven Radio Access Networks (AI-RAN), where reliable physical-layer signals form the foundation for data-driven control and optimization in RAN Intelligent Controllers (RICs). To address these issues, we propose an efficient correction framework based on ellipse fitting and affine transformation, which avoids explicit estimation of imbalance parameters. The distorted constellation is geometrically fitted to an ellipse, transformed to restore circular symmetry, and refined through phase correction. Simulation results with 16-QAM modulation demonstrate that the proposed method achieves performance comparable to conventional schemes in receiver-only scenarios while exhibiting superior robustness to joint Tx/Rx distortions. By delivering clean and interpretable signal constellations with low computational complexity, the approach not only preserves physical-layer fidelity but also enhances the reliability of AI-RAN workflows, positioning impairment correction as a lightweight yet critical enabler for next-generation intelligent wireless networks.</div></div>","PeriodicalId":100790,"journal":{"name":"Journal of Information and Intelligence","volume":"4 2","pages":"Pages 107-121"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147636762","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

Towards transparent 6G AI-RAN: A survey on explainable deep reinforcement learning for intelligent network slicing 走向透明的6G AI-RAN：智能网络切片可解释深度强化学习研究综述

Journal of Information and Intelligence Pub Date : 2026-01-01 Epub Date: 2025-12-29 DOI: 10.1016/j.jiixd.2025.12.005

Shuaishuai Guo , Yutong Zhong , Zhenyu Feng , Shengqi Kang , Jichao Chen

{"title":"Towards transparent 6G AI-RAN: A survey on explainable deep reinforcement learning for intelligent network slicing","authors":"Shuaishuai Guo , Yutong Zhong , Zhenyu Feng , Shengqi Kang , Jichao Chen","doi":"10.1016/j.jiixd.2025.12.005","DOIUrl":"10.1016/j.jiixd.2025.12.005","url":null,"abstract":"<div><div>The advent of the sixth generation (6G) wireless networks envisions an Artificial Intelligence (AI)-native Radio Access Network (AI-RAN), where Deep Reinforcement Learning (DRL) emerges as a key enabler for intelligent and autonomous network slicing. Despite the demonstrated performance gains of DRL-based solutions in dynamic resource allocation and slice orchestration, their opaque decision-making nature raises critical concerns regarding trust, accountability, and operational deployment. To bridge this gap, Explainable Deep Reinforcement Learning (XDRL) has recently attracted significant attention as a means to enhance transparency, interpretability, and controllability of AI-RAN slicing policies. This survey provides a comprehensive overview of the state of the art in explainable DRL for intelligent network slicing. We first review the fundamental principles of DRL in the context of RAN slicing and identify the unique explainability challenges posed by high-dimensional, multi-slice environments. We then categorize existing XDRL approaches into post-hoc explanation, symbolic abstraction, and human-in-the-loop steering, analyzing their methodologies, strengths, and limitations. Furthermore, we highlight benchmark environments and experimental testbeds that have been employed to evaluate XDRL in realistic network scenarios. Finally, we outline key open challenges, including scalability, generalization across traffic patterns, integration with Large Language Models (LLMs), and alignment with intent-based networking, and discuss promising research directions toward achieving transparent, trustworthy, and human-centric AI-RAN in 6G.</div></div>","PeriodicalId":100790,"journal":{"name":"Journal of Information and Intelligence","volume":"4 1","pages":"Pages 23-37"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147416191","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

Artificial Intelligence-native Radio Access Networks (AI-RAN): Foundations, methodologies, and applications 人工智能原生无线接入网络（AI-RAN）：基础、方法和应用

Journal of Information and Intelligence Pub Date : 2026-01-01 Epub Date: 2026-01-02 DOI: 10.1016/j.jiixd.2025.12.012

Chenxi Liu, Howard H. Yang, Kun Guo, Wenchao Xia, Chenyuan Feng, Tony Q.S. Quek

引用次数: 0

Fast collaborative inference via distributed speculative decoding 基于分布式推测解码的快速协同推理

Journal of Information and Intelligence Pub Date : 2026-01-01 Epub Date: 2026-01-10 DOI: 10.1016/j.jiixd.2025.12.008

Ce Zheng , Ke Zhang , Chen Sun , Wenqi Zhang , Qiong Liu , Angesom Ataklity Tesfay

{"title":"Fast collaborative inference via distributed speculative decoding","authors":"Ce Zheng , Ke Zhang , Chen Sun , Wenqi Zhang , Qiong Liu , Angesom Ataklity Tesfay","doi":"10.1016/j.jiixd.2025.12.008","DOIUrl":"10.1016/j.jiixd.2025.12.008","url":null,"abstract":"<div><div>Speculative decoding accelerates Large Language Model (LLM) inference by allowing a lightweight draft model to predict multiple future tokens that are subsequently verified by a larger target model. In AI-native Radio Access Networks (AI-RAN), this mechanism naturally enables device-edge collaborative inference. However, existing distributed speculative decoding schemes incur significant uplink communication overhead, as they require transmitting full-vocabulary logits at every decoding step. To address this challenge, we propose a sparsify-then-sample strategy, termed Truncated Sparse Logits Transmission (TSLT), which transmits only the logits and indices of a truncated candidate set. We provide theoretical guarantees showing that TSLT preserves the acceptance rate of speculative decoding. The proposed framework is further extended to a multi-candidate setting, where multiple draft candidates per step increase the acceptance probability. Extensive experiments demonstrate that TSLT substantially reduces uplink communication while maintaining end-to-end inference latency and model quality, validating its effectiveness for scalable and communication-efficient distributed LLM inference in future AI-RAN systems.</div></div>","PeriodicalId":100790,"journal":{"name":"Journal of Information and Intelligence","volume":"4 1","pages":"Pages 67-85"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147416193","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