arXiv subjects

Hina Tabassum

Publications and source records attributed to Hina Tabassum.

At least 19 recordsLinked to original sources

arXiv2026

Characterization of Beam-Squint and Beam-Split Effects in RIS-assisted Multi-Frequency Networks

Multi-frequency operation in beyond-5G and 6G systems renders the beam directions of large-aperture arrays frequency-dependent, giving rise to beam misalignment effects critical for reconfigurable intelligent surfaces (RISs). When an RIS phase profile is configured at one frequency but illuminated at another, the reflected field may exhibit main-lobe deviation and additional dominant lobes, degrading beamforming performance. In this paper, we develop a unified analytical framework to characterize these effects for uniform planar array-based RISs under both continuous and finite-resolution phase control. We formalize beam-squint as the deviation of the maximum-gain beam from the desired elevation-azimuth angle pair and beam-split as the emergence of additional maximum-gain beams under frequency mismatch and quantization. For continuous-phase RISs, we derive necessary and sufficient peak conditions, obtain closed-form elevation-azimuth peak families, and establish feasibility conditions as functions of the frequency ratio, incidence and configuration angles, and element spacing. Extending the analysis to b-bit phase quantization, we express the quantized beampattern as a superposition of harmonic array responses via Fourier expansion of the quantization-error phasor, leading to closed-form per-harmonic peak families, dominance ordering, and feasibility conditions. To capture peak displacement induced by harmonic superposition, we further develop a perturbation-based correction leveraging dominant-harmonic curvature and residual-harmonic gradients, improving peak-location accuracy without exhaustive two-dimensional searches. Numerical simulations validate the analysis, quantify peak deviations and beam-split probabilities, and demonstrate sum-rate gains by including analytically predicted squinted/split and harmonic candidates in multi-RIS, multi-user, multi-band networks.

eess.SP↗

arXiv2026

Intelligent Multi-UAV Navigation in ITNTNs: A Hierarchical LLM Approach

The deployment of high-speed Uncrewed Aerial Vehicles (UAVs) in 3D aerial highways necessitates robust coordination of physical flight kinematics and multi-tier network handovers. While Deep Reinforcement Learning (DRL) offers rapid tactical control, it lacks the zero-shot strategic reasoning required to quickly adapt to dynamic Integrated Terrestrial and Non-Terrestrial Networks (ITNTNs). Conversely, Large Language Models (LLMs) excel at semantic reasoning but suffer from high inference latency, rendering them unsuitable for real-time aerodynamic control. To bridge this gap, we propose a novel Hierarchical LLM-driven control framework. A massive cloud-based LLM deployed on a High-Altitude Platform Station (HAPS) manages slow-timescale global load balancing, while lightweight edge-LLMs on individual UAVs translate local observations into tactical sub-goals. These sub-goals guide a fast-timescale physical DRL controller to execute collision-free, handover-aware trajectories. Simulation results demonstrate that our agentic architecture significantly reduces collision rates and improves aggregate system throughput compared to existing baselines.

cs.RO↗

arXiv2026

Contrastive Predictive Coding with Compression for Enhanced Channel State Feedback in Wireless Networks

Accurate and timely channel state information (CSI) is essential for next-generation wireless systems, yet existing works treat CSI compression and CSI prediction as separate problems, both in academia and in current 3GPP studies. Consequently, channel aging remains insufficiently addressed within standardized CSI feedback pipelines. In this article, we propose a unified compression-prediction framework that integrates Contrastive Predictive Coding (CPC) directly into the 3GPP-compliant CSI compression architecture. Instead of predicting high-dimensional CSI matrices, our approach forecasts future latent representations and jointly optimizes reconstruction fidelity and temporal predictive coherence via a combined 1-SGCS and InfoNCE objective. This design enables temporal representation learning without increasing feedback overhead. We present two variants: CPC-before-Compression, which performs autoregressive modeling on encoded features prior to quantization, and CPC-after-Compression, which shifts temporal modeling to the base-station to reduce the complexity of users' devices. Evaluations on 3GPP-compliant datasets from Nokia, Oppo, and CATT show that CPC-before-Compression achieves over 90% reconstruction accuracy with 32x lower decoder GFLOPs than the 3GPP baseline, while CPC-after-Compression preserves an identical encoder footprint and the same 64-bit feedback overhead. By unifying compression and prediction within a standardized pipeline, the proposed framework provides an age-aware, computationally efficient CSI feedback solution. The source code is publicly available at: https://github.com/AhmedRadwan02/cpc-3gpp

cs.IT↗

arXiv2026

MU-SHOT-Fi: Self-Supervised Multi-User Wi-Fi Sensing with Source-free Unsupervised Domain Adaptation

Deep learning has been widely adopted for WiFi CSI-based human activity recognition (HAR) due to its ability to learn spatio-temporal features in a privacy-preserving and cost-effective manner. However, DL-based models generalize poorly across environments, a challenge amplified in multi-user settings where overlapping activities cause CSI entanglement and domain shifts. Practical deployments often limit access to labeled source data due to privacy constraints, motivating source-free adaptation using only unlabeled target-domain CSI and a pre-trained source model. In this paper, we propose MU-SHOT-Fi, a source-free unsupervised domain adaptation framework for single- and multi-user Wi-Fi sensing. MU-SHOT-Fi employs permutation-invariant set prediction with Hungarian matching during source training, followed by frozen-classifier backbone adaptation in the target domain. To enable stable adaptation without labels, we introduce occupancy-weighted information maximization that prevents model collapse by focusing diversity regularization on likely-occupied slots while excluding the dominant class from marginal entropy. Additionally, we employ binary rotation prediction as spatial self-supervision that exploits CSI frequency-time structure to learn domain-invariant features. For single-user scenarios, we introduce SU-SHOT-Fi by replacing occupancy weighting with standard information maximization and incorporating contrastive predictive coding to exploit temporal consistency. Extensive experiments on the WiMANS and Widar 3.0 datasets across cross-environment, cross-frequency, cross-orientation, and combined domain shifts demonstrate that MU-SHOT-Fi effectively recovers multi-user exact-activity classification performance under large domain shifts while maintaining accurate occupancy estimation and preventing collapse toward dominant classes.

eess.SP↗

arXiv2026

AMAR: Lightweight Attention-Based Multi-User Activity Recognition from Wi-Fi CSI

Wi-Fi-based human activity recognition (HAR) has emerged as a promising approach for contactless sensing, leveraging channel state information (CSI) collected from wireless transceivers. While existing studies have primarily concentrated on single-user scenarios, real-world deployments often involve multi-user settings where concurrent users' movements induce overlapping CSI patterns that challenge conventional classification methods. To address this limitation, this paper introduces an attention-based multi-user activity recognition (AMAR) framework that formulates HAR as a set prediction problem. The transformer-based architecture in AMAR leverages learnable query embeddings acting as specialized activity detectors, enabling the simultaneous identification of multiple activities from composite CSI representations. Moreover, to address deployment constraints, AMAR is designed in an edge-cloud split architecture form where lightweight convolutional networks on edge devices perform initial feature extraction, followed by residual vector quantization that achieves substantial bandwidth reduction while preserving activity-discriminative information. The cloud component performs final activity prediction through attention-based set matching, enabling the system to handle varying occupancy levels. Across classroom, meeting-room, and empty-room environments, on average AMAR nearly doubles the rate of perfectly predicting all concurrent activities compared to the best baseline. Moreover, it achieves an $F_1$-score of 53.4% compared to 45.6% for the best benchmark, and reduces occupancy estimation error by 74%, while minimizing bandwidth substantially.

eess.SP↗

arXiv2026

Hierarchical LLM-Driven Control for HAPS-Assisted UAV Networks: Joint Optimization of Flight and Connectivity

Uncrewed aerial vehicles (UAVs) are increasingly deployed in complex networked environments, yet the joint optimization of multi-UAV motion control and connectivity remains a fundamental challenge. In this paper, we study a multi-UAV system operating in an integrated terrestrial and non-terrestrial network (ITNTN) comprising terrestrial base stations and high-altitude platform stations (HAPS). We consider a three-dimensional (3D) aerial highway scenario where UAVs must adapt their motion to ensure collision avoidance, efficient traffic flow, and reliable communication under dynamic and partially observable conditions. We first model the problem as a hierarchical multi-objective partially observable Markov decision process (H-MO-POMDP), capturing the coupling between control and communication objectives. Based on this formulation, we propose a large language model (LLM)-driven hierarchical multi-rate control framework. At the global level, an LLM-based controller on the HAPS performs long-term planning for load balancing and handover decisions. At the local level, each UAV employs a hybrid controller that integrates a slow-timescale LLM for high-level spatial reasoning with a reinforcement learning agent for faster UAV-to-infrastructure (U2I) communication and motion control. We further develop a high-fidelity 3D simulation platform by integrating the gym-pybullet-drones environment with 3GPP-compliant RF/THz channel models. Numerical results demonstrate that the proposed framework significantly outperforms state-of-the-art baselines, achieving a 14% increase in transportation efficiency and a 25% improvement in telecommunication throughput. Additionally, it achieves a 23% reduction in physical collision rates, demonstrating strong handover stability and zero-shot generalization in dynamic scenarios.

cs.AI↗

arXiv2026

Multi-objective Optimization for Over-the-Air Federated Edge Learning-enabled Collaborative Integrated Sensing and Communications

This paper introduces a novel multi-objective integrated sensing and communications (ISAC) framework to enable collaborative wireless sensing in conjunction with over-the-air federated-edge learning (OTA-FEEL). The framework enables multi-task OTA aggregation to handle sensing and learning simultaneously, while benefiting from dual-purpose uplink signals for both communications and target sensing. Starting from characterizing the local sufficient statistics at each edge device and establishing its stationary, we develop a tractable analytical expression for the local sufficient statistics. To suppress the interference from uplink transmissions of other devices through matched filtering, we then propose a novel orthogonal pulse shaping method. Then, we derive the optimal unbiased estimate of the target's coordinates by casting the centralized problem of joint likelihood function maximization of all devices as the distributed likelihood maximization of each device (which requires only local sufficient statistics). A lower bound on the sensing error variance is then characterized using the Cramer-Rao bound (CRB). We then formulate a multi-objective optimization (MOOP) problem to minimize the mean square error (MSE) and sensing error bound simultaneously. The considered problem is then solved using the epsilon-constrained method. Numerical results demonstrate that the proposed dual-purpose OTA-FEEL-enabled collaborative ISAC framework enhances sensing accuracy without adversely affecting the performance of the primary OTA-FEEL task. While conventional single-shot collaborative sensing schemes are limited by the average error of local estimators, the proposed algorithm achieves the CRB of the considered problem.

cs.IT↗

arXiv2026

Pinching Antennas-Assisted Low-Latency Federated Learning Over Multi-User Wireless Networks

Federated learning (FL) over wireless networks is fundamentally constrained by unreliable communication links, particularly when uplink channels suffer from blockage, fading, or weak line-of-sight (LoS) conditions. Pinching-antenna systems (PASSs) offer a new physical-layer capability to dynamically reposition radiating points along a dielectric waveguide, enabling controllable LoS connectivity and significantly improved channel quality. This paper develops FedPASS, a novel framework for low-latency wireless FL assisted by PASS. We formulate a multi-objective optimization problem that jointly minimizes the end-to-end round latency and an upper bound on the FL optimality gap. The resulting formulation is a mixed-integer nonlinear program subject to practical constraints on scheduling, transmit power, local CPU frequency, and PA placement. To address the resulting computational challenges, we develop a two-tier iterative algorithm: an outer loop that updates scheduling, communication time allocation, and power control via block coordinate descent, and an inner loop that optimizes PA locations using a Gauss-Seidel-based coordinate update with grid search under spacing constraints. Numerical results on MNIST and CIFAR-10 demonstrate that FedPASS achieves accuracy comparable to idealized FL baselines while drastically reducing the total training latency compared to conventional wireless FL.

cs.IT↗

arXiv2026

SONIC-O1: A Real-World Benchmark for Evaluating Multimodal Large Language Models on Audio-Video Understanding

Multimodal Large Language Models (MLLMs) are a major focus of recent AI research. However, most prior work focuses on static image understanding, while their ability to process sequential audio-video data remains underexplored. This gap highlights the need for a high-quality benchmark to systematically evaluate MLLM performance in a real-world setting. We introduce SONIC-O1, a comprehensive, fully human-verified benchmark of 60 hours (231 clips) spanning 13 real-world conversational domains with 4,958 annotations and demographic metadata. SONIC-O1 evaluates three capabilities: open-ended summarization, multiple-choice question (MCQ) answering, and temporal localization with supporting rationales (reasoning). Across closed- and open-source models, we find that the MCQ accuracy shows the smallest gap between model families, but the best closed-source model outperforms the best open-source model by 22.6% on temporal localization. We further observe accuracy gaps of up to 21.4% on temporal localization across demographic groups, indicating persistent disparities in model behaviour. SONIC-O1 provides an open evaluation suite for temporally grounded and demographically robust multimodal understanding. SONIC-O1 is publicly available for research: Project page (https://vectorinstitute.github.io/sonic-o1/), Dataset (https://huggingface.co/datasets/vector-institute/sonic-o1), GitHub (https://github.com/vectorinstitute/sonic-o1), Leaderboard (https://huggingface.co/spaces/vector-institute/sonic-o1-leaderboard).

cs.AI↗

arXiv2025

EMFusion: Uncertainty-Aware Conditional Diffusion Model for Multivariate Narrow-band Exposure Forecasting

The rapid growth in wireless infrastructure has increased the need to accurately estimate and forecast electromagnetic field (EMF) levels to ensure ongoing compliance, assess potential health impacts, and support efficient network planning. While existing studies rely on univariate forecasting of wideband aggregate EMF data, multivariate narrow-band EMF forecasting is needed to capture the inter-operator and inter-frequency variations essential for proactive network planning. To this end, this paper introduces EMFusion, a conditional diffusion-based EMF forecasting framework that integrates diverse contextual factors, such as time of day, season, and holidays, while providing uncertainty-aware probabilistic forecasts. The proposed architecture features a residual U-Net backbone enhanced by a cross-attention mechanism that dynamically integrates external conditions to guide the generation process. Furthermore, EMFusion integrates an imputation-based sampling strategy that treats forecasting as a structural inpainting task, ensuring temporal coherence even with irregular measurements. Unlike standard point forecasters, EMFusion generates empirical probabilistic prediction intervals from the learned conditional distribution, providing uncertainty-aware probabilistic forecasting rather than simple point estimation. Numerical experiments conducted on the multivariate narrow-band EMF datasets demonstrate that EMFusion with the contextual information of working hours outperforms the baseline models with or without conditions. The proposed EMFusion outperforms the best baseline by 23.85% in continuous ranked probability score (CRPS) and 13.93% in normalized root mean square error.

cs.LG↗

arXiv2025

Resource Allocation in Cooperative Mid-band/THz Networks in the Presence of Mobility

This paper develops a comprehensive framework to investigate and optimize the downlink performance of cooperative multi-band networks (MBNs) operating on upper mid-band (UMB) and terahertz (THz) frequencies, where base stations (BSs) in each band cooperatively serve users. The framework captures sophisticated features such as near-field channel modeling, fully and partially connected antenna architectures, and users' mobility. First, we consider joint user association and hybrid beamforming optimization to maximize the system sum-rate, subject to power constraints, maximum cluster size of cooperating BSs, and users' quality-of-service (QoS) constraints. By leveraging fractional programming FP and majorization-minimization techniques, an iterative algorithm is proposed to solve the non-convex optimization problem. We then consider handover (HO)-aware resource allocation for moving users in a cooperative UMB/THz MBN. Two HO-aware resource allocation methods are proposed. The first method focuses on maximizing the HO-aware system sum-rate subject to HO-aware QoS constraints. Using Jensen's inequality and properties of logarithmic functions, the non-convex optimization problem is tightly approximated with a convex one and solved. The second method addresses a multi-objective optimization problem to maximize the system sum-rate, while minimizing the total number of HOs. Numerical results demonstrate the efficacy of the proposed algorithms, cooperative UMB/THz MBN over stand-alone THz networks, as well as the critical importance of accurate near-field modeling in extremely large antenna arrays. Moreover, the proposed HO-aware resource allocation methods effectively mitigate the impact of HOs, enhancing performance in the considered system.

eess.SP↗

arXiv2025

Semantic-Aware Adaptive Video Streaming Using Latent Diffusion Models for Wireless Networks

This paper proposes a novel Semantic Communication (SemCom) framework for real-time adaptive-bitrate video streaming by integrating Latent Diffusion Models (LDMs) within the FFmpeg techniques. This solution addresses the challenges of high bandwidth usage, storage inefficiencies, and quality of experience (QoE) degradation associated with traditional Constant Bitrate Streaming (CBS) and Adaptive Bitrate Streaming (ABS). The proposed approach leverages LDMs to compress I-frames into a latent space, offering significant storage and semantic transmission savings without sacrificing high visual quality. While retaining B-frames and P-frames as adjustment metadata to support efficient refinement of video reconstruction at the user side, the proposed framework further incorporates state-of-the-art denoising and Video Frame Interpolation (VFI) techniques. These techniques mitigate semantic ambiguity and restore temporal coherence between frames, even in noisy wireless communication environments. Experimental results demonstrate the proposed method achieves high-quality video streaming with optimized bandwidth usage, outperforming state-of-the-art solutions in terms of QoE and resource efficiency. This work opens new possibilities for scalable real-time video streaming in 5G and future post-5G networks.

cs.MM↗

arXiv2025

Generalized Multi-Objective Reinforcement Learning with Envelope Updates in URLLC-enabled Vehicular Networks

We develop a novel multi-objective reinforcement learning (MORL) framework to jointly optimize wireless network selection and autonomous driving policies in a multi-band vehicular network operating on conventional sub-6GHz spectrum and Terahertz frequencies. The proposed framework is designed to 1. maximize the traffic flow and minimize collisions by controlling the vehicle's motion dynamics (i.e., speed and acceleration), and 2. enhance the ultra-reliable low-latency communication (URLLC) while minimizing handoffs (HOs). We cast this problem as a multi-objective Markov Decision Process (MOMDP) and develop solutions for both predefined and unknown preferences of the conflicting objectives. Specifically, we develop a novel envelope MORL solution which develops policies that address multiple objectives with unknown preferences to the agent. While this approach reduces reliance on scalar rewards, policy effectiveness varying with different preferences is a challenge. To address this, we apply a generalized version of the Bellman equation and optimize the convex envelope of multi-objective Q values to learn a unified parametric representation capable of generating optimal policies across all possible preference configurations. Following an initial learning phase, our agent can execute optimal policies under any specified preference or infer preferences from minimal data samples. Numerical results validate the efficacy of the envelope-based MORL solution and demonstrate interesting insights related to the inter-dependency of vehicle motion dynamics, HOs, and the communication data rate. The proposed policies enable autonomous vehicles (AVs) to adopt safe driving behaviors with improved connectivity.

cs.LG↗

arXiv2025

Age of Information in Unreliable Tandem Queues

Stringent demands for timely information delivery, driven by the widespread adoption of real-time applications and the Internet of Things, have established the age of information (AoI) as a critical metric for quantifying data freshness. Existing AoI models often assume multi-hop communication networks with fully reliable nodes, which may not accurately capture scenarios involving node transmission failures. This paper presents an analytical framework for two configurations of tandem queue systems, where status updates generated by a single sensor are relayed to a destination monitor through unreliable intermediate nodes. Using the probability generating function, we first derive the sojourn time distribution for an infinite-buffer M/M/1 tandem system with two unreliable nodes. We then extend our analysis to an M/G/1 tandem system with an arbitrary number of unreliable nodes, employing the supplementary variable technique while assuming that only the first node has an infinite buffer. Numerical results demonstrate the impact of key system parameters on the average AoI in unreliable tandem queues with Markovian and non-Markovian service times.

cs.NI↗

arXiv2025

Hierarchical and Collaborative LLM-Based Control for Multi-UAV Motion and Communication in Integrated Terrestrial and Non-Terrestrial Networks

Unmanned aerial vehicles (UAVs) have been widely adopted in various real-world applications. However, the control and optimization of multi-UAV systems remain a significant challenge, particularly in dynamic and constrained environments. This work explores the joint motion and communication control of multiple UAVs operating within integrated terrestrial and non-terrestrial networks that include high-altitude platform stations (HAPS). Specifically, we consider an aerial highway scenario in which UAVs must accelerate, decelerate, and change lanes to avoid collisions and maintain overall traffic flow. Different from existing studies, we propose a novel hierarchical and collaborative method based on large language models (LLMs). In our approach, an LLM deployed on the HAPS performs UAV access control, while another LLM onboard each UAV handles motion planning and control. This LLM-based framework leverages the rich knowledge embedded in pre-trained models to enable both high-level strategic planning and low-level tactical decisions. This knowledge-driven paradigm holds great potential for the development of next-generation 3D aerial highway systems. Experimental results demonstrate that our proposed collaborative LLM-based method achieves higher system rewards, lower operational costs, and significantly reduced UAV collision rates compared to baseline approaches.

cs.LG↗

arXiv2025

A Tutorial-cum-Survey on Self-Supervised Learning for Wi-Fi Sensing: Trends, Challenges, and Outlook

Wi-Fi technology has evolved from simple communication routers to sensing devices. Wi-Fi sensing leverages conventional Wi-Fi transmissions to extract and analyze channel state information (CSI) for applications like proximity detection, occupancy detection, activity recognition, and health monitoring. By leveraging existing infrastructure, Wi-Fi sensing offers a privacy-preserving, non-intrusive, and cost-effective solution which, unlike cameras, is not sensitive to lighting conditions. Beginning with a comprehensive review of the Wi-Fi standardization activities, this tutorial-cum-survey first introduces fundamental concepts related to Wi-Fi CSI, outlines the CSI measurement methods, and examines the impact of mobile objects on CSI. The mechanics of a simplified testbed for CSI extraction are also described. Then, we present a qualitative comparison of the existing Wi-Fi sensing datasets, their specifications, and pin-point their shortcomings. Next, a variety of preprocessing techniques are discussed that are beneficial for feature extraction and explainability of machine learning (ML) algorithms. We then provide a qualitative review of recent ML approaches in the domain of Wi-Fi sensing and present the significance of self-supervised learning (SSL) in that context. Specifically, the mechanics of contrastive and non-contrastive learning solutions is elaborated in detail and a quantitative comparative analysis is presented in terms of classification accuracy. Finally, the article concludes by highlighting emerging technologies that can be leveraged to enhance the performance of Wi-Fi sensing and opportunities for further research in this domain

eess.SP↗

arXiv2025

EMForecaster: A Deep Learning Framework for Time Series Forecasting in Wireless Networks with Distribution-Free Uncertainty Quantification

With the recent advancements in wireless technologies, forecasting electromagnetic field (EMF) exposure has become critical to enable proactive network spectrum and power allocation, as well as network deployment planning. In this paper, we develop a deep learning (DL) time series forecasting framework referred to as \textit{EMForecaster}. The proposed DL architecture employs patching to process temporal patterns at multiple scales, complemented by reversible instance normalization and mixing operations along both temporal and patch dimensions for efficient feature extraction. We augment {EMForecaster} with a conformal prediction mechanism, which is independent of the data distribution, to enhance the trustworthiness of model predictions via uncertainty quantification of forecasts. This conformal prediction mechanism ensures that the ground truth lies within a prediction interval with target error rate $α$, where $1-α$ is referred to as coverage. However, a trade-off exists, as increasing coverage often results in wider prediction intervals. To address this challenge, we propose a new metric called the \textit{Trade-off Score}, that balances trustworthiness of the forecast (i.e., coverage) and the width of prediction interval. Our experiments demonstrate that EMForecaster achieves superior performance across diverse EMF datasets, spanning both short-term and long-term prediction horizons. In point forecasting tasks, EMForecaster substantially outperforms current state-of-the-art DL approaches, showing improvements of 53.97\% over the Transformer architecture and 38.44\% over the average of all baseline models. EMForecaster also exhibits an excellent balance between prediction interval width and coverage in conformal forecasting, measured by the tradeoff score, showing marked improvements of 24.73\% over the average baseline and 49.17\% over the Transformer architecture.

cs.LG↗

arXiv2025

Latent Diffusion Model-Enabled Low-Latency Semantic Communication in the Presence of Semantic Ambiguities and Wireless Channel Noises

Deep learning (DL)-based Semantic Communications (SemCom) is becoming critical to maximize overall efficiency of communication networks. Nevertheless, SemCom is sensitive to wireless channel uncertainties, source outliers, and suffer from poor generalization bottlenecks. To address the mentioned challenges, this paper develops a latent diffusion model-enabled SemCom system with three key contributions, i.e., i) to handle potential outliers in the source data, semantic errors obtained by projected gradient descent based on the vulnerabilities of DL models, are utilized to update the parameters and obtain an outlier-robust encoder, ii) a lightweight single-layer latent space transformation adapter completes one-shot learning at the transmitter and is placed before the decoder at the receiver, enabling adaptation for out-of-distribution data and enhancing human-perceptual quality, and iii) an end-to-end consistency distillation (EECD) strategy is used to distill the diffusion models trained in latent space, enabling deterministic single or few-step low-latency denoising in various noisy channels while maintaining high semantic quality. Extensive numerical experiments across different datasets demonstrate the superiority of the proposed SemCom system, consistently proving its robustness to outliers, the capability to transmit data with unknown distributions, and the ability to perform real-time channel denoising tasks while preserving high human perceptual quality, outperforming the existing denoising approaches in semantic metrics such as multi-scale structural similarity index measure (MS-SSIM) and learned perceptual image path similarity (LPIPS).

cs.LG↗