Fatemeh Afghah

Gen Li, Jie Ji, Minghai Qin et al.

As deep convolutional neural networks (DNNs) are widely used in various fields of computer vision, leveraging the overfitting ability of the DNN to achieve video resolution upscaling has become a new trend in the modern video delivery system. By dividing videos into chunks and overfitting each chunk with a super-resolution model, the server encodes videos before transmitting them to the clients, thus achieving better video quality and transmission efficiency. However, a large number of chunks are expected to ensure good overfitting quality, which substantially increases the storage and consumes more bandwidth resources for data transmission. On the other hand, decreasing the number of chunks through training optimization techniques usually requires high model capacity, which significantly slows down execution speed. To reconcile such, we propose a novel method for high-quality and efficient video resolution upscaling tasks, which leverages the spatial-temporal information to accurately divide video into chunks, thus keeping the number of chunks as well as the model size to minimum. Additionally, we advance our method into a single overfitting model by a data-aware joint training technique, which further reduces the storage requirement with negligible quality drop. We deploy our models on an off-the-shelf mobile phone, and experimental results show that our method achieves real-time video super-resolution with high video quality. Compared with the state-of-the-art, our method achieves 28 fps streaming speed with 41.6 PSNR, which is 14$\times$ faster and 2.29 dB better in the live video resolution upscaling tasks. Code available in https://github.com/coulsonlee/STDO-CVPR2023.git

Niloufar Alipour Talemi, Hossein Kashiani, Fatemeh Afghah

Multimodal In-Context Learning (ICL) has emerged as a practical inference paradigm for Multimodal Large Language Models, where a small set of interleaved image-text In-Context Demonstrations (ICDs) conditions the model to solve new tasks. Despite its flexibility, multimodal ICL incurs high inference latency and suffers from instability due to sensitivity to demonstration formatting, ordering, and content. To address these limitations, we propose Hyper-ICL, a lightweight, training-based framework for demonstration-free multimodal ICL that reconstructs demonstration effects directly without requiring ICDs at inference time. Hyper-ICL learns a parameter-efficient low-rank logit-level adapter that calibrates attention distributions to better match demonstration-induced attention redistribution. To capture how demonstration influence varies across queries, we introduce a query-adaptive modulation mechanism that adaptively controls intervention strength at token level across layers and heads based on the current query. Finally, we propose a layer-wise hyperbolic anchor distillation loss that aligns intermediate student features to a demonstration-conditioned teacher via Lorentz geodesic distance. This loss encourages the student to reconstruct the demonstration-query relationships induced by ICDs. Extensive experiments across six different multimodal benchmarks (including VQAv2, OK-VQA, and COCO Caption) demonstrate that Hyper-ICL consistently improves accuracy and stability over vanilla ICL and existing state-of-the-art methods.

Alireza Shamsoshoara, Fatemeh Lotfi, Sajad Mousavi et al.

This paper investigates an interference-aware joint path planning and power allocation mechanism for a cellular-connected unmanned aerial vehicle (UAV) in a sparse suburban environment. The UAV's goal is to fly from an initial point and reach a destination point by moving along the cells to guarantee the required quality of service (QoS). In particular, the UAV aims to maximize its uplink throughput and minimize the level of interference to the ground user equipment (UEs) connected to the neighbor cellular BSs, considering the shortest path and flight resource limitation. Expert knowledge is used to experience the scenario and define the desired behavior for the sake of the agent (i.e., UAV) training. To solve the problem, an apprenticeship learning method is utilized via inverse reinforcement learning (IRL) based on both Q-learning and deep reinforcement learning (DRL). The performance of this method is compared to learning from a demonstration technique called behavioral cloning (BC) using a supervised learning approach. Simulation and numerical results show that the proposed approach can achieve expert-level performance. We also demonstrate that, unlike the BC technique, the performance of our proposed approach does not degrade in unseen situations.

Abolfazl Razi, Fatemeh Afghah, Jacob Chakareski

In recent years, there has been a growing interest in using networks of Unmanned Aerial Vehicles (UAV) that collectively perform complex tasks for diverse applications. An important challenge in realizing UAV networks is the need for a communication platform that accommodates rapid network topology changes. For instance, a timely prediction of network topology changes can reduce communication link loss rate by setting up links with prolonged connectivity. In this work, we develop an optimal tracking policy for each UAV to perceive its surrounding network configuration in order to facilitate more efficient communication protocols. More specifically, we develop an algorithm based on particle swarm optimization and Kalman filtering with intermittent observations to find a set of optimal tracking policies for each UAV under time-varying channel qualities and constrained tracking resources such that the overall network estimation error is minimized.

Samuel Reinders, Alireza Ebrahimi Dorcheh, Ryan Barker et al.

Inter-cell interference is a persistent issue in dense 5G deployments, especially in heterogeneous Open Radio Access Network (O-RAN) environments where coordination between base stations is limited. This paper presents AIIM, an adaptive inter-cell interference mitigation xApp for the O-RAN near-real-time RAN Intelligent Controller (near-RT RIC) that performs coordinated physical resource block (PRB) allocation across multiple base stations under diverse traffic demands and channel conditions. Unlike prior studies that rely primarily on simulation or fully hardware-centric testbeds, AIIM is developed and evaluated in a full-stack O-RAN system built on srsRAN, Open5GS, and O-RAN Software Community (ORAN-SC), and deployed on a hybrid experimental platform that simultaneously combines software defined radio (SDR)-based and virtual gNodeBs (gNBs) and user equipment (UEs). This design preserves realistic PHY-layer interactions while substantially improving scalability, reproducibility, and cost-effectiveness for multi-cell interference experiments. AIIM explicitly models overlapping PRB regions across neighboring cells and learns coordinated allocation policies that adapt to per-user QoS demand and pathloss variation across the network. Experimental results show that AIIM improves QoS satisfaction and reduces interference-induced PRB loss relative to proportional-fair scheduling baselines while maintaining comparable aggregate network throughput. These results demonstrate the promise of scalable, learning-driven O-RAN control for practical interference management in heterogeneous multi-gNB 5G networks.\footnote{A video demonstration of the running system can be found at https://github.com/sireinders/AIIM-Multi-gNB-Interference.git.}

Fatemeh Lotfi, Omid Semiari, Fatemeh Afghah

The next-generation wireless networks are required to satisfy a variety of services and criteria concurrently. To address upcoming strict criteria, a new open radio access network (O-RAN) with distinguishing features such as flexible design, disaggregated virtual and programmable components, and intelligent closed-loop control was developed. O-RAN slicing is being investigated as a critical strategy for ensuring network quality of service (QoS) in the face of changing circumstances. However, distinct network slices must be dynamically controlled to avoid service level agreement (SLA) variation caused by rapid changes in the environment. Therefore, this paper introduces a novel framework able to manage the network slices through provisioned resources intelligently. Due to diverse heterogeneous environments, intelligent machine learning approaches require sufficient exploration to handle the harshest situations in a wireless network and accelerate convergence. To solve this problem, a new solution is proposed based on evolutionary-based deep reinforcement learning (EDRL) to accelerate and optimize the slice management learning process in the radio access network's (RAN) intelligent controller (RIC) modules. To this end, the O-RAN slicing is represented as a Markov decision process (MDP) which is then solved optimally for resource allocation to meet service demand using the EDRL approach. In terms of reaching service demands, simulation results show that the proposed approach outperforms the DRL baseline by 62.2%.

Fatemeh Lotfi, Fatemeh Afghah, Jonathan Ashdown

As emerging networks such as Open Radio Access Networks (O-RAN) and 5G continue to grow, the demand for various services with different requirements is increasing. Network slicing has emerged as a potential solution to address the different service requirements. However, managing network slices while maintaining quality of services (QoS) in dynamic environments is a challenging task. Utilizing machine learning (ML) approaches for optimal control of dynamic networks can enhance network performance by preventing Service Level Agreement (SLA) violations. This is critical for dependable decision-making and satisfying the needs of emerging networks. Although RL-based control methods are effective for real-time monitoring and controlling network QoS, generalization is necessary to improve decision-making reliability. This paper introduces an innovative attention-based deep RL (ADRL) technique that leverages the O-RAN disaggregated modules and distributed agent cooperation to achieve better performance through effective information extraction and implementing generalization. The proposed method introduces a value-attention network between distributed agents to enable reliable and optimal decision-making. Simulation results demonstrate significant improvements in network performance compared to other DRL baseline methods.

Mobin Habibpour, Niloufar Alipour Talemi, John Spodnik et al.

Wildfire monitoring requires timely, actionable situational awareness from airborne platforms, yet existing aerial visual question answering (VQA) benchmarks do not evaluate wildfire-specific multimodal reasoning grounded in thermal measurements. We introduce WildFireVQA, a large-scale VQA benchmark for aerial wildfire monitoring that integrates RGB imagery with radiometric thermal data. WildFireVQA contains 6,097 RGB-thermal samples, where each sample includes an RGB image, a color-mapped thermal visualization, and a radiometric thermal TIFF, and is paired with 34 questions, yielding a total of 207,298 multiple-choice questions spanning presence and detection, classification, distribution and segmentation, localization and direction, cross-modal reasoning, and flight planning for operational wildfire intelligence. To improve annotation reliability, we combine multimodal large language model (MLLM)-based answer generation with sensor-driven deterministic labeling, manual verification, and intra-frame and inter-frame consistency checks. We further establish a comprehensive evaluation protocol for representative MLLMs under RGB, Thermal, and retrieval-augmented settings using radiometric thermal statistics. Experiments show that across task categories, RGB remains the strongest modality for current models, while retrieved thermal context yields gains for stronger MLLMs, highlighting both the value of temperature-grounded reasoning and the limitations of existing MLLMs in safety-critical wildfire scenarios. The dataset and benchmark code are open-source at https://github.com/mobiiin/WildFire_VQA.

Edmond Adib, Amanda Fernandez, Fatemeh Afghah et al.

Deep learning image processing models have had remarkable success in recent years in generating high quality images. Particularly, the Improved Denoising Diffusion Probabilistic Models (DDPM) have shown superiority in image quality to the state-of-the-art generative models, which motivated us to investigate their capability in the generation of the synthetic electrocardiogram (ECG) signals. In this work, synthetic ECG signals are generated by the Improved DDPM and by the Wasserstein GAN with Gradient Penalty (WGAN-GP) models and then compared. To this end, we devise a pipeline to utilize DDPM in its original $2D$ form. First, the $1D$ ECG time series data are embedded into the $2D$ space, for which we employed the Gramian Angular Summation/Difference Fields (GASF/GADF) as well as Markov Transition Fields (MTF) to generate three $2D$ matrices from each ECG time series, which when put together, form a $3$-channel $2D$ datum. Then $2D$ DDPM is used to generate $2D$ $3$-channel synthetic ECG images. The $1D$ ECG signals are created by de-embedding the $2D$ generated image files back into the $1D$ space. This work focuses on unconditional models and the generation of \emph{Normal Sinus Beat} ECG signals exclusively, where the Normal Sinus Beat class from the MIT-BIH Arrhythmia dataset is used in the training phase. The \emph{quality}, \emph{distribution}, and the \emph{authenticity} of the generated ECG signals by each model are quantitatively evaluated and compared. Our results show that in the proposed pipeline and in the particular setting of this paper, the WGAN-GP model is consistently superior to DDPM in all the considered metrics.

Gen Li, Zhihao Shu, Jie Ji et al.

Deep neural networks (DNNs) are frequently employed in a variety of computer vision applications. Nowadays, an emerging trend in the current video distribution system is to take advantage of DNN's overfitting properties to perform video resolution upscaling. By splitting videos into chunks and applying a super-resolution (SR) model to overfit each chunk, this scheme of SR models plus video chunks is able to replace traditional video transmission to enhance video quality and transmission efficiency. However, many models and chunks are needed to guarantee high performance, which leads to tremendous overhead on model switching and memory footprints at the user end. To resolve such problems, we propose a Dynamic Deep neural network assisted by a Content-Aware data processing pipeline to reduce the model number down to one (Dy-DCA), which helps promote performance while conserving computational resources. Additionally, to achieve real acceleration on the user end, we designed a framework that optimizes dynamic features (e.g., dynamic shapes, sizes, and control flow) in Dy-DCA to enable a series of compilation optimizations, including fused code generation, static execution planning, etc. By employing such techniques, our method achieves better PSNR and real-time performance (33 FPS) on an off-the-shelf mobile phone. Meanwhile, assisted by our compilation optimization, we achieve a 1.7$\times$ speedup while saving up to 1.61$\times$ memory consumption. Code available in https://github.com/coulsonlee/Dy-DCA-ECCV2024.

Seokmin Choi, Sajad Mousavi, Phillip Si et al.

In the medical field, current ECG signal analysis approaches rely on supervised deep neural networks trained for specific tasks that require substantial amounts of labeled data. However, our paper introduces ECGBERT, a self-supervised representation learning approach that unlocks the underlying language of ECGs. By unsupervised pre-training of the model, we mitigate challenges posed by the lack of well-labeled and curated medical data. ECGBERT, inspired by advances in the area of natural language processing and large language models, can be fine-tuned with minimal additional layers for various ECG-based problems. Through four tasks, including Atrial Fibrillation arrhythmia detection, heartbeat classification, sleep apnea detection, and user authentication, we demonstrate ECGBERT's potential to achieve state-of-the-art results on a wide variety of tasks.

Hossein Rajoli, Fatemeh Lotfi, Adham Atyabi et al.

Facial expressions convey massive information and play a crucial role in emotional expression. Deep neural network (DNN) accompanied by deep metric learning (DML) techniques boost the discriminative ability of the model in facial expression recognition (FER) applications. DNN, equipped with only classification loss functions such as Cross-Entropy cannot compact intra-class feature variation or separate inter-class feature distance as well as when it gets fortified by a DML supporting loss item. The triplet center loss (TCL) function is applied on all dimensions of the sample's embedding in the embedding space. In our work, we developed three strategies: fully-synthesized, semi-synthesized, and prediction-based negative sample selection strategies. To achieve better results, we introduce a selective attention module that provides a combination of pixel-wise and element-wise attention coefficients using high-semantic deep features of input samples. We evaluated the proposed method on the RAF-DB, a highly imbalanced dataset. The experimental results reveal significant improvements in comparison to the baseline for all three negative sample selection strategies.

Fatemeh Lotfi, Fatemeh Afghah

As wireless networks grow to support more complex applications, the Open Radio Access Network (O-RAN) architecture, with its smart RAN Intelligent Controller (RIC) modules, becomes a crucial solution for real-time network data collection, analysis, and dynamic management of network resources including radio resource blocks and downlink power allocation. Utilizing artificial intelligence (AI) and machine learning (ML), O-RAN addresses the variable demands of modern networks with unprecedented efficiency and adaptability. Despite progress in using ML-based strategies for network optimization, challenges remain, particularly in the dynamic allocation of resources in unpredictable environments. This paper proposes a novel Meta Deep Reinforcement Learning (Meta-DRL) strategy, inspired by Model-Agnostic Meta-Learning (MAML), to advance resource block and downlink power allocation in O-RAN. Our approach leverages O-RAN's disaggregated architecture with virtual distributed units (DUs) and meta-DRL strategies, enabling adaptive and localized decision-making that significantly enhances network efficiency. By integrating meta-learning, our system quickly adapts to new network conditions, optimizing resource allocation in real-time. This results in a 19.8% improvement in network management performance over traditional methods, advancing the capabilities of next-generation wireless networks.

Ali Owfi, Fatemeh Afghah

Passive space-borne radiometers operating in the 1400-1427 MHz protected frequency band face radio frequency interference (RFI) from terrestrial sources. With the growth of wireless devices and the appearance of new technologies, the possibility of sharing this spectrum with other technologies would introduce more RFI to these radiometers. This band could be an ideal mid-band frequency for 5G and Beyond, as it offers high capacity and good coverage. Current RFI detection and mitigation techniques at SMAP (Soil Moisture Active Passive) depend on correctly detecting and discarding or filtering the contaminated data leading to the loss of valuable information, especially in severe RFI cases. In this paper, we propose an autoencoder-based RFI mitigation method to remove the dominant RFI caused by potential coexistent terrestrial users (i.e., 5G base station) from the received contaminated signal at the passive receiver side, potentially preserving valuable information and preventing the contaminated data from being discarded.

Alireza Ebrahimi Dorcheh, Tolunay Seyfi, Ryan Barker et al.

Reinforcement-learning (RL) solutions for dynamic spectrum access and radio resource management in Open Radio Access Networks (O-RAN) depend critically on the fidelity of the throughput signal used for training. Analytical or physical-layer (PHY)-only simulators scale well but often miss protocol-stack effects such as signaling overhead and retransmissions, whereas exhaustive throughput profiling on a standards-compliant 5G stack is slow and can be unstable under software execution constraints. This paper presents MORPH, a measurement-grounded multi-environment RL pipeline {for slice-aware PRB-level spectrum allocation (spectrum sharing and slice isolation within a single gNB)} built on OpenAirInterface (OAI) 5G-NR RF-simulator mode. MORPH leverages three complementary throughput sources: (i) application-layer throughput measured via \texttt{iPerf} on the OAI stack under controlled AWGN pathloss settings, (ii) empirical MCS-selection distributions conditioned on path loss, enabling a distribution-aware theoretical throughput estimator that reflects standards-compliant link adaptation, and (iii) scalable throughput estimates from a 3GPP-parameterized PHY-fidelity OFDM simulator. Using these components, we train and compare agents that differ only in the origin of their throughput feedback: an OAI-grounded practical agent, a simulator-driven agent, and MORPH, which fuses real and synthetic throughput signals for policy optimization. Evaluation on the OAI execution harness across heterogeneous slicing scenarios shows that MORPH yields more robust slice-wise performance and improved SLA compliance than single-source training, providing a practical foundation for PRB-level spectrum sharing and slice isolation within a single-cell stack and a stepping stone toward multi-cell spectrum coordination and interference management.

Xin Wang, Burcu Ozek, Aruna Mohan et al.

Electrocardiogram (ECG) analysis is crucial for diagnosing heart disease, but most self-supervised learning methods treat ECG as a generic time series, overlooking physiologic semantics and rhythm-level structure. Existing contrastive methods utilize augmentations that distort morphology, whereas generative approaches employ fixed-window segmentation, which misaligns cardiac cycles. To address these limitations, we propose RhythmBERT, a generative ECG language model that considers ECG as a language paradigm by encoding P, QRS, and T segments into symbolic tokens via autoencoder-based latent representations. These discrete tokens capture rhythm semantics, while complementary continuous embeddings retain fine-grained morphology, enabling a unified view of waveform structure and rhythm. RhythmBERT is pretrained on approximately 800,000 unlabeled ECG recordings with a masked prediction objective, allowing it to learn contextual representations in a label-efficient manner. Evaluations show that despite using only a single lead, RhythmBERT achieves comparable or superior performance to strong 12-lead baselines. This generalization extends from prevalent conditions such as atrial fibrillation to clinically challenging cases such as subtle ST-T abnormalities and myocardial infarction. Our results suggest that considering ECG as structured language offers a scalable and physiologically aligned pathway for advancing cardiac analysis.

Tolunay Seyfi, Erfan Khadem, Fatemeh Afghah

We propose \emph{PRISM} (\textbf{Pseudorandom Residue-based Indexed Scheduling Method}), a deterministic topology-discovery framework for single-hop wireless networks with bounded interference. Each receiver has at most \(L\) interfering transmitters among \(K\) transmitters and identifies them through singleton transmissions. PRISM assigns finite-field labels to transmitters and schedules transmissions via modular multiplication and a second prime modulus. It achieves full discovery in \(O(L(1+δ)\log K)\) rounds in expectation with failure probability \(K^{-δ}\), and in \(O(L^2\log K)\) rounds deterministically. Simulations show \(\approx 0.9L\log K\) scaling, with \(q/L\approx1.2\) minimizing mean completion time and \(q/L\approx1.4\text{--}1.6\) improving tail performance.

Ali Owfi, Amirmohammad Bamdad, Tolunay Seyfi et al.

Deep learning has emerged as a leading approach for Automatic Modulation Classification (AMC), demonstrating superior performance over traditional methods. However, vulnerability to adversarial attacks and susceptibility to data distribution shifts hinder their practical deployment in real-world, dynamic environments. To address these threats, we propose a novel, unified framework that integrates meta-learning with domain adaptation, making AMC systems resistant to both adversarial attacks and environmental changes. Our framework utilizes a two-phase strategy. First, in an offline phase, we employ a meta-learning approach to train the model on clean and adversarially perturbed samples from a single source domain. This method enables the model to generalize its defense, making it resistant to a combination of previously unseen attacks. Subsequently, in the online phase, we apply domain adaptation to align the model's features with a new target domain, allowing it to adapt without requiring substantial labeled data. As a result, our framework achieves a significant improvement in modulation classification accuracy against these combined threats, offering a critical solution to the deployment and operational challenges of modern AMC systems.

Jie Ji, Gen Li, Kaiyuan Deng et al.

Deep learning models, despite their impressive achievements, suffer from high computational costs and memory requirements, limiting their usability in resource-constrained environments. Sparse neural networks significantly alleviate these constraints by dramatically reducing parameter count and computational overhead. However, existing sparse training methods often experience chaotic and noisy gradient signals, severely hindering convergence and generalization performance, particularly at high sparsity levels. To tackle this critical challenge, we propose Zero-Order Sharpness-Aware Minimization (ZO-SAM), a novel optimization framework that strategically integrates zero-order optimization within the SAM approach. Unlike traditional SAM, ZO-SAM requires only a single backpropagation step during perturbation, selectively utilizing zero-order gradient estimations. This innovative approach reduces the backpropagation computational cost by half compared to conventional SAM, significantly lowering gradient variance and effectively eliminating associated computational overhead. By harnessing SAM's capacity for identifying flat minima, ZO-SAM stabilizes the training process and accelerates convergence. These efficiency gains are particularly important in sparse training scenarios, where computational cost is the primary bottleneck that limits the practicality of SAM. Moreover, models trained with ZO-SAM exhibit improved robustness under distribution shift, further broadening its practicality in real-world deployments.

Duncan McCain, Hossein Kashiani, Fatemeh Afghah

Visual anomaly detection in multi-class settings poses significant challenges due to the diversity of object categories, the scarcity of anomalous examples, and the presence of camouflaged defects. In this paper, we propose PromptMAD, a cross-modal prompting framework for unsupervised visual anomaly detection and localization that integrates semantic guidance through vision-language alignment. By leveraging CLIP-encoded text prompts describing both normal and anomalous class-specific characteristics, our method enriches visual reconstruction with semantic context, improving the detection of subtle and textural anomalies. To further address the challenge of class imbalance at the pixel level, we incorporate Focal loss function, which emphasizes hard-to-detect anomalous regions during training. Our architecture also includes a supervised segmentor that fuses multi-scale convolutional features with Transformer-based spatial attention and diffusion iterative refinement, yielding precise and high-resolution anomaly maps. Extensive experiments on the MVTec-AD dataset demonstrate that our method achieves state-of-the-art pixel-level performance, improving mean AUC to 98.35% and AP to 66.54%, while maintaining efficiency across diverse categories.

Sajad Mousavi, Fatemeh Afghah, U. Rajendra Acharya

Electroencephalogram (EEG) is a common base signal used to monitor brain activity and diagnose sleep disorders. Manual sleep stage scoring is a time-consuming task for sleep experts and is limited by inter-rater reliability. In this paper, we propose an automatic sleep stage annotation method called SleepEEGNet using a single-channel EEG signal. The SleepEEGNet is composed of deep convolutional neural networks (CNNs) to extract time-invariant features, frequency information, and a sequence to sequence model to capture the complex and long short-term context dependencies between sleep epochs and scores. In addition, to reduce the effect of the class imbalance problem presented in the available sleep datasets, we applied novel loss functions to have an equal misclassified error for each sleep stage while training the network. We evaluated the proposed method on different single-EEG channels (i.e., Fpz-Cz and Pz-Oz EEG channels) from the Physionet Sleep-EDF datasets published in 2013 and 2018. The evaluation results demonstrate that the proposed method achieved the best annotation performance compared to current literature, with an overall accuracy of 84.26%, a macro F1-score of 79.66% and Cohen's Kappa coefficient = 0.79. Our developed model is ready to test with more sleep EEG signals and aid the sleep specialists to arrive at an accurate diagnosis. The source code is available at https://github.com/SajadMo/SleepEEGNet.

Sayed Pedram Haeri Boroujeni, Abolfazl Razi, Sahand Khoshdel et al.

Wildfires have emerged as one of the most destructive natural disasters worldwide, causing catastrophic losses in both human lives and forest wildlife. Recently, the use of Artificial Intelligence (AI) in wildfires, propelled by the integration of Unmanned Aerial Vehicles (UAVs) and deep learning models, has created an unprecedented momentum to implement and develop more effective wildfire management. Although some of the existing survey papers have explored various learning-based approaches, a comprehensive review emphasizing the application of AI-enabled UAV systems and their subsequent impact on multi-stage wildfire management is notably lacking. This survey aims to bridge these gaps by offering a systematic review of the recent state-of-the-art technologies, highlighting the advancements of UAV systems and AI models from pre-fire, through the active-fire stage, to post-fire management. To this aim, we provide an extensive analysis of the existing remote sensing systems with a particular focus on the UAV advancements, device specifications, and sensor technologies relevant to wildfire management. We also examine the pre-fire and post-fire management approaches, including fuel monitoring, prevention strategies, as well as evacuation planning, damage assessment, and operation strategies. Additionally, we review and summarize a wide range of computer vision techniques in active-fire management, with an emphasis on Machine Learning (ML), Reinforcement Learning (RL), and Deep Learning (DL) algorithms for wildfire classification, segmentation, detection, and monitoring tasks. Ultimately, we underscore the substantial advancement in wildfire modeling through the integration of cutting-edge AI techniques and UAV-based data, providing novel insights and enhanced predictive capabilities to understand dynamic wildfire behavior.

Ryan Barker, Tolunay Seyfi, Alireza Ebrahimi Dorcheh et al.

Fifth-generation (5G) systems are increasingly studied as shared communication and computing infrastructure for connected vehicles, roadside edge platforms, and future unmanned-system applications. Yet results from simulators, host-OS emulators, digital twins, and hardware-in-the-loop testbeds are often compared as if timing, input/output (I/O), and control-loop behavior were equivalent across them. They are not. Consequently, apparent limits in throughput, latency, scalability, or real-time behavior may reflect the execution harness rather than the wireless design itself. This paper presents \textit{AtlasRAN}, a capability-oriented framework for modeling and performance evaluation of 5G Open Radio Access Network (O-RAN) platforms. It introduces two reference architectures, terminology that separates functional compatibility from timing fidelity, and a capability matrix that maps research questions to evaluation environments that can support them credibly. O-RAN is used here as an experimental coordinate system spanning Centralized Unit (CU)/Distributed Unit (DU) partitioning, fronthaul transport, control exposure, and core-network anchoring. We validate \textit{AtlasRAN} through a CU-DU uplink load study on a coherent CPU-GPU edge platform. For both a CPU-only baseline and a GPU-accelerated low-density parity-check decoding variant, aggregate goodput drops sharply as user count rises from 1 to 12, while fairness remains near ideal and compute utilization decreases rather than increases. This pattern indicates time-scale dilation and online I/O starvation in the emulation harness, not decoder saturation, as the dominant scaling limit. The key lesson is that timing, memory, and transport semantics must be reported as first-class experimental variables when evaluating ubiquitous 5G infrastructure.

Niloufar Alipour Talemi, Julia Boone, Fatemeh Afghah

The paradigm of Earth Observation analysis is shifting from static deep learning models to autonomous agentic AI. Although recent vision foundation models and multimodal large language models advance representation learning, they often lack the sequential planning and active tool orchestration required for complex geospatial workflows. This survey presents the first comprehensive review of agentic AI in remote sensing. We introduce a unified taxonomy distinguishing between single-agent copilots and multi-agent systems while analyzing architectural foundations such as planning mechanisms, retrieval-augmented generation, and memory structures. Furthermore, we review emerging benchmarks that move the evaluation from pixel-level accuracy to trajectory-aware reasoning correctness. By critically examining limitations in grounding, safety, and orchestration, this work outlines a strategic roadmap for the development of robust, autonomous geospatial intelligence.

Md Raihan Uddin, Tolunay Seyfi, Fatemeh Afghah

Automatic modulation classification (AMC) in real-world deployments demands robustness to distribution shifts arising from hardware impairments, unseen propagation environments, and recording conditions never encountered during training. Although wireless foundation models offer a promising starting point for robust RF representation learning, an important open question is how to adapt them efficiently to out-of-distribution (OOD) downstream tasks without overwriting the structure learned during large-scale pre-training. In this paper, we investigate prompt-based adaptation as a general mechanism for OOD transfer in wireless foundation models. We propose RFPrompt, a parameter-efficient framework that introduces learnable deep prompt tokens while keeping the pretrained backbone frozen, enabling task-specific adaptation with minimal trainable parameters. We instantiate and evaluate this approach on the Large Wireless Model (LWM), a mixture-of-experts wireless foundation model, and study its behavior under both standard and OOD modulation-classification settings. Results show that prompt-based adaptation consistently improves robustness under distribution shift and limited supervision, particularly on real-world over-the-air IQ data, while preserving strong parameter efficiency. These findings suggest that prompt learning is a practical and effective strategy for adapting wireless foundation models to challenging downstream RF environments.

Alireza Ebrahimi Dorcheh, Tolunay Seyfi, Ryan Barker et al.

Efficient downlink radio resource management in 5G requires jointly optimizing user scheduling and transmit-power allocation under time-varying wireless conditions. This is challenging in OFDMA systems because PRB assignment is combinatorial, power allocation is continuous, and performance depends on channel evolution, link adaptation, and long-term fairness. We propose a hierarchical cooperative multi-agent reinforcement learning framework with staged curriculum training for joint downlink PRB and power allocation in a physically grounded 5G environment. System-level simulation is implemented in Sionna, while Sionna RT supports wireless scene construction and mobility-aware ray-traced channel generation. The control task is decomposed into two sequential stages: a PRB agent learns user-level resource shares, which are converted to exact PRB assignments by a deterministic channel-aware quota resolver, and a power agent distributes the base-station power budget across users and their assigned PRB-symbol resources. The framework operates in a cross-layer loop with adaptive modulation and coding, HARQ feedback, outer-loop link adaptation, and a fairness-aware reward based on smoothed throughput and Jain's fairness index. Training stability is improved through a three-phase curriculum for PRB allocation, power control, and joint fine-tuning. Under matched channel realizations, we compare against a PF scheduler with equal-power transmission and two ablations isolating the learned PRB and power-control components. Results show that both learned components improve throughput distribution relative to PF, while the full PRB and power controller achieves the largest cell-throughput gain with only a modest reduction in Jain's fairness index.

Mobin Habibpour, Fatemeh Afghah

While Vision-Language Models (VLMs) are set to transform robotic navigation, existing methods often underutilize their reasoning capabilities. To unlock the full potential of VLMs in robotics, we shift their role from passive observers to active strategists in the navigation process. Our framework outsources high-level planning to a VLM, which leverages its contextual understanding to guide a frontier-based exploration agent. This intelligent guidance is achieved through a trio of techniques: structured chain-of-thought prompting that elicits logical, step-by-step reasoning; dynamic inclusion of the agent's recent action history to prevent getting stuck in loops; and a novel capability that enables the VLM to interpret top-down obstacle maps alongside first-person views, thereby enhancing spatial awareness. When tested on challenging benchmarks like HM3D, Gibson, and MP3D, this method produces exceptionally direct and logical trajectories, marking a substantial improvement in navigation efficiency over existing approaches and charting a path toward more capable embodied agents.

Fatemeh Lotfi, Fatemeh Afghah

With emerging applications such as autonomous driving, smart cities, and smart factories, network slicing has become an essential component of 5G and beyond networks as a means of catering to a service-aware network. However, managing different network slices while maintaining quality of services (QoS) is a challenge in a dynamic environment. To address this issue, this paper leverages the heterogeneous experiences of distributed units (DUs) in ORAN systems and introduces a novel approach to ORAN slicing xApp using distributed deep reinforcement learning (DDRL). Additionally, to enhance the decision-making performance of the RL agent, a prediction rApp based on long short-term memory (LSTM) is incorporated to provide additional information from the dynamic environment to the xApp. Simulation results demonstrate significant improvements in network performance, particularly in reducing QoS violations. This emphasizes the importance of using the prediction rApp and distributed actors' information jointly as part of a dynamic xApp.

Bryce Hopkins, Leo ONeill, Michael Marinaccio et al.

The increasing accessibility of radiometric thermal imaging sensors for unmanned aerial vehicles (UAVs) offers significant potential for advancing AI-driven aerial wildfire management. Radiometric imaging provides per-pixel temperature estimates, a valuable improvement over non-radiometric data that requires irradiance measurements to be converted into visible images using RGB color palettes. Despite its benefits, this technology has been underutilized largely due to a lack of available data for researchers. This study addresses this gap by introducing methods for collecting and processing synchronized visual spectrum and radiometric thermal imagery using UAVs at prescribed fires. The included imagery processing pipeline drastically simplifies and partially automates each step from data collection to neural network input. Further, we present the FLAME 3 dataset, the first comprehensive collection of side-by-side visual spectrum and radiometric thermal imagery of wildland fires. Building on our previous FLAME 1 and FLAME 2 datasets, FLAME 3 includes radiometric thermal Tag Image File Format (TIFFs) and nadir thermal plots, providing a new data type and collection method. This dataset aims to spur a new generation of machine learning models utilizing radiometric thermal imagery, potentially trivializing tasks such as aerial wildfire detection, segmentation, and assessment. A single-burn subset of FLAME 3 for computer vision applications is available on Kaggle with the full 6 burn set available to readers upon request.

Mahshid Rezakhani, Tolunay Seyfi, Fatemeh Afghah

In recent years, rapid technological advancements and expanded Internet access have led to a significant rise in anomalies within network traffic and time-series data. Prompt detection of these irregularities is crucial for ensuring service quality, preventing financial losses, and maintaining robust security standards. While machine learning algorithms have shown promise in achieving high accuracy for anomaly detection, their performance is often constrained by the specific conditions of their training data. A persistent challenge in this domain is the scarcity of labeled data for anomaly detection in time-series datasets. This limitation hampers the training efficacy of both traditional machine learning and advanced deep learning models. To address this, unsupervised transfer learning emerges as a viable solution, leveraging unlabeled data from a source domain to identify anomalies in an unlabeled target domain. However, many existing approaches still depend on a small amount of labeled data from the target domain. To overcome these constraints, we propose a transfer learning-based model for anomaly detection in multivariate time-series datasets. Unlike conventional methods, our approach does not require labeled data in either the source or target domains. Empirical evaluations on novel intrusion detection datasets demonstrate that our model outperforms existing techniques in accurately identifying anomalies within an entirely unlabeled target domain.

Hossein Rajoli, Sahand Khoshdel, Fatemeh Afghah et al.

FlameFinder is a deep metric learning (DML) framework designed to accurately detect flames, even when obscured by smoke, using thermal images from firefighter drones during wildfire monitoring. Traditional RGB cameras struggle in such conditions, but thermal cameras can capture smoke-obscured flame features. However, they lack absolute thermal reference points, leading to false positives.To address this issue, FlameFinder utilizes paired thermal-RGB images for training. By learning latent flame features from smoke-free samples, the model becomes less biased towards relative thermal gradients. In testing, it identifies flames in smoky patches by analyzing their equivalent thermal-domain distribution. This method improves performance using both supervised and distance-based clustering metrics.The framework incorporates a flame segmentation method and a DML-aided detection framework. This includes utilizing center loss (CL), triplet center loss (TCL), and triplet cosine center loss (TCCL) to identify optimal cluster representatives for classification. However, the dominance of center loss over the other losses leads to the model missing features sensitive to them. To address this limitation, an attention mechanism is proposed. This mechanism allows for non-uniform feature contribution, amplifying the critical role of cosine and triplet loss in the DML framework. Additionally, it improves interpretability, class discrimination, and decreases intra-class variance. As a result, the proposed model surpasses the baseline by 4.4% in the FLAME2 dataset and 7% in the FLAME3 dataset for unobscured flame detection accuracy. Moreover, it demonstrates enhanced class separation in obscured scenarios compared to VGG19, ResNet18, and three backbone models tailored for flame detection.

Alireza Ebrahimi, Fatemeh Afghah

5G technology enhances industries with high-speed, reliable, low-latency communication, revolutionizing mobile broadband and supporting massive IoT connectivity. With the increasing complexity of applications on User Equipment (UE), offloading resource-intensive tasks to robust servers is essential for improving latency and speed. The 3GPP's Multi-access Edge Computing (MEC) framework addresses this challenge by processing tasks closer to the user, highlighting the need for an intelligent controller to optimize task offloading and resource allocation. This paper introduces a novel methodology to efficiently allocate both communication and computational resources among individual UEs. Our approach integrates two critical 5G service imperatives: Ultra-Reliable Low Latency Communication (URLLC) and Massive Machine Type Communication (mMTC), embedding them into the decision-making framework. Central to this approach is the utilization of Proximal Policy Optimization, providing a robust and efficient solution to the challenges posed by the evolving landscape of 5G technology. The proposed model is evaluated in a simulated 5G MEC environment. The model significantly reduces processing time by 4% for URLLC users under strict latency constraints and decreases power consumption by 26% for mMTC users, compared to existing baseline models based on the reported simulation results. These improvements showcase the model's adaptability and superior performance in meeting diverse QoS requirements in 5G networks.

Aruna Mohan, Danne Elbers, Or Zilbershot et al.

Remote patient monitoring based on wearable single-lead electrocardiogram (ECG) devices has significant potential for enabling the early detection of heart disease, especially in combination with artificial intelligence (AI) approaches for automated heart disease detection. There have been prior studies applying AI approaches based on deep learning for heart disease detection. However, these models are yet to be widely accepted as a reliable aid for clinical diagnostics, in part due to the current black-box perception surrounding many AI algorithms. In particular, there is a need to identify the key features of the ECG signal that contribute toward making an accurate diagnosis, thereby enhancing the interpretability of the model. In the present study, we develop a vision transformer approach to identify atrial fibrillation based on single-lead ECG data. A residual network (ResNet) approach is also developed for comparison with the vision transformer approach. These models are applied to the Chapman-Shaoxing dataset to classify atrial fibrillation, as well as another common arrhythmia, sinus bradycardia, and normal sinus rhythm heartbeats. The models enable the identification of the key regions of the heartbeat that determine the resulting classification, and highlight the importance of P-waves and T-waves, as well as heartbeat duration and signal amplitude, in distinguishing normal sinus rhythm from atrial fibrillation and sinus bradycardia.

Fatemeh Lotfi, Hossein Rajoli, Fatemeh Afghah

Advanced wireless networks must support highly dynamic and heterogeneous service demands. Open Radio Access Network (O-RAN) architecture enables this flexibility by adopting modular, disaggregated components, such as the RAN Intelligent Controller (RIC), Centralized Unit (CU), and Distributed Unit (DU), that can support intelligent control via machine learning (ML). While deep reinforcement learning (DRL) is a powerful tool for managing dynamic resource allocation and slicing, it often struggles to process raw, unstructured input like RF features, QoS metrics, and traffic trends. These limitations hinder policy generalization and decision efficiency in partially observable and evolving environments. To address this, we propose \textit{ORAN-GUIDE}, a dual-LLM framework that enhances multi-agent RL (MARL) with task-relevant, semantically enriched state representations. The architecture employs a domain-specific language model, ORANSight, pretrained on O-RAN control and configuration data, to generate structured, context-aware prompts. These prompts are fused with learnable tokens and passed to a frozen GPT-based encoder that outputs high-level semantic representations for DRL agents. This design adopts a retrieval-augmented generation (RAG) style pipeline tailored for technical decision-making in wireless systems. Experimental results show that ORAN-GUIDE improves sample efficiency, policy convergence, and performance generalization over standard MARL and single-LLM baselines.

Hossein Kashiani, Niloufar Alipour Talemi, Fatemeh Afghah

Recent advancements in anomaly detection have shifted focus towards Multi-class Unified Anomaly Detection (MUAD), offering more scalable and practical alternatives compared to traditional one-class-one-model approaches. However, existing MUAD methods often suffer from inter-class interference and are highly susceptible to domain shifts, leading to substantial performance degradation in real-world applications. In this paper, we propose a novel robust prompt-driven MUAD framework, called ROADS, to address these challenges. ROADS employs a hierarchical class-aware prompt integration mechanism that dynamically encodes class-specific information into our anomaly detector to mitigate interference among anomaly classes. Additionally, ROADS incorporates a domain adapter to enhance robustness against domain shifts by learning domain-invariant representations. Extensive experiments on MVTec-AD and VISA datasets demonstrate that ROADS surpasses state-of-the-art methods in both anomaly detection and localization, with notable improvements in out-of-distribution settings.

Hossein Kashiani, Niloufar Alipour Talemi, Fatemeh Afghah

Deepfake detectors often struggle to generalize to novel forgery types due to biases learned from limited training data. In this paper, we identify a new type of model bias in the frequency domain, termed spectral bias, where detectors overly rely on specific frequency bands, restricting their ability to generalize across unseen forgeries. To address this, we propose FreqDebias, a frequency debiasing framework that mitigates spectral bias through two complementary strategies. First, we introduce a novel Forgery Mixup (Fo-Mixup) augmentation, which dynamically diversifies frequency characteristics of training samples. Second, we incorporate a dual consistency regularization (CR), which enforces both local consistency using class activation maps (CAMs) and global consistency through a von Mises-Fisher (vMF) distribution on a hyperspherical embedding space. This dual CR mitigates over-reliance on certain frequency components by promoting consistent representation learning under both local and global supervision. Extensive experiments show that FreqDebias significantly enhances cross-domain generalization and outperforms state-of-the-art methods in both cross-domain and in-domain settings.

Fatemeh Lotfi, Hossein Rajoli, Fatemeh Afghah

Modern wireless networks must adapt to dynamic conditions while efficiently managing diverse service demands. Traditional deep reinforcement learning (DRL) struggles in these environments, as scattered and evolving feedback makes optimal decision-making challenging. Large Language Models (LLMs) offer a solution by structuring unorganized network feedback into meaningful latent representations, helping RL agents recognize patterns more effectively. For example, in O-RAN slicing, concepts like SNR, power levels and throughput are semantically related, and LLMs can naturally cluster them, providing a more interpretable state representation. To leverage this capability, we introduce a contextualization-based adaptation method that integrates learnable prompts into an LLM-augmented DRL framework. Instead of relying on full model fine-tuning, we refine state representations through task-specific prompts that dynamically adjust to network conditions. Utilizing ORANSight, an LLM trained on O-RAN knowledge, we develop Prompt-Augmented Multi agent RL (PA-MRL) framework. Learnable prompts optimize both semantic clustering and RL objectives, allowing RL agents to achieve higher rewards in fewer iterations and adapt more efficiently. By incorporating prompt-augmented learning, our approach enables faster, more scalable, and adaptive resource allocation in O-RAN slicing. Experimental results show that it accelerates convergence and outperforms other baselines.

Julia Boone, Tolunay Seyfi, Fatemeh Afghah

Internet of Vehicles (IoV) systems, while offering significant advancements in transportation efficiency and safety, introduce substantial security vulnerabilities due to their highly interconnected nature. These dynamic systems produce massive amounts of data between vehicles, infrastructure, and cloud services and present a highly distributed framework with a wide attack surface. In considering network-centered attacks on IoV systems, attacks such as Denial-of-Service (DoS) can prohibit the communication of essential physical traffic safety information between system elements, illustrating that the security concerns for these systems go beyond the traditional confidentiality, integrity, and availability concerns of enterprise systems. Given the complexity and volume of data generated by IoV systems, traditional security mechanisms are often inadequate for accurately detecting sophisticated and evolving cyberattacks. Here, we present an unsupervised autoencoder method trained entirely on benign network data for the purpose of unseen attack detection in IoV networks. We leverage a weighted combination of reconstruction and triplet margin loss to guide the autoencoder training and develop a diverse representation of the benign training set. We conduct extensive experiments on recent network intrusion datasets from two different application domains, industrial IoT and home IoT, that represent the modern IoV task. We show that our method performs robustly for all unseen attack types, with roughly 99% accuracy on benign data and between 97% and 100% performance on anomaly data. We extend these results to show that our model is adaptable through the use of transfer learning, achieving similarly high results while leveraging domain features from one domain to another.

Sayed Pedram Haeri Boroujeni, Niloufar Mehrabi, Fatemeh Afghah et al.

Fire and smoke phenomena pose a significant threat to the natural environment, ecosystems, and global economy, as well as human lives and wildlife. In this particular circumstance, there is a demand for more sophisticated and advanced technologies to implement an effective strategy for early detection, real-time monitoring, and minimizing the overall impacts of fires on ecological balance and public safety. Recently, the rapid advancement of Artificial Intelligence (AI) and Computer Vision (CV) frameworks has substantially revolutionized the momentum for developing efficient fire management systems. However, these systems extensively rely on the availability of adequate and high-quality fire and smoke data to create proficient Machine Learning (ML) methods for various tasks, such as detection and monitoring. Although fire and smoke datasets play a critical role in training, evaluating, and testing advanced Deep Learning (DL) models, a comprehensive review of the existing datasets is still unexplored. For this purpose, we provide an in-depth review to systematically analyze and evaluate fire and smoke datasets collected over the past 20 years. We investigate the characteristics of each dataset, including type, size, format, collection methods, and geographical diversities. We also review and highlight the unique features of each dataset, such as imaging modalities (RGB, thermal, infrared) and their applicability for different fire management tasks (classification, segmentation, detection). Furthermore, we summarize the strengths and weaknesses of each dataset and discuss their potential for advancing research and technology in fire management. Ultimately, we conduct extensive experimental analyses across different datasets using several state-of-the-art algorithms, such as ResNet-50, DeepLab-V3, and YoloV8.

Amirmohammad Bamdad, Ali Owfi, Fatemeh Afghah

DL-based automatic modulation classification (AMC) models are highly susceptible to adversarial attacks, where even minimal input perturbations can cause severe misclassifications. While adversarially training an AMC model based on an adversarial attack significantly increases its robustness against that attack, the AMC model will still be defenseless against other adversarial attacks. The theoretically infinite possibilities for adversarial perturbations mean that an AMC model will inevitably encounter new unseen adversarial attacks if it is ever to be deployed to a real-world communication system. Moreover, the computational limitations and challenges of obtaining new data in real-time will not allow a full training process for the AMC model to adapt to the new attack when it is online. To this end, we propose a meta-learning-based adversarial training framework for AMC models that substantially enhances robustness against unseen adversarial attacks and enables fast adaptation to these attacks using just a few new training samples, if any are available. Our results demonstrate that this training framework provides superior robustness and accuracy with much less online training time than conventional adversarial training of AMC models, making it highly efficient for real-world deployment.

Ali Owfi, Ali Abbasi, Fatemeh Afghah et al.

Modulation recognition is a fundamental task in communication systems as the accurate identification of modulation schemes is essential for reliable signal processing, interference mitigation for coexistent communication technologies, and network optimization. Incorporating deep learning (DL) models into modulation recognition has demonstrated promising results in various scenarios. However, conventional DL models often fall short in online dynamic contexts, particularly in class incremental scenarios where new modulation schemes are encountered during online deployment. Retraining these models on all previously seen modulation schemes is not only time-consuming but may also not be feasible due to storage limitations. On the other hand, training solely on new modulation schemes often results in catastrophic forgetting of previously learned classes. This issue renders DL-based modulation recognition models inapplicable in real-world scenarios because the dynamic nature of communication systems necessitate the effective adaptability to new modulation schemes. This paper addresses this challenge by evaluating the performance of multiple Incremental Learning (IL) algorithms in dynamic modulation recognition scenarios, comparing them against conventional DL-based modulation recognition. Our results demonstrate that modulation recognition frameworks based on IL effectively prevent catastrophic forgetting, enabling models to perform robustly in dynamic scenarios.

Michael Marinaccio, Fatemeh Afghah

High-fidelity wildfire monitoring using Unmanned Aerial Vehicles (UAVs) typically requires multimodal sensing - especially RGB and thermal imagery - which increases hardware cost and power consumption. This paper introduces SAM-TIFF, a novel teacher-student distillation framework for pixel-level wildfire temperature prediction and segmentation using RGB input only. A multimodal teacher network trained on paired RGB-Thermal imagery and radiometric TIFF ground truth distills knowledge to a unimodal RGB student network, enabling thermal-sensor-free inference. Segmentation supervision is generated using a hybrid approach of segment anything (SAM)-guided mask generation, and selection via TOPSIS, along with Canny edge detection and Otsu's thresholding pipeline for automatic point prompt selection. Our method is the first to perform per-pixel temperature regression from RGB UAV data, demonstrating strong generalization on the recent FLAME 3 dataset. This work lays the foundation for lightweight, cost-effective UAV-based wildfire monitoring systems without thermal sensors.

Mobin Habibpour, Fatemeh Afghah

Object Goal Navigation (ObjectNav) challenges robots to find objects in unseen environments, demanding sophisticated reasoning. While Vision-Language Models (VLMs) show potential, current ObjectNav methods often employ them superficially, primarily using vision-language embeddings for object-scene similarity checks rather than leveraging deeper reasoning. This limits contextual understanding and leads to practical issues like repetitive navigation behaviors. This paper introduces a novel zero-shot ObjectNav framework that pioneers the use of dynamic, history-aware prompting to more deeply integrate VLM reasoning into frontier-based exploration. Our core innovation lies in providing the VLM with action history context, enabling it to generate semantic guidance scores for navigation actions while actively avoiding decision loops. We also introduce a VLM-assisted waypoint generation mechanism for refining the final approach to detected objects. Evaluated on the HM3D dataset within Habitat, our approach achieves a 46% Success Rate (SR) and 24.8% Success weighted by Path Length (SPL). These results are comparable to state-of-the-art zero-shot methods, demonstrating the significant potential of our history-augmented VLM prompting strategy for more robust and context-aware robotic navigation.

Niloufar Alipour Talemi, Hossein Kashiani, Fatemeh Afghah

Pre-trained Vision-language (VL) models, such as CLIP, have shown significant generalization ability to downstream tasks, even with minimal fine-tuning. While prompt learning has emerged as an effective strategy to adapt pre-trained VL models for downstream tasks, current approaches frequently encounter severe overfitting to specific downstream data distributions. This overfitting constrains the original behavior of the VL models to generalize to new domains or unseen classes, posing a critical challenge in enhancing the adaptability and generalization of VL models. To address this limitation, we propose Style-Pro, a novel style-guided prompt learning framework that mitigates overfitting and preserves the zero-shot generalization capabilities of CLIP. Style-Pro employs learnable style bases to synthesize diverse distribution shifts, guided by two specialized loss functions that ensure style diversity and content integrity. Then, to minimize discrepancies between unseen domains and the source domain, Style-Pro maps the unseen styles into the known style representation space as a weighted combination of style bases. Moreover, to maintain consistency between the style-shifted prompted model and the original frozen CLIP, Style-Pro introduces consistency constraints to preserve alignment in the learned embeddings, minimizing deviation during adaptation to downstream tasks. Extensive experiments across 11 benchmark datasets demonstrate the effectiveness of Style-Pro, consistently surpassing state-of-the-art methods in various settings, including base-to-new generalization, cross-dataset transfer, and domain generalization.

Fatemeh Lotfi, Hossein Rajoli, Fatemeh Afghah

Next-generation networks utilize the Open Radio Access Network (O-RAN) architecture to enable dynamic resource management, facilitated by the RAN Intelligent Controller (RIC). While deep reinforcement learning (DRL) models show promise in optimizing network resources, they often struggle with robustness and generalizability in dynamic environments. This paper introduces a novel resource management approach that enhances the Soft Actor Critic (SAC) algorithm with Sharpness-Aware Minimization (SAM) in a distributed Multi-Agent RL (MARL) framework. Our method introduces an adaptive and selective SAM mechanism, where regularization is explicitly driven by temporal-difference (TD)-error variance, ensuring that only agents facing high environmental complexity are regularized. This targeted strategy reduces unnecessary overhead, improves training stability, and enhances generalization without sacrificing learning efficiency. We further incorporate a dynamic $ρ$ scheduling scheme to refine the exploration-exploitation trade-off across agents. Experimental results show our method significantly outperforms conventional DRL approaches, yielding up to a $22\%$ improvement in resource allocation efficiency and ensuring superior QoS satisfaction across diverse O-RAN slices.

Hossein R. Nowdeh, Jie Ji, Xiaolong Ma et al.

In multimodal learning, dominant modalities often overshadow others, limiting generalization. We propose Modality-Aware Sharpness-Aware Minimization (M-SAM), a model-agnostic framework that applies to many modalities and supports early and late fusion scenarios. In every iteration, M-SAM in three steps optimizes learning. \textbf{First, it identifies the dominant modality} based on modalities' contribution in the accuracy using Shapley. \textbf{Second, it decomposes the loss landscape}, or in another language, it modulates the loss to prioritize the robustness of the model in favor of the dominant modality, and \textbf{third, M-SAM updates the weights} by backpropagation of modulated gradients. This ensures robust learning for the dominant modality while enhancing contributions from others, allowing the model to explore and exploit complementary features that strengthen overall performance. Extensive experiments on four diverse datasets show that M-SAM outperforms the latest state-of-the-art optimization and gradient manipulation methods and significantly balances and improves multimodal learning.

Julia Boone, Fatemeh Afghah

Cyber-physical systems (CPS) are being increasingly utilized for critical applications. CPS combines sensing and computing elements, often having multi-layer designs with networking, computational, and physical interfaces, which provide them with enhanced capabilities for a variety of application scenarios. However, the combination of physical and computational elements also makes CPS more vulnerable to attacks compared to network-only systems, and the resulting impacts of CPS attacks can be substantial. Intelligent intrusion detection systems (IDS) are an effective mechanism by which CPS can be secured, but the majority of current solutions often train and validate on network traffic-only datasets, ignoring the distinct attacks that may occur on other system layers. In order to address this, we develop an adaptable CPS anomaly detection model that can detect attacks within CPS without the need for previously labeled data. To achieve this, we utilize domain adaptation techniques that allow us to transfer known attack knowledge from a network traffic-only environment to a CPS environment. We validate our approach using a state-of-the-art CPS intrusion dataset that combines network, operating system (OS), and Robot Operating System (ROS) data. Through this dataset, we are able to demonstrate the effectiveness of our model across network traffic-only and CPS environments with distinct attack types and its ability to outperform other anomaly detection methods.

Niloufar Alipour Talemi, Hossein Kashiani, Hossein R. Nowdeh et al.

Prompt learning has emerged as a powerful paradigm for adapting vision-language models such as CLIP to downstream tasks. However, existing methods often overfit to seen data, leading to significant performance degradation when generalizing to novel classes or unseen domains. To address this limitation, we propose DiSa, a Directional Saliency-Aware Prompt Learning framework that integrates two complementary regularization strategies to enhance generalization. First, our Cross-Interactive Regularization (CIR) fosters cross-modal alignment by enabling cooperative learning between prompted and frozen encoders. Within CIR, a saliency-aware masking strategy guides the image encoder to prioritize semantically critical image regions, reducing reliance on less informative patches. Second, we introduce a directional regularization strategy that aligns visual embeddings with class-wise prototype features in a directional manner to prioritize consistency in feature orientation over strict proximity. This approach ensures robust generalization by leveraging stable prototype directions derived from class-mean statistics. Extensive evaluations on 11 diverse image classification benchmarks demonstrate that DiSa consistently outperforms state-of-the-art prompt learning methods across various settings, including base-to-novel generalization, cross-dataset transfer, domain generalization, and few-shot learning.

Ali Owfi, Jonathan Ashdown, Kurt Turck et al.

Channel Autoencoders (CAEs) have shown significant potential in optimizing the physical layer of a wireless communication system for a specific channel through joint end-to-end training. However, the practical implementation of CAEs faces several challenges, particularly in realistic and dynamic scenarios. Channels in communication systems are dynamic and change with time. Still, most proposed CAE designs assume stationary scenarios, meaning they are trained and tested for only one channel realization without regard for the dynamic nature of wireless communication systems. Moreover, conventional CAEs are designed based on the assumption of having access to a large number of pilot signals, which act as training samples in the context of CAEs. However, in real-world applications, it is not feasible for a CAE operating in real-time to acquire large amounts of training samples for each new channel realization. Hence, the CAE has to be deployable in few-shot learning scenarios where only limited training samples are available. Furthermore, most proposed conventional CAEs lack fast adaptability to new channel realizations, which becomes more pronounced when dealing with a limited number of pilots. To address these challenges, this paper proposes the Online Meta Learning channel AE (OML-CAE) framework for few-shot CAE scenarios with dynamic channels. The OML-CAE framework enhances adaptability to varying channel conditions in an online manner, allowing for dynamic adjustments in response to evolving communication scenarios. Moreover, it can adapt to new channel conditions using only a few pilots, drastically increasing pilot efficiency and making the CAE design feasible in realistic scenarios.

Hossein Rajoli, Pouya Afshin, Fatemeh Afghah

Unmanned aerial vehicles (UAVs) offer a flexible and cost-effective solution for wildfire monitoring. However, their widespread deployment during wildfires has been hindered by a lack of operational guidelines and concerns about potential interference with aircraft systems. Consequently, the progress in developing deep-learning models for wildfire detection and characterization using aerial images is constrained by the limited availability, size, and quality of existing datasets. This paper introduces a solution aimed at enhancing the quality of current aerial wildfire datasets to align with advancements in camera technology. The proposed approach offers a solution to create a comprehensive, standardized large-scale image dataset. This paper presents a pipeline based on CycleGAN to enhance wildfire datasets and a novel fusion method that integrates paired RGB images as attribute conditioning in the generators of both directions, improving the accuracy of the generated images.