George Floros

Yixian Shen, Zhiheng Yang, Qi Bi et al.

Multimodal spatial reasoning often relies on long chains of intermediate textual and visual thoughts, where accumulating visual tokens and dense cross-modal attention incur substantial computation and memory overhead. To address this challenge, we propose Spectral-Progressive Thought Flow (SpecFlow), a novel lightweight multimodal spatial reasoning framework that represents intermediate visual thoughts in a fixed-size discrete cosine space. By exploiting strong energy compaction, SpecFlow preserves global layout and relational structure while introducing high-frequency details only when increased spatial precision is required. To align visual state evolution with linguistic intent, classifier-free guidance enables autoregressive textual thoughts to steer flow-based updates of the visual workspace/state without expanding the context. As a result, SpecFlow maintains a bounded visual workspace whose updates depend only on the current visual state and accumulated textual trace, enabling long-horizon inference with stable latency and memory usage independent of reasoning depth. Empirical results show that SpecFlow achieves competitive or superior reasoning performance while reducing computation and KV cache costs by up to 2.1 times.

Ilias Exouzidis, Alberto Garcia-Ortiz, George Floros et al.

Through-silicon vias (TSVs) enable dense vertical interconnects in 3D-IC and chiplet systems, but their metal-oxide-silicon structure introduces significant parasitic coupling paths that can degrade the spectral purity of sensitive RF blocks. This paper presents a compact, design-oriented methodology for assessing TSV-induced substrate noise in mixed-signal circuits. We derive a closed-form analytical three-port RLGC macromodel for a Signal-Ground TSV pair that explicitly exposes the substrate node. The methodology is validated using a three-stage Ring VCO designed in a 22 nm FD-SOI technology, where specific RF devices from the process design kit (PDK) provide direct access to the transistor substrate terminals for controlled noise injection. Multi-tone Harmonic Balance simulations in Spectre RF quantify the impact of TSV aggressors on the oscillator's output spectrum. The results indicate that an aggressor of 1 GHz, 0.5 V$_{pp}$ induces a primary sideband spur of -35.2 dBc. Sensitivity characterization reveals that the magnitude of these sideband spurs increases monotonically with the aggressor amplitude. Furthermore, frequency sweeps demonstrate a low-pass coupling response, where the induced spur magnitude decreases from -20.2 dBc at 500 MHz to -33.1 dBc at 2 GHz.

Yixian Shen, Chaoyao Shen, Jan Deen et al.

Large Foundation Model (LFM) inference is both memory- and compute-intensive, traditionally relying on GPUs. However, the limited availability and high cost have motivated the adoption of high-performance general-purpose CPUs, especially emerging 3D-stacked Static Non-Uniform Cache Architecture (3D S-NUCA) systems. These architectures offer enhanced bandwidth and locality but suffer from severe thermal challenges and uneven cache latencies due to 3D Networks-on-Chip (NoC). Optimal management of thread migration and V/f scaling is non-trivial due to LFM kernel diversity and system heterogeneity. Existing thermal management approaches often rely on oversimplified analytical models and lack adaptability. We propose AILFM, an Active Imitation Learning (AIL)-based scheduling framework that learns near-optimal thermal-aware scheduling policies from Oracle demonstrations with minimal run-time overhead. AILFM accounts for both core-level performance heterogeneity and kernel-specific behavior in LFMs to maintain thermal safety while maximizing performance. Extensive experiments show that AILFM outperforms state-of-the-art baselines and generalizes well across diverse LFM workloads.

Oran Hayes, Maria Pantazi-Kypraiou, Athanasios Tziouvaras et al.

Power Delivery Networks (PDNs) are critical for maintaining voltage integrity in modern multiprocessor systems. Conventional early-stage PDN planning relies on static or worst-case power assumptions, often leading to over-provisioned designs and inefficient use of routing resources. This paper proposes a workload-aware methodology for early-stage PDN optimization based on architectural power traces. Using architectural simulations, temporal power activity is captured at fine granularity and mapped to spatial power density distributions across the chip. These distributions are then translated into current demand profiles to guide PDN topology planning at tile granularity. By incorporating realistic workload behavior, the proposed approach enables adaptive PDN resource allocation during early design stages. Experimental results demonstrate that the method achieves up to 32.94% reduction in PDN metal area compared to conventional worst-case designs, while maintaining compliance with IR drop and electromigration constraints.

Athanasios Papanikolaou, Athanasios Tziouvaras, Pavlos Stoikos et al.

Early detection of plant diseases is critical for improving crop productivity, while it also facilitates the foundations of precision agriculture. Recent advances in distributed deep learning have enabled plant disease classification models to be trained across geographically distributed agricultural sensing infrastructures. However, deploying such systems in large-scale Internet of Things (IoT) environments, introduces significant challenges related to computational cost, energy consumption, and system efficiency. In this paper, we present a design-space exploration of hierarchical federated learning architectures for plant disease classification, with a particular focus on the trade-offs between predictive performance and energy efficiency. We further introduce a power- and energy-aware optimization framework that enables the systematic evaluation and selection of model-aggregator configurations under varying deployment constraints. The hierarchical federated architecture organizes distributed clients through intermediate aggregation layers, reducing communication and computational overhead. We evaluate multiple convolutional neural network architectures, including EfficientNet-B0, ResNet-50, and MobileNetV3-Large, in combination with different federated aggregation strategies such as FedAvg, FedProx, and FedAvgM. Experimental results demonstrate that different model-aggregator combinations exhibit distinct performance-energy trade-offs. Consequently, we highlight configurations that achieve competitive diagnostic accuracy and significantly reduce system resource requirements.

Athanasios Tziouvaras, Carolina Fortuna, George Floros et al.

AI-native 6G networks promise unprecedented automation and performance by embedding machine-learning models throughout the radio access and core segments of the network. However, the non-stationary nature of wireless environments due to infrastructure changes, user mobility, and emerging traffic patterns, induces concept drifts that can quickly degrade these model accuracies. Existing methods in general are very domain specific, or struggle with certain type of concept drift. In this paper, we introduce two unsupervised, model-agnostic, batch concept drift detectors. Both methods compute an expected-utility score to decide when concept drift occurred and if model retraining is warranted, without requiring ground-truth labels after deployment. We validate our framework on two real-world wireless use cases in outdoor fingerprinting for localization and for link-anomaly detection, and demonstrate that both methods are outperforming classical detectors such as ADWIN, DDM, CUSUM by 20-40 percentage points. Additionally, they achieve an F1-score of 0.94 and 1.00 in correctly triggering retraining alarm, thus reducing the false alarm rate by up to 20 percentage points compared to the best classical detectors.

Athanasios Tziouvaras, Blaz Bertalanic, George Floros et al.

AI is foreseen to be a centerpiece in next generation wireless networks enabling enabling ubiquitous communication as well as new services. However, in real deployment, feature distribution changes may degrade the performance of AI models and lead to undesired behaviors. To counter for undetected model degradation, we propose ALERT; a method that can detect feature distribution changes and trigger model re-training that works well on two wireless network use cases: wireless fingerprinting and link anomaly detection. ALERT includes three components: representation learning, statistical testing and utility assessment. We rely on MLP for designing the representation learning component, on Kolmogorov-Smirnov and Population Stability Index tests for designing the statistical testing and a new function for utility assessment. We show the superiority of the proposed method against ten standard drift detection methods available in the literature on two wireless network use cases.