Papers

In standard federated learning systems, the parameter server broadcasts the global model to the participating devices in every iteration. Motivated by the temporal correlation between consecutive global models, differential coding can be applied to global model dissemination to reduce the information magnitude, thereby enabling communication with fewer quantization bits. However, due to wireless link failures, devices may occasionally miss differential updates and consequently fail to reconstruct the global model. As a result, they either continue local training based on an outdated model or remain idle until the next full-model broadcast becomes available. To address this challenge, we propose a mixed-timescale differential coding (MTDC) scheme that performs differential coding at two different levels by adjusting the reference model. With MTDC, a device can reconstruct the latest global model between two full-model broadcasts even if it misses a differential update. We provide a convergence analysis that motivates the design of an age-aware variant of MTDC, along with a device scheduling policy to further improve communication efficiency. Simulation results demonstrate that the proposed MTDC schemes achieve superior learning performance compared to baseline methods under similar communication resource budgets in the presence of downlink transmission failures.

This paper introduces LiTCom, a lightweight transmitter and inference-capable receiver framework, designed to enable robust 6G uplink communication under low signal-to-noise (SNR) conditions. It embraces the resource asymmetry between edge devices and the network infrastructure. LiTCom simplifies transmitter design by applying basic low-pass filtering for source coding and minimal channel coding, significantly reducing the processing complexity. The receiver employs large-scale generative artificial intelligence (GenAI) models to infer high semantic-fidelity content from highly distorted and degraded signals beyond traditional decoding capabilities. Furthermore, efficient power allocation strategies are developed by exploiting data importance to improve system performance, which is measured by the introduced quality of experience (QoE) metric. Simulation results validate the effectiveness of the proposed LiTCom framework and the lightweight coding design. Compared with the 5G NR-like baseline (using JPEG source coding and LDPC channel coding) and the Deep-JSCC baseline, LiTCom achieves SNR gains up to 8 dB and 2.5 dB, respectively, while reducing over 95% transmitter-side computations.

Since the paradigm centered on convolutional neural networks and recurrent architectures was established in 2020, the fundamental backbone networks for audio-visual navigation have undergone no essential changes for more than five years, making them inadequate to support efficient representation of dynamic multimodal sequences. This paper proposes Samba(A Hybrid Mamba for Audio-Visual Navigation). It uses the adaptive selection-enabled Mamba State Encoder (M-SE) to replace conventional GRUs for temporal aggregation, and constructs an Audio Mamba Encoder (AME) to remedy the limitations of convolutional operators in capturing global time-frequency dependencies in spectrograms. Experiments demonstrate that Samba exhibits exceptional generalization performance when facing unheard sound sources and unseen scenes. On the Matterport3D dataset, it improves the navigation success rate (SR) by 11.3% compared with existing state-of-the-art models, and the performance gain is even more pronounced on the Replica dataset, which features finer scene structures. Such modernized architectural reconstruction unlocks stronger embodied representation capabilities at a lower computational cost, thereby providing a highly robust technical pathway for paradigm evolution in the field of audio-visual navigation.

Edge-based Artificial Intelligence (AI) acceleration has recently improved progress in real-time object detection. Object detection on edge devices requires a balance between accuracy, speed, and power efficiency. This paper proposes a customized Deep Learning Processor Unit (DPU)-aware architecture for attention-based YOLO variants deployed on AMD FPGAs. Specifically, we evaluate and benchmark YOLOv26 and YOLOv11, two modern attention-based YOLO variants, on the Xilinx ZCU104 across both standard and oriented object detection tasks. We replace unsupported activation functions, substitute split operations with 1x1 convolutions, and approximate the spatial attention mechanism in a DPU-compatible way. All models are then trained and evaluated across six benchmark datasets such as COCO, Pascal VOC, KITTI, DOTA, DIOR-R, and an in-house human presence dataset, and benchmarked across all eight DPU configurations (B512 to B4096) in terms of mAP, FPS, latency, power, and resource utilization. Notably, YOLOv26n and YOLOv26n-OBB deliver the highest end-to-end throughput at 34.05 and 29.55 FPS for standard and oriented detection, respectively, with an average of 5% absolute reduction in accuracy due to quantization while achieving up to approximately 3x lower power consumption compared with the state of the art.

Large language model (LLM) agents increasingly automate multi-step engineering and informatics workflows, yet they rarely ask how much effort a task actually requires. They often follow a maximum-context-first strategy–re-reading files and dependencies they have already seen–turning a one-line edit into a small code-base audit. We argue the missing capability is task-aware execution-scope estimation: judging a task's difficulty, the information it truly needs, and the shortest reliable path before committing budget. We formalize minimum-sufficient execution and the Agent Cognitive Redundancy Ratio (ACRR), and propose E3 (Estimate, Execute, Expand): the agent estimates an initial operating point, executes a minimum viable path, and expands scope only when verification fails. On MSE-Bench–a deterministic benchmark of 121 edits in a capability-controlled simulator–E3 matches the strongest baseline's 100% success while cutting cost by 85%, tokens by 91%, and inspected files by 92%, and further beats a strong adaptive retrieval baseline by 16%; the gains survive held-out instruction wording and essentially every cost weighting. A companion real-model harness (LLM-Case) corroborates the effect on a live gpt-4o agent editing a real open-source library, with every candidate patch graded by actually running the project's real pytest suite against a measured oracle: the over-reading is milder but real, and E3 is the leanest and fastest policy at comparable task success–its one shortfall a provider rate-limit, not a wrong edit. We frame this as a controlled probe of execution redundancy, not a measurement of any deployed agent, and position task-aware execution as a step toward engineering-grounded AI (EGAI)–agents whose effort is anchored in the engineering reality of the task. We release the framework and benchmark.

We study online control of a known linear dynamical system with adversarial costs and bounded disturbances, measuring regret against a general class of benchmark policies. We introduce counterfactual tracking, which separates the challenge of learning from the challenge of controlling the system. An online learner builds a reference trajectory by selecting or averaging the trajectories that the benchmark policies would have generated under the realized costs and disturbances, and a corrective law steers the system toward that reference. Charging each change in the reference its recovery cost (the cost of steering the system onto the new reference) reduces the problem to online learning with switching costs. Conversely, under additional natural assumptions, we show that this reduction is tight: the two problems have the same minimax regret up to a system-dependent factor, uniformly over horizons and policy classes. The reduction gives sharp regret guarantees for policy classes beyond standard finite-memory parameterizations. For a class of $N$ possibly nonlinear or history-dependent policies, it achieves $O(\sqrt{T\log N})$ regret over $T$ rounds, provided their trajectories remain within a bounded distance of one another and recovery costs are bounded. For the full $\ell_1$ ball of disturbance-response controllers, it achieves $O(\sqrt{T\log T})$ regret, which is minimax optimal in $T$, without assuming a common decay rate for disturbance effects. The framework also improves the best known regret bounds for linear state-feedback policies.

The growing supply of retired electric vehicle batteries presents an opportunity for second-life stationary energy storage, but assembling heterogeneous retired cells into reliable packs is challenging due to substantial variation in capacity, DC internal resistance (DCIR), and self-discharge. This paper proposes a robust optimization framework for cell-to-pack assembly of second-life batteries. A topology-screening stage first identifies minimum-cell series-parallel configurations satisfying inverter and energy requirements, reducing the dimensionality of the subsequent assignment problem. For each candidate topology, a mixed-integer linear program selects cells and assigns them along the series string, enforcing power, voltage, and energy requirements as hard constraints while minimizing a normalized, weighted sum of DCIR spread, capacity spread, and self-discharge imbalance. Additionally, measurement uncertainty in capacity and DCIR is modeled as bounded intervals to guarantee feasibility under worst-case parameter deviations. The framework is evaluated on four heterogeneous inventories for a 10 kW/10 kWh stationary backup application. The proposed method satisfies all feasibility requirements in every case, while single-metric sorting heuristics each fail on at least one inventory. Relative to the best single-metric baseline by objective value, it reduces the normalized mismatch objective by 76-87%, demonstrating that jointly optimizing cell matching with application-level feasibility requirements improves heterogeneous second-life pack assembly under screening uncertainty.

Limited-angle digital breast tomosynthesis (DBT) reconstructs a volume from a few low-dose projections over a narrow arc. At a representative nine-view, $25^{\circ}$ protocol more than 98% of image space is unmeasured, so a learned prior must supply structure in the missing wedge. Conditional diffusion priors achieve strong perceptual quality here but leave three clinical obstacles: inexact data consistency, unlocalized hallucination, and uncalibrated uncertainty. We enforce measurements exactly by replacing the per-step proximal update of a conditional diffusion sampler with exact Euclidean projection onto the data-consistent set, computed via an $m$-dimensional dual system with a one-time Gram matrix $AA^{\top}$ factorization. This projection costs 4.5 ms per step (a $248\times$ speedup) and drives the data residual to the double-precision floor ($2.4\times10^{-13}$). We prove it is the $\rho\to0$ limit of the proximal step, provide a no-harm theorem, and show that exactly consistent sample ensembles have variance supported on null($A$). Thus, the mean's entire error lies in the unmeasured subspace covered by the uncertainty map. On patient-derived breast phantoms, this improves fidelity at no depth-resolution cost. Conversely, a proximal step applied post-update degrades quality, isolating the consistency step's placement as decisive. Isotonic recalibration brings the ensemble spread to a calibrated error scale (expected calibration error $0.029\to0.008$; standardized error $4.7\to0.96$), ranking errors better than the pure prior. We also repair a 20.3% adjoint mismatch in a deployed projector via a materialized operator of record. This is the first data-consistent, uncertainty-calibrated learned reconstruction for limited-angle DBT. The solver naturally relaxes to discrepancy-ball and maximum-a-posteriori modes for noisy measurements.

We optimise bidirectional OESCL-band coherent transmission under total fibre power constraints using a GPU-accelerated boundary-value Raman solver and launch-power optimisation. While no gain is observed without power constraints, for an 18-dBm limit 3-span transmission reversing the O-band direction increases aggregate capacity by up to 24.5%

Neuromorphic computing has so far been driven predominantly by machine-learning workloads, yet its underlying properties also make it particularly well suited to combinatorial optimization problems expressed in Ising or QUBO form. While neuromorphic Ising solvers have been demonstrated, how a given problem should be formulated to best suit neuromorphic dynamics has received far less attention. Maximum-likelihood (ML) channel decoding can be expressed as an Ising/QUBO problem, and two distinct formulations already exist in the quantum-annealing literature: a squared-penalty formulation that uses few spins but produces dense intra-check couplings, and a chain-product formulation that improves locality at the cost of additional auxiliary spins. Both place the ML codeword at the ground state under sufficient constraint enforcement, but they have not been compared under the constraints that neuromorphic hardware imposes. This work provides the first systematic side-by-side comparison of QUBO/Ising formulations of ML decoding for linear codes. We show that the two formulations impose fundamentally different tradeoffs in neuron count, synaptic density, locality, and convergence behavior. The preferred formulation is inseparable from the choice of solver, and the two must be considered jointly. Finally, we show that ground-state correctness alone is an insufficient design criterion, and that signal processing tasks should ideally be co-formulated with their neuromorphic hardware models if neuromorphic computing is to extend into the receiver pipeline.

Multi-agent Reinforcement Learning (MARL) holds great potential for robot swarms, but the black-box nature of neural policies complicates strategic analysis, limiting multi-robot applications. Furthermore, complex swarm behaviors can surprisingly emerge from simple rewards without explicit aggregation incentives. Unveiling the mechanisms behind this emergence is critical, but the disconnection between simple rewards and collective behaviors exacerbates interpretability challenges. This paper aims to reveal the hidden mechanisms in this process. We propose a two-stage EEC (\LinkIII) explanatory framework. This includes a novel analytical tool called the Agent Response Map (ARM), which reveals agents' decision-making patterns across space and identifies regions of aggregation and avoidance. ARM reveals that the robots implicitly learn the geometric fields of the environment and utilize these structures as desired targets for coordinated movement. We validate this finding across two distinct tasks: a cooperative multi-robot shape assembly and a competitive predator-prey pursuit-evasion. 1) In the cooperative task, ARM identifies the unoccupied target interior as the desired destination for robot navigation. As the center becomes occupied, this target region automatically shifts toward the boundary, demonstrating the robots' capacity to autonomously explore unoccupied areas. 2) In the competitive task, ARM surprisingly identifies the boundary of the predators' Voronoi diagram as the convergence destination for prey agents. Together, these two tasks demonstrate the capability of ARM to discover the hidden geometric structures underlying MARL policies in robot swarms.

Generative fixed-filter active noise control (GFANC) effectively attenuates noise with diverse frequency characteristics through the combination of sub control filters. However, it does not incorporate the spatial information of the noise source, which limits its performance, particularly in reverberant environments. To address this limitation, this paper proposes a novel spatial-frequency cued GFANC (SF-GFANC) method that exploits both three-dimensional (3D) spatial and frequency information of the noise source. Specifically, a multi-task convolutional recurrent neural network (CRNN) is designed to estimate the source distance, elevation angle, and azimuth angle as spatial cues, while predicting the combination weights of sub control filters as frequency cues. These spatial-frequency cues jointly guide the generation of the appropriate control filter. In addition, a theoretical analysis of the optimal control filter in reverberant environments is presented, highlighting the importance of 3D spatially conditioned control filter design. Evaluations using both simulated and measured acoustic paths demonstrate that the CRNN is robust to unseen acoustic environments and noise types. Furthermore, the results confirm that SF-GFANC outperforms representative ANC algorithms when handling noise sources across diverse 3D locations and frequency characteristics in reverberant environments.

This study introduces a unified control framework for fixed-wing unmanned aerial vehicles (UAVs) fitted with a pan-tilt (PT) camera, intended to perform an end-to-end mission spanning from initial target detection to accurate terminal engagement. The proposed system employs a three-phase strategy: a vision-based target acquisition phase, an NMPC-based tracking phase, and a terminal guidance phase. During tracking, the framework uses an Unscented Kalman Filter (UKF) to fuse YOLO-based visual detections with inertial measurements, enabling robust target state estimation under unknown dynamics. To ensure reliable visual contact, we introduce a constraint-aware Nonlinear Model Predictive Control (NMPC) strategy that incorporates Control Barrier Functions (CBFs) to explicitly prevent UAV self-occlusion – a common limitation in fixed-wing tracking. Upon satisfying terminal engagement conditions, the system seamlessly transitions control to a quaternion-based Biased Proportional Navigation Guidance (BPNG) law, enforcing precise impact angle constraints. High-fidelity simulations demonstrate that the framework achieves stable, robust tracking and accurate terminal interception while strictly respecting the vehicle's dynamic limits and camera field-of-view constraints.

Scenario-based model predictive control (SBMPC) is a variant of model predictive control (MPC) that explicitly accounts for uncertainty by optimizing control actions over multiple predicted scenarios. However, its computational complexity increases rapidly with the number of scenarios and prediction horizon, limiting its applicability to real-time planning and control. This paper presents a learning-accelerated Alternating Direction Method of Multipliers (ADMM) algorithm for efficiently solving SBMPC problems by leveraging parallel computing and Moreau envelope learning, while maintaining high solution accuracy. We reformulate the SBMPC problems into consensus forms that can be decomposed via ADMM, separating the scenario-dependent dynamics from non-anticipativity constraints and enabling parallel updates across scenarios and time steps. Building on this decomposition, we utilize a learning-to-optimize scheme that leverages Moreau envelope learning of the cost function to accelerate the primal update in ADMM, thereby reducing computation time. The proposed framework is evaluated on a microgrid energy management problem subject to load and renewable generation uncertainties. Comparisons with IPOPT and MadNLP, two popular and modern nonlinear programming solvers, demonstrate substantial computational speedups while maintaining reliable closed-loop control performance.

We propose an interference-free multi-backscatter device (BD) access scheme for orthogonal frequency division multiplexing (OFDM)-based symbiotic backscatter communication (SBC). Specifically, we introduce an orthogonal frequency-code spread (OFC) scheme in which the transmitter reserves empty subcarriers for BDs to incorporate their information through frequency shifting, which effectively suppresses direct-link interference (DLI). Since enabling simultaneous access over shared subcarriers introduces inter-backscatter device interference (IBDI), a blockwise orthogonal code-spread is applied to assign each BD to a unique codeword, thereby mitigating IBDI with orthogonal transmissions of all BD signals in the code domain. We develop a non-coherent energy detector whose performance is analyzed in terms of average probability of missed detection (PMD) and sum-rate under Rayleigh fading. The simulation results validate the OFC scheme and demonstrate low PMD values and high spectral efficiency compared to conventional code-assisted multiple-BD access schemes.

Graph neural networks (GNNs) have emerged as a promising approach to learning wireless policies efficiently by leveraging topology prior and incorporating relational inductive biases. However, when the optimal policy is not permutation equivariant (PE), conventional GNNs suffer from mismatched inductive biases, leading to degraded performance or poor generalizability. This issue arises in wireless tasks with expected objectives, such as channel estimation and end-to-end (E2E) precoding, where the PE property of the optimal policy depends on the underlying channel distribution. In this paper, we propose a novel positional attention-based GNN to learn permutation nonequivariant policies efficiently. The core idea is to incorporate relative positions of vertices into the attention mechanism via an embedding function, enabling the GNNs to capture asymmetric relationships. Consequently, the proposed GNN can represent permutation non-equivariant functions, while retaining high learning efficiency and size generalizability through parameter sharing. We consider channel estimation and E2E precoding as case studies, and prove that their policies are PE to users but not to antennas under spatially correlated channels. We employ the proposed GNN to learn the policies, where the embedding function is designed based on the channel covariance matrix. Simulation results demonstrate that the proposed GNN outperforms existing channel estimation and E2E precoding methods, requires fewer samples for training, and can be generalized to systems with different numbers of antennas and users.

Encrypted control lets a cloud coordinate a fleet of agents on fully homomorphically encrypted state, keeping their positions and commands private. The approximate scheme for real-valued control, CKKS, returns decryptions that carry the encryption noise, a key-recovery leak; the loop must decrypt to actuate, so the leak is unavoidable. Yet the security of approximate FHE is studied statically, encrypted control assumes an honest-but-curious cloud, and persistent-threat games never reach inside the cryptosystem. We model the loop's security under an advanced persistent threat as a two-phase game, passive reconnaissance then active manipulation, separated by a measured residual detector that sees only the manipulation. The passive phase reduces to the known flooding tradeoff; the active defense is re-keying, not bootstrapping, since only re-keying resets accumulated leakage. The active phase is a detection-evasion timing game: overt manipulation is caught, so the rational adversary stays stealthy, and at its Stackelberg equilibrium the defender re-keys on the laziest cadence that denies it, set by the control-theoretic fragility of the graph topology. The marginally-stable graph must re-key far more often than the well-connected one. A three-way tension among FHE precision, control accuracy, and re-key cadence sets where this game lives, between a securability floor and a static-suffices ceiling. The efficient secure point is that window, where re-keying is the price of precision efficiency. More broadly, security for an approximate cryptosystem in a feedback loop is a dynamic game whose defender's move is the scheme's own refresh, applying beyond control to any system that must repeatedly decrypt to act.

This paper proposes a superimposed transmission strategy for cooperative cellular and cell-free massive MIMO systems. By classifying users into near and far, the base station transmits an additional data symbol for each near user, superimposed on the signals from distributed access points. Successive interference cancellation is employed at near-user receivers to decode both symbols. The proposed strategy achieves the highest peak spectral efficiency while maintaining fairness at the cell edge, thereby outperforming all the existing network configurations in system capacity.

We propose a new task, audio diarization. The motivation is that there are applications, such as audio monitoring in an unknown environment, where initially the sound event classes to be recognized are unknown. For such a scenario, we propose to first localize in time relevant sound events and to classify them, e.g., by comparing with known event classes, in a second step. This contribution is dedicated to the first step, which we call audio diarization, as it is reminiscent of the speaker diarization stage that precedes and simplifies the second stage, speech recognition, in multi-talker conversational speech processing. In this contribution, we define audio diarization as detecting onset and offset times of sound events with overlap for an open set of classes and without user prompts. We show how a speaker diarization system can be adjusted for audio diarization and propose an evaluation setup. Compared to a closed-set sound event detection system, the proposed system achieves similar performance with the additional ability to detect novel sounds.

This work presents an examination of the main interactions between grid-following (GFL) and grid-forming (GFM) voltage source converters (VSCs) and synchronous generators (SGs), capturing the dynamics of a real power grid and pointing out the limitations of considering an ideal one for stability studies. Eigenvalue trajectories and participation factors are studied to perform in-depth small-signal analyses. Specifically, the GFL and GFM converters are compared in different grid strength scenarios by varying their rating powers and the grid short circuit ratio. Then, time-domain simulations of the non-linear and the developed linear systems are run to validate the mathematical findings from the stability analysis. The results reveal that the stability of VSCs-dominated grids, either in GFL or GFM mode, is strongly affected by both the grid strength and the VSC power, due to the coupling between the VSC control and the SGs.

Pinching antenna systems (PASS) employing dielectric waveguides have recently emerged as a promising flexible antenna architecture for high-frequency wireless communications. While prior work has focused primarily on millimeter-wave regimes, extending PASS to the terahertz (THz) band introduces distinct electromagnetic phenomena that invalidate conventional modeling assumptions. This paper develops the first analytical framework for THz-PASS that integrates in-waveguide propagation attenuation, evanescent coupling via coupled-mode theory, and THz-specific free-space effects including molecular absorption and its re-radiation noise. Using this model, we benchmark THz-PASS against conventional phased arrays under identical propagation scenarios. Our comparative evaluation reveals that THz-PASS achieves effective gains in spectral efficiency through proximity exploitation, making it particularly well-suited for confined and linear deployment topologies.

The paper introduces the Internet of Agentic Things (IoAT), an architectural framework that integrates agentic AI, IoT, cyber-physical systems, Physical AI, edge computing, and digital twins into a unified closed-loop orchestration framework. The proposed architecture consists of cloud, edge/fog, and physical IoT layers connected through autonomous AI agents that perceive, reason, coordinate, and actuate across distributed cyber-physical environments. The paper formalizes IoAT as a coupled workflow-control problem with nested strategic and tactical decision making using a hylomorphic dynamic programming framework that links agentic planning with physical execution. Smart-building orchestration is presented as a representative use case, and key research challenges related to safety, security, governance, resilience, and trustworthy deployment are discussed.

Recent progress in compressing large-scale 3D Gaussian Splatting (3DGS) data has substantially reduced storage footprint, network transmission bandwidth, and memory traffic to GPU caches before rendering. Yet decoding with advanced 3DGS codecs still takes seconds, making them unsuitable for interactive applications. To systematically address this challenge, we propose SpeedyGS, a Content-Aware 3DGS Compressor that separately optimizes the structural formation and statistical coding. First, in structural formation, we jointly optimize adaptive quantization and pruning under a unified rate-distortion objective, where the rate term is replaced by a lightweight rate proxy that estimates entropy coding cost of the next stage, thereby efficiently regulating Gaussian density and precision to yield a compact scene representation. Then, in the statistical coding phase, Gaussian geometry is converted into sparse octree tokens and subsequently undergoes multi-stage coding, while Gaussian attributes are serialized into a 1D token stream for entropy coding via a complexity-controllable local autoregressive model. SpeedyGS achieves a favorable balance among optimization efficiency, compression performance, decoding latency, and rendering speed. Compared to vanilla 3DGS, SpeedyGS achieves up to 160$\times$ model size reduction with negligible quality degradation across common datasets. Compared to state-of-the-art compression methods, it also offers significantly faster decoding and accelerates optimization by 9$\times$ on consumer-grade hardware. To further reduce decoding overhead, the statistical coding stage also supports channel-wise, fixed-length coding for Gaussian as a simpler alternative, enabling SpeedyGS to better adapt to the underlying application and reduce decoding latency to nearly zero.

Spatial information gleaned from multi-channel input has been shown to lead to improvements in meeting processing tasks like diarization and source separation. At the same time, diarization based on features extracted by large pretrained single-channel foundation models, such as WavLM, achieved state-of-the-art performance. This work compares three approaches to integrate spatial features into foundation model-based diarization systems: the cascade of a beamformer and a single-channel foundation model, a multi-channel foundation model, and the conditioning of the downstream network on explicitly extracted spatial features. Results show that the beamformer front-end is even detrimental to diarization performance in regions of overlapped speech, while best performance is achieved with the conditioning, demonstrating that the incorporation of explicit spatial features is a competitive approach to foundation-model-supported diarization. This approach is further subjected to a detailed error analysis showing that the conditioning system removes errors to a good extent that would occur when either only spectral or only spatial features were used.

The pinching-antenna system (PASS) uses dielectric particles along a low-loss waveguide as reconfigurable passive radiators. Existing analyses conclude that the in-waveguide attenuation is negligible at low frequencies and millimeter wave bands; we show this fails at terahertz (THz), where realizable waveguide losses are dramatically larger. We develop a unified wideband THz-PASS propagation model integrating in-waveguide attenuation, atmospheric absorption, molecular re-radiation noise, and beam squint. Closed-form results follow: a band-averaged coherence factor; a cluster-center placement satisfying a band-edge SINR equalization condition; an associated placement-inversion threshold; and a proposed Switched-Feed PASS (SF-PASS) architecture in which a centrally located radio-frequency switch routes the signal among multiple waveguide segments, with a closed-form insertion-loss payoff threshold. Numerical evaluation at the best PASS-compatible THz operating point shows that SF-PASS substantially outperforms single-feed PASS in spectral efficiency and is competitive with a large-scale antenna array at much lower hardware costs.

Wireless aerial virtual reality (VR) aims to provide immersive access to large-scale scenes, but high-resolution view generation and delivery are jointly constrained by limited bandwidth, latency, and power. 3D Gaussian Splatting (3DGS) can reduce the payload by rendering views from compact pose information, yet its geometry errors may cause severe VR quality degradation. Existing channel-aware or pixel-level resource allocation schemes fail to capture such geometry-sensitive distortion. To address this issue, this paper proposes GeoFovea-GS as a geometry-aware cross-layer framework for communication-efficient wireless aerial VR. A foveated geometry-aware distortion metric is developed to characterize photometric rendering error, geometric inconsistency, and view-dependent perceptual importance in a unified form. Based on this metric, the joint selection of pose-only 3DGS rendering and image/tile correction transmission is formulated as a cross-layer optimization problem under wireless constraints. A lightweight value-of-information scheduler is further developed to allocate communication resources to regions that are both geometry-critical and perceptually important. Experiments on real-world 3DGS scenes demonstrate that GeoFovea-GS achieves superior immersive rendering quality with substantially reduced transmission cost.

This study proposes a Chroma from Luma (CfL)-enhanced Star-Tetrix transform (STT), referred to as CfL-STT, for improving raw image compression in JPEG XS. The proposed CfL-STT integrates CfL prediction into the STT to predict chroma components from the luma component in CFA-sampled raw images. Unlike conventional CfL prediction designed for full-color images, the proposed method employs spatially aligned luma samples obtained via linear interpolation along the horizontal and vertical directions to match the chroma sampling grid. This spatial alignment suppresses high-frequency sensor noise while preserving cross-channel correlation, resulting in a more decorrelated Y-Delta-Du-Dv color space. The proposed method was implemented in the JPEG XS reference software and evaluated on raw image datasets. Experimental results demonstrate that a direct application of CfL prediction yields image-dependent performance and may degrade coding efficiency due to the lack of spatial alignment, whereas the proposed CfL-STT consistently improves coding efficiency in lossless raw image compression while preserving exact reversibility.

Microcontrollers with on-die neural processing units (NPUs) have become mainstream, but the system software hosting them has not: production combinations of Zephyr or FreeRTOS with TensorFlow Lite Micro treat AI inference as an application-layer library, leaving memory fragmentation, accelerator-state hygiene, and model-lifecycle guards as recurring application-developer concerns. We present the Phase 1 foundation of SynapticOS, an open-source runtime built on Zephyr that treats inference as a first-class workload. It contributes four cooperating subsystems: (1) a tensor-aware bump allocator with 16-byte DMA-aligned persistent and ephemeral lifetimes sharing a single arena, achieving constant-time allocation (~154 cycles per call, ~78,000 allocations per second at 150 MHz, invariant across tensor sizes) with zero fragmentation by construction; (2) a four-state hardware abstraction layer for the NPU and DSP, implemented by a deterministic software stub (for CI under QEMU) and a Neutron-flavoured backend (for the NXP MCXN947); (3) a three-state model lifecycle registry with duplicate-name detection, idempotent load/unload, and hot-swap guards; and (4) a four-mark cycle-accurate profiler. We evaluate on the NXP FRDM-MCXN947 (dual Cortex-M33 at 150 MHz) and the qemu_cortex_m3 emulator. Build footprints are 67 KB flash / 184 KB SRAM on FRDM (shell, 128 KB arena) and 24 KB flash / 28 KB SRAM on QEMU (no shell, 8 KB arena). End-to-end inference brackets through the deterministic stub kernel measure 1,038 us on FRDM and 781 us on QEMU for a 16x16x3 INT8 input; these are baseline overhead numbers, not Neutron silicon measurements, which arrive with the real SDK invoke path in Phase 2. A 61-test suite across 10 ZTEST suites passes 100% in 6.6 s on the CI emulator path. SynapticOS is released under Apache 2.0 at https://github.com/Dimitrios-Kafetzis/SynapticOS

The evolution of energy-efficient ultra-low-power (ULP) parallel processors and the diffusion of convolutional neural networks (CNNs) are fueling the advent of autonomous driving nano-sized unmanned aerial vehicles (UAVs). These sub-10 cm robotic platforms are envisioned as next-generation ubiquitous smart-sensors and unobtrusive robotic-helpers. However, the limited computational/memory resources available aboard nano-UAVs introduce the challenge of minimizing and optimizing vision-based CNNs – which to date require error-prone, labor-intensive iterative development flows. This work explores methodologies and software tools to streamline and automate all the deployment of vision-based CNN navigation on a ULP multicore system-on-chip acting as a mission computer on a Crazyflie 2.1 nano-UAV. We focus on the deployment of PULP-Dronet, a state-of-the-art CNN for autonomous navigation of nano-UAVs, from the initial training to the final closed-loop evaluation. Compared to the original hand-crafted CNN, our results show a 2x reduction of memory footprint and a speedup of 1.6x in inference time while guaranteeing the same prediction accuracy and significantly improving the behavior in the field, achieving: i) obstacle avoidance with a peak braking-speed of 1.65 m/s and improving the speed/braking-space ratio of the baseline, ii) free flight in a familiar environment up to 1.96 m/s (0.5 m/s for the baseline), and iii) lane following on a path featuring a 90 deg turn – all while using for computation less than 1.6% of the drone's power budget. To foster new applications and future research, we open-source all the software design in a ready-to-run project compatible with the Crazyflie 2.1

Reinforcement learning (RL) is traditionally concerned with learning a control policy for a fixed environment. In many engineering systems, however, the environment itself is alterable, i.e., physical or operational parameters can be tuned to shape the system's transition dynamics and costs experienced by the RL agent. This motivates jointly optimizing both the policy and the environment design parameters. To this end, we establish an Environment Parameter Gradient Theorem — a formal expression for the gradient of the RL's objective function with respect to environment parameters. The key theoretical device is a generalized action-value function $Q_{\pi,\xi}(s,a,\zeta)$, which comprises two copies of the environment parameters: $\zeta$ governs the cost and transition dynamics at the current state–action pair, while $\xi$ governs the future rollouts. This decoupling yields a tractable closed-form gradient expression and is essential to the theorem's derivation. Building on this result, we develop a model-free algorithm that simultaneously learns the optimal policy and the environment parameters. We demonstrate the efficacy of our framework on a UAV network design problem, where the optimal UAV placement (environment parameters) and communication routes (governed by the policy) are learned jointly to minimize the total communication cost in the network.