Papers

Text-to-audio retrieval has made significant progress with shared embedding models such as CLAP and Pengi, yet they often struggle with fine-grained semantic alignment due to the inherent modality gap between text and audio. In this work, we propose FORTE, a unified framework that integrates structured logical reasoning with parameter-efficient cross-modal alignment to improve retrieval precision. Our approach first transforms queries into first-order logic and refines them via a constrained search that preserves semantic invariance while introducing discriminative attributes. The refined representation is then aligned with audio embeddings using a lightweight projection module, followed by a predicate-aware re-ranking step that enforces logical consistency at inference. Extensive experiments on AudioCaps and Clotho demonstrate consistent improvements over strong baselines, particularly in challenging fine-grained scenarios. Our results highlight the effectiveness of combining symbolic reasoning with representation learning for cross-modal retrieval.

We propose an AI Agent tailored for link power management in multi-band systems. In S+C+L band span-level study, the agent efficiently solves various optimization objectives. In network-wide evaluation, it delivers 689.0 Tbps gain in total allocated traffic with merely 303 average interactions per power profile.

In power systems, alternating current optimal power flow (AC-OPF) has been a challenging problem for decades due to its nonconvexity, but fast and efficient solutions are even more needed because of high penetration of large scale renewable generation and load growth. Recently, neural networks (NN) have gained attention in solving AC-OPF, but it is still in an early stage to be applicable for real and large-scale power system operation with topology-changing characteristics. To end this, we propose a novel framework called GraphOPF that considers topology-adaptability, scalability, NN training time, self-supervision, and feasibility altogether. Extensive experiments show that the proposed framework against the baselines is up to 200 times faster in NN training and up to 66 times faster in solving AC-OPF for large-scale power systems including the real Korean power system, while achieving more than 99% feasibility.

Audio-Visual Speech Recognition (AVSR) enhances speech recognition robustness by leveraging visual cues, while real-world scenarios remain challenging due to viewpoint variation, audio distortion, and visual occlusion, which degrade modality quality and increase audio-visual asynchrony. In this paper, we propose a novel Modality-aware Multi-view Self-supervised representation framework for robust Audio-Visual Speech Recognition (M2S-AVSR). First, we introduce a multi-view representation learning encoder to learn view-invariant visual speech representations. Next, we employ a modality-aware module that explicitly models modality quality and cross-modal synchrony to perform fine-grained modality-aware fusion, enabling fine-grained visual information injection during decoding. In addition, we release AISHELL8-RealScene, a public multi-scenario, multi-view conversational audio-visual dataset recorded in real-world environments, and establish a speech recognition benchmark on it. Experiments on English and Mandarin benchmarks demonstrate the effectiveness of the proposed method under challenging conditions. On LRS3, M2S-AVSR achieves up to 29.4% relative improvement under viewpoint perturbation and visual degradation settings. Our method also achieves new state-of-the-art performance on the MISP2021-AVSR test set. On AISHELL8-RealScene, it achieves the best result in outdoor scenes. The proposed method and dataset provide useful support for future research on robust speech and multimodal tasks under realistic conditions.

Phase-sensitive optical time-domain reflectometry ($\phi$-OTDR) is widely used in large-scale distributed acoustic sensing (DAS) because it provides distributed spatiotemporal monitoring over long sensing distances. Its field performance can still deteriorate because of polarization-induced fading (PIF), local signal degradation, and strong environmental interference. This study develops a Sagnac-assisted enhanced $\phi$-OTDR sensing architecture and a standardized benchmark framework for engineering-oriented DAS event recognition. The Sagnac interferometer provides a continuous phase response that supplements fading-prone observations in the $\phi$-OTDR channel, and heterogeneous signal alignment is achieved using a cross-correlation procedure implemented on an FPGA platform. The benchmark protocol compares conventional feature-engineering methods, probabilistic shallow classifiers, single-branch deep models, and dual-branch fusion models under consistent data partitioning, preprocessing, and metric definitions. Experiments on a 10-km sensing fiber with six representative acoustic event classes show that the dual-branch fusion model provides the most favorable trade-off among the evaluated methods, reaching 89.79% accuracy, 89.83% macro-F1, and a nuisance alarm rate of 5.00% on the balanced test set. The results also show that channel grouping strongly affects dual-branch evaluation, indicating that deployment-oriented conclusions should be based on accuracy, macro-F1, nuisance alarm rate, false negative rate, and latency rather than accuracy alone. This work provides a physically motivated enhancement strategy for $\phi$-OTDR-based DAS and a reproducible benchmark protocol for future fusion-oriented sensing research. The implementation and scripts for reproducing the DAS event-recognition experiments are publicly available at https://github.com/wawa-abc/das.

This study presents a comparative analysis between the speaker embeddings of speech foundation models and human subjective perception of speaker similarity. Human listeners have the ability to judge speaker similarity on a continuous scale discerning how similar two voices are. In contrast, speech foundation models embed speaker characteristics into numerical representation. However, a question remains: does the numerical distance between speaker embeddings in these models truly align with the similarity perceived by humans? To address this, we conduct a comprehensive investigation using more than 40 models to compare model-derived distances with human-perceived similarity scores. Furthermore, we identify which factors in model configuration contribute most to a speaker embedding that mirrors human perception. Our findings provide insights for the development of more perceptually grounded speech foundation models.

Automatic Audio Captioning (AAC) seeks to generate natural language descriptions of complex acoustic scenes, bridging auditory perception and language understanding. However, word-selection indeterminacy and increasing reliance on large-scale sequence-to-sequence or LLM-based models limit practical deployment. We propose a resource-efficient AAC framework that explicitly grounds caption generation in auxiliary AudioSet semantics. Frame-level acoustic representations extracted using a ConvNeXt encoder are augmented with top-$K$ predicted AudioSet keywords, providing structured contextual cues for decoding. A compact six-layer BART-style decoder conditions on this joint acoustic-semantic representation, enabling caption generation without LLM-scale decoding. The proposed design balances semantic grounding and computational efficiency within a compact architecture. Evaluations on Clotho V2 and AudioCaps confirm competitive caption quality under practical deployment constraints.

Multimodal sentiment analysis (MSA) infers human affect from language, acoustic, and visual signals. Recent methods increasingly adapt large multimodal models (LMMs) via generative readout: prompting the model to emit a sentiment score as a text string. While convenient, this ties continuous regression to discrete autoregressive decoding, incurring unmeasured costs. We revisit this readout mechanism and propose a discriminative formulation built on the Thinker module of a native omni-modal LLM (Qwen2.5-Omni-7B). Instead of text decoding, we map the final-layer hidden state of the last non-padding token to a continuous score via a lightweight regression head in a single forward pass. Using 4-bit quantization and low-rank adaptation (QLoRA), the entire 7B pipeline – including video and audio processing – trains on a single consumer GPU (RTX 5090, 32 GB) with 10-21 GB peak memory and 1.14% trainable parameters. Through a controlled comparison fixing the backbone, data, and LoRA configuration, we isolate the impact of the readout. On CMU-MOSI and CMU-MOSEI, our discriminative readout reaches state-of-the-art accuracy without task-specific feature engineering (MOSI: MAE 0.551, Corr 0.888; MOSEI: MAE 0.506, Corr 0.790) and exhibits strong multi-seed stability. In contrast, the generative readout – even after equivalent supervised training – more than doubles the mean absolute error, yields unparsable or out-of-range outputs (2.8% zero-shot), and suffers from higher latency. Modality ablations reveal a text-dominant regime on CMU-MOSI. Our findings indicate that how an LMM is read out is as consequential as how it is trained, demonstrating that a discriminative readout offers a more accurate, efficient, and reliable alternative for continuous MSA.

Underwater vehicles are naturally modelled as rigid bodies on SE(3) subjected to added mass effects. The passivity of the Hamiltonian structure of the system can be exploited to design energy-based stabilising controllers, however, the extension of these control designs to tracking control is not trivial since the error system for the classical error formulations is not itself Hamiltonian. In this paper, we show that a novel choice of error function leads to error dynamics that are Hamiltonian. We go on to derive an energy-based tracking control for a fully coupled model of a submersible vehicle. Asymptotic convergence of the control scheme is proved and the control is demonstrated in a simulation study of the Blue Robotics BlueROV2 Heavy submersible.

In humanoid motion control, model predictive control (MPC) offers physically grounded prediction and constraint handling, while reinforcement learning (RL) enables robust whole-body skills through large-scale simulation. However, using MPC inside RL often requires time-consuming problem construction or excessive training overhead, making such frameworks difficult to justify in practice. This work studies efficient training-time MPC guidance for humanoid locomotion and manipulation, termed MPC-RL. We introduce a centroidal-dynamics MPC reward formulation that leverages guidance from MPC trajectories in training time. To make this practical in massively parallel RL, we develop $\pi^n$MPC, a parallel-in-horizon and construction-free batched GPU MPC solver that operates directly on time-varying dynamics to avoid high memory usage and pre-compilation. Through a variety of comparative studies and hardware validations, we have found that MPC-RL achieves superior performance in locomotion and manipulation skills. The code base is available at https://github.com/junhengl/mpc-rl.

Robotic cellular warehousing systems (RCWS) give rise to multi-agent pickup and delivery (MAPD) processes in which robots sequentially collect multiple stock-keeping units (SKUs) for each order. Unlike classical MAPD formulations that assume static tasks, real warehouse operations often involve dynamic order evolution, where new SKUs may be appended to an order while it is being executed. Motivated by this practical requirement, this letter formulates the Dynamic-MAPD problem considering internal order evolution for the first time. Building on the token passing (TP) mechanism, we propose two event-triggered online replanning algorithms. The two strategies target different robot-resource configurations, depending on whether additional robotic resources are available for cooperative assistance. The first, Dynamic-TP, enables an event-triggered dynamic response by allowing robots to replan from their current execution states through priority-aware token acquisition after order updates. The second, Cooperative-TP, further enables reserved robots to assist newly added SKUs while preserving the original order ownership. Simulation results demonstrate that the proposed methods significantly reduce order flowtime compared with static and non-cooperative baselines, thereby improving the order fulfillment efficiency in RCWS.

This paper addresses the question: How can mission effectiveness be systematically defined or approximated in the absence of customer requirements? Legacy requirements engineering frameworks presuppose customer input to define specifications but leave a gap in the process when stakeholder input is ill-defined or missing. Rapid build and development programs (such as military acquisition, space assets, infrastructure projects, etc.) often see requirement and objective evolutions throughout the proposal process, so a more adaptive method is needed. To address this gap, a structured approach is proposed that decomposes mission intent into mission context, functions, constraints, critical dimensions, effectiveness attributes, and architecture alternatives. This method conducts a mission feasibility assessment, prioritizes mission-critical dimensions using Best-Worst Scaling, and introduces a mission complexity factor to quantitatively understand the impacts of external mission difficulties, technology maturity, evidence and confidence standards, and mission utility. The resulting method provides a traceable basis for deriving Tier 1 and 2 requirements. The approach is structured to support future Unified Architecture Framework (UAF) and Systems Modeling Language (SysML) artifact integration. The proposed framework is demonstrated using a notional close air support mission example.

As sixth-generation (6G) wireless systems evolve toward higher frequency bands, large-scale antenna arrays, and intelligent interaction with the wireless environment, conventional fixed-position antennas (FPAs) are increasingly constrained by limited spatial degrees of freedom and insufficient hardware-level adaptability. Fluid antenna systems (FAS) provide new physical-layer flexibility by dynamically reconfiguring antenna ports, geometries, and radiation characteristics. However, existing studies have mainly focused on one- or two-dimensional apertures, leaving the spatial reconfigurability required for complex three-dimensional (3D) propagation environments insufficiently exploited. In this article, we present a 3D spherical fluid antenna system (3D SFAS) architecture for flexible spatially reconfigurable communications. By activating radiating elements in different spherical regions, 3D SFAS realizes array-level spatial reconfiguration through flexible region switching. Within the selected regions, element-level reconfiguration further adjusts the effective aperture size, array topology, and radiation characteristics. This joint framework enables flexible beamforming, concurrent multi-region transmission, blockage-adaptive aperture switching, effective-aperture reconfiguration, and high-resolution 3D aperture control. We also discuss its potential applications in space-air-ground integrated networks, high-mobility communications, integrated sensing and communication systems, and emergency communications. Numerical results demonstrate the potential of 3D SFAS to improve wireless communication performance through flexible spatial reconfiguration. Overall, 3D SFAS extends FAS design beyond 2D position switching toward comprehensive 3D spatial reconfigurability.

Generative models have shown promising results for speech enhancement (SE), but they often rely on multi-step inference, limiting low-latency deployment. We propose SB-RF, a one-step generative framework that integrates Rectified Flow (RF) with Schrödinger Bridge (SB) theory. During training, SB-RF samples intermediate states from an SB time marginal and trains a conditional velocity field with the RF velocity-matching objective. At inference, SB-RF starts from the noisy observation and applies a single Euler update. Experiments show that SB-RF achieves competitive performance among generative methods on the VoiceBank-DEMAND benchmark. To further assess performance beyond this standard setting, we evaluate SB-RF on a simulated low signal-to-noise ratio test set using an expanded training dataset. Under these conditions, SB-RF achieves superior performance over the compared baselines, supporting its potential for real-world applications.

Sound effects (SFX) datasets and libraries often employ distinct tagging schemes, taxonomies, and metadata structures. This creates challenges for research on SFX classification and generation because incompatible taxonomies lead to siloed datasets that might require individualized approaches, result in non-comparable outcomes, and prevent data merging strategies. We propose a modular dataset relabeling framework that adopts the Universal Category System (UCS), an industry-standard hierarchical taxonomy for sound effects, as a shared structural foundation. This open-source framework enables us (i) to convert tags of existing datasets to UCS with a rule-based multi-stage pipeline and conflict resolution to achieve high automatic conversion rates, (ii) to suggest a stratified dataset split for the new labels, and (iii) to combine multiple datasets. To showcase the practical utility, we introduce the EnvSound-UCS dataset, a publicly available unified UCS-compliant dataset of environmental sounds with 58,057 sound clips from three sources: AudioSet, FSD50K, and ESC-50.

Mispronunciation Detection and Diagnosis (MDD) has gained increasing importance in computer-assisted language learning and speech technology in recent years. In this paper, we propose a method for constructing statistical graphs that enable models to learn phoneme confusion patterns represented as directed graphs. Furthermore, we introduce a language-specific strategy to capture systematic pronunciation differences across various native language (L1) backgrounds. The effectiveness of our approach is demonstrated through extensive experiments on the L2-ARCTIC benchmark, where it achieves an F1-score of 59.52%, outperforming several competitive baselines.

Pretrained spatial audio encoders are increasingly used as general-purpose representations for perceptual tasks, yet their spatial encoding capabilities remain poorly understood. We introduce the Spatial Audio Representation Learning (SARL) benchmark, a controlled framework for evaluating spatial information in pretrained audio models. SARL probes source-level factors (azimuth, elevation, distance, class) and room-level factors (RT60, volume, shape). Experiments across diverse encoders reveal three patterns: input configuration and training paradigm shape spatial encoding; source factors are consistently easier to decode than room factors; and sensitivity analysis under controlled perturbations shows heterogeneous responses to source and room variation. These results reveal systematic biases in current pretrained audio representations. SARL is released as an open-source benchmark for reproducible evaluation of spatial audio representations.

As grid-forming (GFM) battery energy storage systems (BESS) are increasingly deployed to enhance power system inertial response and frequency stability, incorporating their frequency support capabilities into day-ahead energy scheduling (DAES) is essential for achieving both frequency security and operational efficiency. However, accurately determining frequency metrics in grids with coexisting GFM inverters and synchronous generators requires electromagnetic transient (EMT) simulations, which are computationally prohibitive for direct embedding in grid operational optimization models. To bridge the gap between modeling accuracy and computational efficiency, a learning-assisted DAES (LA-DAES) framework is proposed in this work. By leveraging a surrogate model to represent the frequency support dynamics of GFM BESS, the proposed framework ensures frequency security with a reasonable solve time. Comparative results demonstrate that, relative to analytical frequency-constrained DAES, the proposed LA-DAES framework more accurately captures grid frequency metrics and improves the utilization of GFM BESS.

In this paper, multi-target tracking and scanning are considered in a radar system operating in the track-while-scan mode. Specifically, time allocation for radar scanning and tracking of multiple maneuvering targets under a time budget constraint is addressed, aiming to jointly optimize the performance of both tracking and scanning in a cognitive radar. We first present the details of the model for tracking and scanning and formulate the time management task as a constrained optimization problem. Subsequently, we design a \gls{cdrl} framework to find the time allocation strategy for the problem. In the proposed \gls{cdrl} framework, the parameters of the neural networks and the dual variable are learned simultaneously. The deep deterministic policy gradient (DDPG) algorithm is introduced to tackle continuous action space and its performance is compared with deep Q-learning, heuristic approaches, and an optimization-based approach. Numerical results show that the radar with the proposed \gls{cdrl} framework can autonomously allocate more time to the tracking task that requires greater attention while providing time for scanning and also constraining the total time budget below the predefined threshold.

Diffusion MRI (dMRI) tractography is the only noninvasive approach for mapping white-matter pathways in the living human brain. It represents each brain as a tractogram: a large, unordered set of three-dimensional streamlines that includes information about both local streamline geometry and whole-brain anatomical organization. This structure makes tractograms a natural but challenging target for representation learning. Existing methods treat streamline classification and subject-level prediction as separate problems: streamline classifiers focus on geometric patterns, whereas subject-level prediction often depends on hand-crafted features. As a result, current methods do not learn reusable representations that connect streamline anatomy with whole-brain inter-subject variation. Here we introduce TractFM, a tractogram foundation model that learns reusable representations directly from whole-brain streamline sets. TractFM combines a local streamline encoder with a permutation-equivariant tractogram encoder, allowing all streamlines from a subject to be contextualized jointly in a single forward pass. Pretraining on dense anatomical tract parcellation, i.e., assigning anatomical labels to individual streamlines, yields two complementary representations: contextualized streamline-level embeddings for tract parcellation and compact subject-level descriptors for downstream prediction of subject phenotypes. Across three tractography algorithms and five dMRI datasets, TractFM transfers to both streamline-level and subject-level tasks. Its frozen representations achieve accurate tract parcellation and predict age and sex across independent datasets. These results show that whole-brain geometric context, learned once, can generalize across tractography pipelines, datasets, and prediction tasks.

Automated surface defect detection is critical for ensuring rigorous quality control in high-speed manufacturing environments. While deep learning models offer remarkable accuracy, deploying them on resource-constrained edge hardware without introducing significant latency remains a persistent challenge. This paper presents Industrial-YOLO, an edge-optimized framework built upon a fine-tuned YOLOv8 architecture specifically engineered for real-time industrial defect detection. We conduct a systematic benchmark utilizing the NEU surface defect database for steel sheets and the MVTec AD dataset, supplemented with custom automotive manufacturing extensions representing real-world structural anomalies (scratches, pits, and inclusions). To bridge the gap between algorithmic complexity and edge hardware constraints, target-specific optimizations are introduced via TensorRT and OpenVINO acceleration engines. Experimental results demonstrate that Industrial-YOLO achieves a high-velocity inference speed exceeding 120 FPS on the NVIDIA Jetson Orin platform while maintaining an exceptional mean Average Precision (mAP) of 98.5%. The proposed framework showcases highly robust, zero-latency performance when deployed directly onto an active automotive assembly line, offering a scalable blueprint for next-generation automated optical inspection (AOI) systems.

The ubiquity of social media platforms facilitates malicious linguistic steganography, posing significant security risks. However, detection is severely hampered by two fundamental issues during model training. Firstly, extreme class imbalance (less than 1% steganographic samples) induces a strong decision bias. Secondly, the invisibility of generative steganography means its features are nearly indistinguishable from benign text; this similarity, compounded by their extreme rarity, leads to severe feature marginalization, where faint steganographic signals are completely overwhelmed. To directly address these optimization-level challenges, we propose FADRW (Feature-Aware Modulated and Dynamically Reweighted Loss), a novel loss function framework engineered for few-shot steganalysis. FADRW employs Dynamic Reweighting to progressively counteract decision bias, and a Feature-Aware Modulation module to structurally reshape the feature space, preventing feature marginalization by enhancing the separability of these subtle features. Extensive experiments on datasets from three real-world social platforms demonstrate that FADRW significantly outperforms state-of-the-art methods, particularly in the challenging few-shot steganographic sample scenario.

Breast cancer remains one of the leading causes of cancer-related mortality among women worldwide, making early detection essential for effective treatment. Mammography is the primary screening modality; however, accurate delineation of suspicious lesions remains challenging and subject to inter-observer variability. Automated segmentation methods can assist radiologists by providing consistent and efficient lesion localization. This study presents DSU-Net, an attention-enhanced Dense Skip U-Net architecture for automated breast lesion segmentation in mammographic images. The proposed framework integrates dense skip connections and attention mechanisms to improve feature propagation, preserve spatial information, and enhance lesion boundary delineation. Experiments were conducted using the Curated Breast Imaging Subset of the Digital Database for Screening Mammography (CBIS-DDSM). To address severe foreground-background imbalance, a composite loss function combining Dice loss, focal loss, and binary cross-entropy loss was employed during training. The proposed model achieved a Dice Similarity Coefficient of 0.9421, an Intersection over Union of 0.8905, an accuracy of 0.9711, and an AUC-ROC of 0.9878 on the validation dataset. Qualitative evaluation demonstrated accurate delineation of lesions with varying sizes and morphologies, while quantitative results confirmed robust discrimination between lesion and background regions. These findings demonstrate that DSU-Net provides accurate and reliable breast lesion segmentation in mammographic images and highlights the potential of attention-guided deep learning for computer-aided breast cancer screening and diagnosis.

Longitudinal medical visual question answering (VQA) requires reasoning about anatomical differences between an image of a current time point and an image of a referred time point. We propose an attention-guided encoder-decoder for this task with chest X-rays. Instead of conventional direct contrast, we propose to include a lightweight affine registration module to reduce nuisance motion by co-registering the current image to the reference image with a small registration regularizer. The registered image pair is fed into the image encoder, followed by a frozen DINO-based mask generator and a trainable adaptive mask generator to produce masks applied to the original image pairs. The masked image pairs are again fed into the image encoder and concatenated with text features as the input to a multimodal transformer-based decoder to generate final answers. To facilitate learning stabilization and clarify the change signal, inspired by DINO-v3, we include additional auxiliary objectives, including a mask rebuilding loss, a pairwise Gram-style consistency loss, and a KoLeo uniformity loss, which enhances the geometry of the representation. On the Medical-Diff-VQA benchmark, the model delivers strong BLEU, ROUGE-L, CIDEr, and METEOR scores while offering intrinsic interpretability through the shared saliency mask. These results support saliency-conditioned generation with mild pre-alignment as a principled framework for longitudinal reasoning in medical VQA. Our training strategy also illustrates the potential of a paradigm in utilizing image foundation models in biomedicine: optimizing both supervised and unsupervised learning objectives simultaneously.

Recent advancements in Large Language Models (LLMs) have shown promising results in music understanding and generation tasks. However, existing works remain confined to Western tonal traditions, offering little insight into whether current LLMs can handle structurally distinct low-resource musical traditions. We present the first systematic evaluation of LLM competence in South Asian classical music, a tradition governed by raga, tala-based melodic constraints that impose fundamentally different structural principles from Western harmony-driven music. We ground our evaluation in Hindustani classical theory and Bengali classical forms, including Rabindra and Nazrul Sangeet – representative low-resource traditions within South Asian classical music. For music understanding evaluation, we introduce a 504-question-answer benchmark spanning raga grammar, cultural knowledge, and symbolic notation reasoning, evaluating 33 LLMs where frontier models such as Gemini 2.5 Pro achieve 85-90% accuracy, while most open-source models remain in the 23-40% range. For music generation, we design a five-level controlled prompting framework and find that even the strongest model produces stylistically faithful outputs only 40% of the time. These results reveal that structural validity and stylistic faithfulness in music generation are distinct objectives and highlight an open challenge for culturally grounded music modeling.

This paper presents a comprehensive 2D analytical model of a toroidal magnetic ring with a square cross-section, subjected to sinusoidal excitation. By applying Maxwell's equations in local Cartesian coordinates and utilizing a complex permeability framework, the exact analytical expressions for the internal magnetic field, flux, complex impedance, and losses are derived. The model rigorously separates eddy current losses, hysteresis losses, and winding losses, explicitly accounting for the skin effect and complex permeability within the conductive core using separation of variables and hyperbolic functions. Furthermore, parameter for apparent permeability is expressed to map the core behavior onto simplified linear material models. The derivations establish a mathematical foundation highly suitable for standardized material characterizations, such as Brockhaus and Iwatsu ring measurements, by avoiding the heavy computational cost of 2D and 3D Finite Element Analysis.

Data-driven Prognostics and Health Management (PHM) uses time-varying condition-monitoring data to diagnose system states and estimate remaining useful life in engineered assets. These tasks are central to maintenance planning, but industrial PHM data are often fragmented, partially observed, and poorly labeled, which hinders supervised learning. Foundation models offer a route toward reusable predictive systems, yet most time-series foundation models are designed for forecasting and assume long, coherent, regularly sampled sequences. To address this gap, we propose a framework for applying Tabular Foundation Models to industrial time series using in-context learning, and we evaluate them on a variety of PHM tasks. By converting raw unit-level signals into tabular rows, we show that these models perform well across multiple tasks - including prognostics, and diagnostics - and are highly data efficient. We compare them directly with sequence models, transformer baselines, and gradient-boosted trees under a common evaluation protocol. The results indicate that tabular foundation models achieve the best average ranks across prognostic and diagnostic tasks. Our findings further show that PFN-based models are competitive in low-data regimes, that temporal context can be preserved in the tabular representation, and that performance depends on representative context construction under subsampling. These results demonstrate that tabular foundation models provide a practical and general interface for heterogeneous PHM problems.

We propose the Control Algorithm Performance Evaluation (CAPE) framework, a systematic methodology for benchmarking racing controllers under our proposed learned enhanced physics model (EPM). The proposed framework enables cross-controller comparison by evaluating five closed-loop control architectures. We further compare our proposed EPM with two state-of-the-art learned vehicle dynamics models: Deep Pacejka Model (DPM) and Deep-learning Dynamics Model (DDM). Closed-loop experiments show that across all models and controllers, the proposed EPM achieves best average lap times. Specifically, the Adaptive NMPC with EPM achieves a time of 5.82 s, compared with 12.99 s for DPM and 8.80 s for DDM, while simultaneously producing substantially lower longitudinal and lateral tracking errors under identical controller configurations. We further evaluate all three models and five controllers using a disturbance-aware simulation framework incorporating measurement noise, process disturbances, actuator delay, and parametric uncertainty. Under moderate global disturbance scaling factor ({\eta} = 1), results averaged across the five controllers show that EPM reduces a) longitudinal tracking error by 29.0% and 17.2%; b) lateral tracking error by 24.6% and 12.3%; c) while increasing average velocity magnitude by 39.9% and 3.1% relative to DPM and DDM, respectively. Overall, CAPE establishes a systematic benchmark for evaluating the performance of learned vehicle dynamics models in a closed-loop control framework and demonstrates that our proposed EPM significantly improves controller robustness and performance under realistic uncertainties.

The safety, security, and reliability of microelectronic systems depend on a trustworthy, secured supply chain and design flow. Globally distributed supply chains or unintentional design weaknesses leave the door open for attacks on the hardware level. These scenarios encompass counterfeiting, hardware trojans, or on-device attacks. For these, hardware reverse engineering (RE) results play a pivotal role. The ongoing publication of new RE-involved attacks motivated the development of the common RE scoring system (CRESS). The system enables a general classification of RE-involved scenarios for a common, consistent rating. In this work, the originally qualitative system is extended to a quantitative system. We performed an extensive interview study with experts in the field. The interview results allowed us to derive weights that measure the severity of different RE-involved attack categories. The weights form an equation that quantifies scenarios, resulting in the severity-indicating CRESS score. The score enables the coherent rating of novel scenarios, renders them comparable, and supports the development of effective countermeasures. To showcase the effectiveness of the quantitative CRESS Score, six selected case studies are rated qualitatively and quantitatively. The CRESS Score proves to be significantly more expressive than the industry-standard Common Vulnerability Scoring System (CVSS).

The power consumption of the analog-to-digital converters (ADCs) and digital-to-analog converters (DACs) in fully digital massive multiple-input multiple-output (MIMO) systems motivates the adoption of low-resolution architectures. In particular, 1-bit DACs reduce the power consumption and hardware complexity at the transmitter, but introduce severe transmit-side quantization distortion. In this paper, we investigate data detection for a point-to-point massive MIMO system with 1-bit DACs at the transmitter, where the linearly precoded signal is dithered prior to quantization, and either full-resolution or 1-bit ADCs at the receiver. Assuming that the dither vector applied at the transmitter is known at the receiver, we first develop softestimation-based data detection methods with symbol-independent dither removal for both full-resolution and 1-bit ADCs. We then introduce a new symbol-dependent linearization of the transmitted signal at the output of the 1-bit DACs and use it to derive maximum-likelihood (ML)-based data detection methods that directly recover the data symbol vector from the received signal. For full-resolution ADCs, this leads to an ML-based method with and without dither removal. For 1-bit ADCs, we develop an approximate ML-based method that exploits the derived statistics of the received signal without dither removal. We also propose low-complexity variants of the ML-based methods to mitigate the exponential complexity growth with the number of streams. Numerical results in terms of symbol error rate highlight the critical role of the dither power and demonstrate that the proposed ML-based methods (along with their low-complexity variants) achieve significant gains over a baseline based on binary ML detection via a homotopy algorithm.