Papers

Clarifying the neural basis of speech intelligibility is critical for computational neuroscience and digital speech processing. Recent neuroimaging studies have shown that intelligibility modulates cortical activity beyond simple acoustics, primarily in the superior temporal and inferior frontal gyri. However, previous studies have been largely confined to clean speech, leaving it unclear whether the brain employs condition-invariant neural codes across diverse listening environments. To address this gap, we propose a novel architecture built upon a deep state space model for decoding intelligibility from fMRI signals, specifically tailored to their high-dimensional temporal structure. We present the first attempt to decode intelligibility across acoustically distinct conditions, showing our method significantly outperforms classical approaches. Furthermore, region-wise analysis highlights contributions from auditory, frontal, and parietal regions, and cross-condition transfer indicates the presence of condition-invariant neural codes, thereby advancing understanding of abstract linguistic representations in the brain.

Millimeter-wave (mmWave) and Terahertz (THz)-band communications hold great promise in meeting the growing data-rate demands of next-generation wireless networks, offering abundant bandwidth. To mitigate the severe path loss inherent to these high frequencies and reduce hardware costs, ultra-massive multiple-input multiple-output (UM-MIMO) systems with hybrid beamforming architectures can deliver substantial beamforming gains and enhanced spectral efficiency. However, accurate channel estimation (CE) in mmWave and THz UM-MIMO systems is challenging due to high channel dimensionality and compressed observations from a limited number of RF chains, while the hybrid near- and far-field radiation patterns, arising from large array apertures and high carrier frequencies, further complicate CE. Conventional compressive sensing based frameworks rely on predefined sparsifying matrices, which cannot faithfully capture the hybrid near-field and far-field channel structures, leading to degraded estimation performance. This paper introduces DiffPace, a diffusion-based plug-and-play method for channel estimation. DiffPace uses a diffusion model (DM) to capture the channel distribution based on the hybrid spherical and planar-wave (HPSM) model. By applying the plug-and-play approach, it leverages the DM as prior knowledge, improving CE accuracy. Moreover, DM performs inference by solving an ordinary differential equation, minimizing the number of required inference steps compared with stochastic sampling method. Experimental results show that DiffPace achieves competitive CE performance, attaining -15 dB normalized mean square error (NMSE) at a signal-to-noise ratio (SNR) of 10 dB, with 90% fewer inference steps compared to state-of-the-art schemes, simultaneously providing high estimation precision and enhanced computational efficiency.

As Electric Vehicle (EV) adoption accelerates in urban environments, optimizing charging infrastructure is vital for balancing user satisfaction, energy efficiency, and financial viability. This study advances beyond static models by proposing a digital twin framework that integrates agent-based decision support with embedded optimization to dynamically simulate EV charging behaviors, infrastructure layouts, and policy responses across scenarios. Applied to a localized urban site (a university campus) in Hanoi, Vietnam, the model evaluates operational policies, EV station configurations, and renewable energy sources. The interactive dashboard enables seasonal analysis, revealing a 20% drop in solar efficiency from October to March, with wind power contributing under 5% of demand, highlighting the need for adaptive energy management. Simulations show that dynamic notifications of newly available charging slots improve user satisfaction, while gasoline bans and idle fees enhance slot turnover with minimal added complexity. Embedded metaheuristic optimization identifies near-optimal mixes of fast (30kW) and standard (11kW) solar-powered chargers, balancing energy performance, profitability, and demand with high computational efficiency. This digital twin provides a flexible, computation-driven platform for EV infrastructure planning, with a transferable, modular design that enables seamless scaling from localized to city-wide urban contexts.

Accurate modeling of nonlinear systems is essential for reliable control, yet conventional identification methods often struggle to capture latent dynamics while maintaining stability. We propose a stable-by-design LPV neural network-based state-space (NN-SS) model that simultaneously learns latent states and internal scheduling variables directly from data. The state-transition matrix, generated by a neural network using the learned scheduling variables, is guaranteed to be stable through a Schur-based parameterization. The architecture combines an encoder for initial state estimation with a state-space representer network that constructs the full set of scheduling-dependent system matrices. For training the NN-SS, we develop a framework that integrates multi-step prediction losses with a state-consistency regularization term, ensuring robustness against drift and improving long-horizon prediction accuracy. The proposed NN-SS is evaluated on benchmark nonlinear systems, and the results demonstrate that the model consistently matches or surpasses classical subspace identification methods and recent gradient-based approaches. These findings highlight the potential of stability-constrained neural LPV identification as a scalable and reliable framework for modeling complex nonlinear systems.

High Dynamic Range (HDR) imaging aims to reproduce the wide range of brightness levels present in natural scenes, which the human visual system can perceive but conventional digital cameras often fail to capture due to their limited dynamic range. To address this limitation, we propose a deep learning-based multi-exposure fusion approach for HDR image generation. The method takes a set of differently exposed Low Dynamic Range (LDR) images, typically an underexposed and an overexposed image, and learns to fuse their complementary information using a convolutional neural network (CNN). The underexposed image preserves details in bright regions, while the overexposed image retains information in dark regions; the network effectively combines these to reconstruct a high-quality HDR output. The model is trained in an unsupervised manner, without relying on ground-truth HDR images, making it practical for real-world applications where such data is unavailable. We evaluate our results using the Multi-Exposure Fusion Structural Similarity Index Measure (MEF-SSIM) and demonstrate that our approach achieves superior visual quality compared to existing fusion methods. A customized loss function is further introduced to improve reconstruction fidelity and optimize model performance.

Child speech differs from adult speech in acoustics, prosody, and language development, and disfluencies (repetitions, prolongations, blocks) further challenge Automatic Speech Recognition (ASR) and downstream Natural Language Processing (NLP). Recent large audio-language models (LALMs) demonstrate strong cross-modal audio understanding; however, their behavior in disfluent child speech remains underexplored. We evaluate several state-of-the-art LALMs in two settings: an interview (mixed speakers) and a reading task (single child). The tasks are (i) single-channel source separation to isolate the child and (ii) child-only summarization that preserves clinically relevant disfluencies and avoids adult-speech leakage. Evaluation combines Large Language Model (LLM) as a judge, human expert ratings, and BERTScore (F1), and we report agreement between models and between models and humans to assess reliability. Our findings delineate the conditions under which LALMs produce faithful child-only summaries from mixed audio and where they fail, offering practical guidance for clinical and educational deployments. We provide prompts and evaluation scripts to support replication.

Accurate tropical cyclone (TC) short-term intensity forecasting with a 24-hour lead time is essential for disaster mitigation in the Atlantic TC basin. Since most TCs evolve far from land-based observing networks, satellite imagery is critical to monitoring these storms; however, these complex and high-resolution spatial structures can be challenging to qualitatively interpret in real time by forecasters. Here we propose a concise, interpretable, and descriptive approach to quantify fine TC structures with a multi-resolution analysis (MRA) by the discrete wavelet transform, enabling data analysts to identify physically meaningful structural features that strongly correlate with rapid intensity change. Furthermore, deep-learning techniques can build on this MRA for short-term intensity guidance.

Immersive televisualization is important both for telepresence and teleoperation, but resolution and fidelity are often limited by communication bandwidth constraints. We propose a lightweight method for foveated compression of immersive televisualization video streams that can be easily integrated with common video codecs, reducing the required bandwidth if eye tracking data is available. Specifically, we show how to spatially adjust the Quantization Parameter of modern block-based video codecs in a adaptive way based on eye tracking information. The foveal region is transmitted with high fidelity while quality is reduced in the peripheral region, saving bandwidth. We integrate our method with the NimbRo avatar system, which won the ANA Avatar XPRIZE competition. Our experiments show that bandwidth can be reduced to a third without sacrificing immersion. We analyze transmission fidelity with qualitative examples and report quantitative results.

Different transformer architectures implement identical linguistic computations via distinct connectivity patterns, yielding model imprinted “computational fingerprints” detectable through spectral analysis. Using graph signal processing on attention induced token graphs, we track changes in algebraic connectivity (Fiedler value, $\Delta\lambda_2$) under voice alternation across 20 languages and three model families, with a prespecified early window (layers 2–5). Our analysis uncovers clear architectural signatures: Phi-3-Mini shows a dramatic English specific early layer disruption ($\overline{\Delta\lambda_2}_{[2,5]}\!\approx\!-0.446$) while effects in 19 other languages are minimal, consistent with public documentation that positions the model primarily for English use. Qwen2.5-7B displays small, distributed shifts that are largest for morphologically rich languages, and LLaMA-3.2-1B exhibits systematic but muted responses. These spectral signatures correlate strongly with behavioral differences (Phi-3: $r=-0.976$) and are modulated by targeted attention head ablations, linking the effect to early attention structure and confirming functional relevance. Taken together, the findings are consistent with the view that training emphasis can leave detectable computational imprints: specialized processing strategies that manifest as measurable connectivity patterns during syntactic transformations. Beyond voice alternation, the framework differentiates reasoning modes, indicating utility as a simple, training free diagnostic for revealing architectural biases and supporting model reliability analysis.

Controllable music generation remains a significant challenge, with existing methods often requiring model retraining or introducing audible artifacts. We introduce MusicRFM, a framework that adapts Recursive Feature Machines (RFMs) to enable fine-grained, interpretable control over frozen, pre-trained music models by directly steering their internal activations. RFMs analyze a model's internal gradients to produce interpretable "concept directions", or specific axes in the activation space that correspond to musical attributes like notes or chords. We first train lightweight RFM probes to discover these directions within MusicGen's hidden states; then, during inference, we inject them back into the model to guide the generation process in real-time without per-step optimization. We present advanced mechanisms for this control, including dynamic, time-varying schedules and methods for the simultaneous enforcement of multiple musical properties. Our method successfully navigates the trade-off between control and generation quality: we can increase the accuracy of generating a target musical note from 0.23 to 0.82, while text prompt adherence remains within approximately 0.02 of the unsteered baseline, demonstrating effective control with minimal impact on prompt fidelity. We release code to encourage further exploration on RFMs in the music domain.

This paper investigates the wisdom of crowds of linear opinion dynamics models evolving on signed networks. Conditions are given under which models such as the DeGroot, Friedkin-Johnsen (FJ) and concatenated FJ models improve or undermine collective wisdom. The extension to dependent initial opinions is also presented, highlighting how the correlation structure influences the feasibility and geometry of the wisdom-improving regions.

Large language models achieve impressive results but distinguishing factual reasoning from hallucinations remains challenging. We propose a spectral analysis framework that models transformer layers as dynamic graphs induced by attention, with token embeddings as signals on these graphs. Through graph signal processing, we define diagnostics including Dirichlet energy, spectral entropy, and high-frequency energy ratios, with theoretical connections to computational stability. Experiments across GPT architectures suggest universal spectral patterns: factual statements exhibit consistent "energy mountain" behavior with low-frequency convergence, while different hallucination types show distinct signatures. Logical contradictions destabilize spectra with large effect sizes ($g>1.0$), semantic errors remain stable but show connectivity drift, and substitution hallucinations display intermediate perturbations. A simple detector using spectral signatures achieves 88.75% accuracy versus 75% for perplexity-based baselines, demonstrating practical utility. These findings indicate that spectral geometry may capture reasoning patterns and error behaviors, potentially offering a framework for hallucination detection in large language models.

Ensuring the safety of vulnerable road users (VRUs), including pedestrians, cyclists, electric scooter riders, and motorcyclists, remains a major challenge for advanced driver assistance systems (ADAS) and connected and automated vehicles (CAV) technologies. Real-world VRU tests are expensive and sometimes cannot capture or repeat rare and hazardous events. In this paper, we present a lightweight, configurable simulation framework that follows European New Car Assessment Program (Euro NCAP) VRU testing protocols. A rule-based finite-state machine (FSM) is developed as a motion planner to provide vehicle automation during the VRU interaction. We also integrate ego-vehicle perception and idealized Vehicle-to-Everything (V2X) awareness to demonstrate safety margins in different scenarios. This work provides an extensible platform for rapid and repeatable VRU safety validation, paving the way for broader case-study deployment in diverse, user-defined settings, which will be essential for building a more VRU-friendly and sustainable intelligent transportation system.

This paper proposes a time-domain fault location identification method for mixed overhead-underground power distribution systems that can handle challenging fault scenarios such as sub-cycle faults, arcing faults and evolving faults. The proposed method is formulated based on differential equations of the system and accounts for the peculiarities of power distribution systems with distributed generations. It considers the presence of loads, multi-phase laterals and sub-laterals, heterogenous overhead and underground lines, and infeeds and remote-end fault current contributions of distributed generations. It utilizes data collected by limited number of measuring devices installed in modern power distribution systems to systematically eliminate possible multiple fault location estimations to provide a single correct estimation of the actual location of the fault. The performance of the proposed method is demonstrated using IEEE 34-node test system.

The significance of employing a controller in prosthetic hands cannot be overstated, as it plays a crucial role in enhancing the functionality and usability of these systems. This paper introduces an adaptive neuro-controller specifically developed for a tendon-driven soft continuum wrist of a prosthetic hand. Kinematic and dynamic modeling of the wrist is carried out using the Timoshenko beam theory. A Neural Network (NN) based strategy is adopted to predict the required motor currents to manipulate the wrist tendons from the errors in the deflection of the wrist section. The Timoshenko beam theory is used to compute the required tendon tension from the input motor current. A comparison of the adaptive neuro-controller with other similar controllers is conducted to analyze the performance of the proposed approach. Simulation studies and experimental validations of the fabricated wrist are included to demonstrate the effectiveness of the controller.

This paper proposes graph analysis methods to fully automate the fault location identification task in power distribution systems. The proposed methods take basic unordered data from power distribution systems as input, including branch parameters, load values, and the location of measuring devices. The proposed data preparation and analysis methods automatically identify the system's topology and extract essential information, such as faulted paths, structures, loading of laterals and sublaterals, and estimate the fault location accordingly. The proposed graph analysis methods do not require complex node and branch numbering processes or renumbering following changes in the system topology. The proposed methods eliminate the need for human intervention at any step of the fault location identification process. They are scalable and applicable to systems of any size. The performance of the proposed algorithm is demonstrated using the IEEE 34-bus distribution test system.

Conjunction analysis and maneuver planning for spacecraft collision avoidance remains a manual and time-consuming process, typically involving repeated forward simulations of hand-designed maneuvers. With the growing density of satellites in low-Earth orbit (LEO), autonomy is becoming essential for efficiently evaluating and mitigating collisions. In this work, we present an algorithm to design low-thrust collision-avoidance maneuvers for short-term conjunction events. We first formulate the problem as a nonconvex quadratically-constrained quadratic program (QCQP), which we then relax into a convex semidefinite program (SDP) using Shor's relaxation. We demonstrate empirically that the relaxation is tight, which enables the recovery of globally optimal solutions to the original nonconvex problem. Our formulation produces a minimum-energy solution while ensuring a desired probability of collision at the time of closest approach. Finally, if the desired probability of collision cannot be satisfied, we relax this constraint into a penalty, yielding a minimum-risk solution. We validate our algorithm with a high-fidelity simulation of a satellite conjunction in low-Earth orbit with a simulated conjunction data message (CDM), demonstrating its effectiveness in reducing collision risk.

The vision-based grasping brain network integrates visual perception with cognitive and motor processes for visuomotor tasks. While invasive recordings have successfully decoded localized neural activity related to grasp type planning and execution, macroscopic neural activation patterns captured by noninvasive electroencephalography (EEG) remain far less understood. We introduce a novel vision-based grasping platform to investigate grasp-type-specific (precision, power, no-grasp) neural activity across large-scale brain networks using EEG neuroimaging. The platform isolates grasp-specific planning from its associated execution phases in naturalistic visuomotor tasks, where the Filter-Bank Common Spatial Pattern (FBCSP) technique was designed to extract discriminative frequency-specific features within each phase. Support vector machine (SVM) classification discriminated binary (precision vs. power, grasp vs. no-grasp) and multiclass (precision vs. power vs. no-grasp) scenarios for each phase, and were compared against traditional Movement-Related Cortical Potential (MRCP) methods. Low-frequency oscillations (0.5-8 Hz) carry grasp-related information established during planning and maintained throughout execution, with consistent classification performance across both phases (75.3-77.8%) for precision vs. power discrimination, compared to 61.1% using MRCP. Higher-frequency activity (12-40 Hz) showed phase-dependent results with 93.3% accuracy for grasp vs. no-grasp classification but 61.2% for precision vs. power discrimination. Feature importance using SVM coefficients identified discriminative features within frontoparietal networks during planning and motor networks during execution. This work demonstrated the role of low-frequency oscillations in decoding grasp type during planning using noninvasive EEG.

Multimodal Large Language Models (MLLMs) have demonstrated capabilities in audio understanding, but current evaluations may obscure fundamental weaknesses in relational reasoning. We introduce the Music Understanding and Structural Evaluation (MUSE) Benchmark, an open-source resource with 10 tasks designed to probe fundamental music perception skills. We evaluate four SOTA models (Gemini Pro and Flash, Qwen2.5-Omni, and Audio-Flamingo 3) against a large human baseline (N=200). Our results reveal a wide variance in SOTA capabilities and a persistent gap with human experts. While Gemini Pro succeeds on basic perception, Qwen and Audio Flamingo 3 perform at or near chance, exposing severe perceptual deficits. Furthermore, we find Chain-of-Thought (CoT) prompting provides inconsistent, often detrimental results. Our work provides a critical tool for evaluating invariant musical representations and driving development of more robust AI systems.

This paper addresses motion planning and con- trol of an overactuated 4-wheel drive train with independent steering (4WIS) where mechanical constraints prevent the wheels from executing full 360-degree rotations (swerve). The configuration space of such a robot is constrained and contains discontinuities that affect the smoothness of the robot motion. We introduce a mathematical formulation of the steering constraints and derive discontinuity planes that partition the velocity space into regions of smooth and efficient motion. We further design the motion planner for path tracking and ob- stacle avoidance that explicitly accounts for swerve constraints and the velocity transition smoothness. The motion controller uses local feedback to generate actuation from the desired velocity, while properly handling the discontinuity crossing by temporarily stopping the motion and repositioning the wheels. We implement the proposed motion planner as an extension to ROS Navigation package and evaluate the system in simulation and on a physical robot.

Electrical grid congestion is a growing challenge in Europe, driving the need for accurate prediction of load, particularly of peak load. Non-time-resolved models of peak load offer the advantages of simplicity and compactness, and among them, Velander's formula (VF) is a traditional method that has been used for decades. Moreover, VF can be adapted into a quantile VF, which learns a truncated cumulative distribution function of peak load based on electricity consumption. This paper proposes a mathematical model based on extreme value theory to characterize the probability distribution of peak load for large non-residential customers. The model underpins the quantile VF as demonstrated through multiple quantile regression and reduces its representation to just four parameters without sacrificing predictive performance. Moreover, using maximum likelihood estimation and the likelihood ratio test, we validate that the probability distribution of peak load of analysed groups belongs to the heavy-tailed Fréchet class.

Within the project management context, project scheduling serves as an indispensable component, functioning as a fundamental tool for planning, monitoring, controlling, and managing projects more broadly. Although the resource-constrained project scheduling problem (RCPSP) lies at the core of project management activities, it remains largely disconnected from the broader literature on model-based systems engineering (MBSE), thereby limiting its integration into the design and management of complex systems. The original contribution of this paper is twofold. First, the paper seeks to reconcile the RCPSP with the broader literature and vocabulary of model-based systems engineering and hetero-functional graph theory (HFGT). A concrete translation pipeline from an activity-on-node network to a SysML activity diagram, and then to an operand net is constructed. Using this representation, it specializes the hetero-functional network minimum-cost flow (HFNMCF) formulation to the RCPSP context as a systematic means of HFGT for quantitative analysis and proves that the RCPSP is recoverable as a special case of a broader model. Secondly, on an illustrative instance with renewable and non-renewable operands, the specialized HFNMCF, while producing similar schedules, yields explicit explanations of the project states that enable richer monitoring and control. Overall, the framework preserves the strengths of the classical RCPSP while accommodating real-world constraints and enterprise-level decision processes encountered in large, complex megaprojects.

Terahertz inter-satellite links enable unprecedented sensing precision for Low Earth Orbit (LEO) constellations, yet face fundamental bounds from hardware impairments, pointing errors, and network interference. We develop a Network Cramér-Rao Lower Bound (N-CRLB) framework incorporating dynamic topology, hardware quality factor $\Gamma_{\text{eff}}$, phase noise $\sigma^2_\phi$, and cooperative effects through recursive Fisher Information analysis. Our analysis reveals three key insights: (i) hardware and phase noise create power-independent performance ceilings ($\sigma_{\text{ceiling}} \propto \sqrt{\Gamma_{\text{eff}}}$) and floors ($\sigma_{\text{floor}} \propto \sqrt{\sigma^2_\phi}/f_c$), with power-only scaling saturating above $\text{SNR}_{\text{crit}}=1/\Gamma_{\text{eff}}$; (ii) interference coefficients $\alpha_{\ell m}$ enable opportunistic sensing with demonstrated gains of 5.5~dB under specific conditions (65~dB processing gain, 50~dBi antennas); (iii) measurement correlations from shared timing references, when properly modeled, do not degrade performance and can provide common-mode rejection benefits compared to mismodeled independent-noise baselines. Sub-millimeter ranging requires co-optimized hardware ($\Gamma_{\text{eff}}<0.01$), oscillators ($\sigma^2_\phi<10^{-2}$), and appropriate 3D geometry configurations.

We present an experimental unit that realizes the “multi-input, multi-output manifold” thermal management technology proposed by Lamarre & Raymond (2023). The proposed setup can be used for experiments aimed at controlling spatiotemporal temperature distribution. Temperature control is achieved by impinging coolant fluid jets, leveraging a manifold of channels targeted to the surface. The direction of the fluid is controlled by shifting the role of channels between inputs, outputs, or closing them. Files associated with this work include Computer-Aided Design (CAD) STEP files, Gerber files to manufacture a Printed Circuit Board (PCB), and a Graphical User Interface (GUI) written in Python. We provide a step-by-step guide to assemble the experimental setup. We also provide instructions to interact with the setup through the GUI, which allows for real-time tracking of sample temperature and flow rates per flow control device. Additionally, we provide examples of usage of the setup, including system characterization with step response, Proportional-Integral-Derivative performance tracking, and disturbance rejection in a coupled system. Extending the application is accessible through the files provided in the open repository associated with this work. The active cooling device presents a safe, flexible, and complete design, allowing for lab-scale assessment of the performance of custom temperature control strategies using enclosed impinging jets.

Emerging technologies such as Reconfigurable Intelligent Surfaces (RIS) make it possible to optimize some parameters of wireless channels. Conventional approaches require relating the channel and its programmable parameters via a simple model that supports rapid optimization, e.g., re-tuning the parameters each time the users move. However, in practice such models are often crude approximations of the channel, and a more faithful description can be obtained via complex simulators, or only by measurements. In this work, we introduce a novel approach for rapid optimization of programmable channels based on AI-aided Annealed Langevin Dynamics (ALD), which bypasses the need for explicit channel modeling. By framing the ALD algorithm using the MAP estimate, we design a deep unfolded ALD algorithm that leverages a Deep Neural Network (DNN) to estimate score gradients for optimizing channel parameters. We introduce a training method that overcomes the need for channel modeling using zero-order gradients, combined with active learning to enhance generalization, enabling optimization in complex and dynamically changing environments. We evaluate the proposed method in RIS-aided scenarios subject to rich-scattering effects. Our results demonstrate that our AI-aided ALD method enables rapid and reliable channel parameter tuning with limited latency.

Over 70 million people worldwide experience stuttering, yet most automatic speech systems misinterpret disfluent utterances or fail to transcribe them accurately. Existing methods for stutter correction rely on handcrafted feature extraction or multi-stage automatic speech recognition (ASR) and text-to-speech (TTS) pipelines, which separate transcription from audio reconstruction and often amplify distortions. This work introduces StutterZero and StutterFormer, the first end-to-end waveform-to-waveform models that directly convert stuttered speech into fluent speech while jointly predicting its transcription. StutterZero employs a convolutional-bidirectional LSTM encoder-decoder with attention, whereas StutterFormer integrates a dual-stream Transformer with shared acoustic-linguistic representations. Both architectures are trained on paired stuttered-fluent data synthesized from the SEP-28K and LibriStutter corpora and evaluated on unseen speakers from the FluencyBank dataset. Across all benchmarks, StutterZero had a 24% decrease in Word Error Rate (WER) and a 31% improvement in semantic similarity (BERTScore) compared to the leading Whisper-Medium model. StutterFormer achieved better results, with a 28% decrease in WER and a 34% improvement in BERTScore. The results validate the feasibility of direct end-to-end stutter-to-fluent speech conversion, offering new opportunities for inclusive human-computer interaction, speech therapy, and accessibility-oriented AI systems.

Room impulse responses are a core resource for dereverberation, robust speech recognition, source localization, and room acoustics estimation. We present RIR-Mega, a large collection of simulated RIRs described by a compact, machine friendly metadata schema and distributed with simple tools for validation and reuse. The dataset ships with a Hugging Face Datasets loader, scripts for metadata checks and checksums, and a reference regression baseline that predicts RT60 like targets from waveforms. On a train and validation split of 36,000 and 4,000 examples, a small Random Forest on lightweight time and spectral features reaches a mean absolute error near 0.013 s and a root mean square error near 0.022 s. We host a subset with 1,000 linear array RIRs and 3,000 circular array RIRs on Hugging Face for streaming and quick tests, and preserve the complete 50,000 RIR archive on Zenodo. The dataset and code are public to support reproducible studies.

This paper presents a novel Lyapunov-Based Quantum Reinforcement Learning (LQRL) framework that integrates quantum policy optimization with Lyapunov stability analysis for continuous-time vehicle control. The proposed approach combines the representational power of variational quantum circuits (VQCs) with a stability-aware policy gradient mechanism to ensure asymptotic convergence and safe decision-making under dynamic environments. The vehicle longitudinal control problem was formulated as a continuous-state reinforcement learning task, where the quantum policy network generates control actions subject to Lyapunov stability constraints. Simulation experiments were conducted in a closed-loop adaptive cruise control scenario using a quantum-inspired policy trained under stability feedback. The results demonstrate that the LQRL framework successfully embeds Lyapunov stability verification into quantum policy learning, enabling interpretable and stability-aware control performance. Although transient overshoot and Lyapunov divergence were observed under aggressive acceleration, the system maintained bounded state evolution, validating the feasibility of integrating safety guarantees within quantum reinforcement learning architectures. The proposed framework provides a foundational step toward provably safe quantum control in autonomous systems and hybrid quantum-classical optimization domains.

Hamilton-Jacobi (HJ) Reachability offers a framework for generating safe value functions and policies in the face of adversarial disturbance, but is limited by the curse of dimensionality. Physics-informed deep learning is able to overcome this infeasibility, but itself suffers from slow and inaccurate convergence, primarily due to weak PDE gradients and the complexity of self-supervised learning. A few works, recently, have demonstrated that enriching the self-supervision process with regular supervision (based on the nature of the optimal control problem), greatly accelerates convergence and solution quality, however, these have been limited to single player problems and simple games. In this work, we introduce MADR: MPC-guided Adversarial DeepReach, a general framework to robustly approximate the two-player, zero-sum differential game value function. In doing so, MADR yields the corresponding optimal strategies for both players in zero-sum games as well as safe policies for worst-case robustness. We test MADR on a multitude of high-dimensional simulated and real robotic agents with varying dynamics and games, finding that our approach significantly out-performs state-of-the-art baselines in simulation and produces impressive results in hardware.

Principal component analysis (PCA) is a fundamental technique for dimensionality reduction and denoising; however, its application to three-dimensional data with arbitrary orientations – common in structural biology – presents significant challenges. A naive approach requires augmenting the dataset with many rotated copies of each sample, incurring prohibitive computational costs. In this paper, we extend PCA to 3D volumetric datasets with unknown orientations by developing an efficient and principled framework for SO(3)-invariant PCA that implicitly accounts for all rotations without explicit data augmentation. By exploiting underlying algebraic structure, we demonstrate that the computation involves only the square root of the total number of covariance entries, resulting in a substantial reduction in complexity. We validate the method on real-world molecular datasets, demonstrating its effectiveness and opening up new possibilities for large-scale, high-dimensional reconstruction problems.