Papers

Electroencephalography (EEG) plays a crucial role in brain-computer interfaces (BCIs) and neurological diagnostics, but its real-world deployment faces challenges due to noise artifacts, missing data, and high annotation costs. We introduce SSL-SE-EEG, a framework that integrates Self-Supervised Learning (SSL) with Squeeze-and-Excitation Networks (SE-Nets) to enhance feature extraction, improve noise robustness, and reduce reliance on labeled data. Unlike conventional EEG processing techniques, SSL-SE-EEG} transforms EEG signals into structured 2D image representations, suitable for deep learning. Experimental validation on MindBigData, TUH-AB, SEED-IV and BCI-IV datasets demonstrates state-of-the-art accuracy (91% in MindBigData, 85% in TUH-AB), making it well-suited for real-time BCI applications. By enabling low-power, scalable EEG processing, SSL-SE-EEG presents a promising solution for biomedical signal analysis, neural engineering, and next-generation BCIs.

Accurate simulation of wave propagation in complex acoustic materials is crucial for applications in sound design, noise control, and material engineering. Traditional numerical solvers, such as finite element methods, are computationally expensive, especially when dealing with large-scale or real-time scenarios. In this work, we introduce a dataset of 31,000 acoustic materials, named HA30K, designed and simulated solving the Helmholtz equations. For each material, we provide the geometric configuration and the corresponding pressure field solution, enabling data-driven approaches to learn Helmholtz equation solutions. As a baseline, we explore a deep learning approach based on Stable Diffusion with ControlNet, a state-of-the-art model for image generation. Unlike classical solvers, our approach leverages GPU parallelization to process multiple simulations simultaneously, drastically reducing computation time. By representing solutions as images, we bypass the need for complex simulation software and explicit equation-solving. Additionally, the number of diffusion steps can be adjusted at inference time, balancing speed and quality. We aim to demonstrate that deep learning-based methods are particularly useful in early-stage research, where rapid exploration is more critical than absolute accuracy.

Early recurrence (ER) prediction after curative-intent resection remains a critical challenge in the clinical management of hepatocellular carcinoma (HCC). Although contrast-enhanced computed tomography (CT) with full multi-phase acquisition is recommended in clinical guidelines and routinely performed in many tertiary centers, complete phase coverage is not consistently available across all institutions. In practice, single-phase portal venous (PV) scans are often used alone, particularly in settings with limited imaging resources, variations in acquisition protocols, or patient-related factors such as contrast intolerance or motion artifacts. This variability results in a mismatch between idealized model assumptions and the practical constraints of real-world deployment, underscoring the need for methods that can effectively leverage limited multi-phase data. To address this challenge, we propose a Dual-Branch Prototype-guided (DuoProto) framework that enhances ER prediction from single-phase CT by leveraging limited multi-phase data during training. DuoProto employs a dual-branch architecture: the main branch processes single-phase images, while the auxiliary branch utilizes available multi-phase scans to guide representation learning via cross-domain prototype alignment. Structured prototype representations serve as class anchors to improve feature discrimination, and a ranking-based supervision mechanism incorporates clinically relevant recurrence risk factors. Extensive experiments demonstrate that DuoProto outperforms existing methods, particularly under class imbalance and missing-phase conditions. Ablation studies further validate the effectiveness of the dual-branch, prototype-guided design. Our framework aligns with current clinical application needs and provides a general solution for recurrence risk prediction in HCC, supporting more informed decision-making.

Surgical video datasets are essential for scene understanding, enabling procedural modeling and intra-operative support. However, these datasets are often heavily imbalanced, with rare actions and tools under-represented, which limits the robustness of downstream models. We address this challenge with $SurgiFlowVid$, a sparse and controllable video diffusion framework for generating surgical videos of under-represented classes. Our approach introduces a dual-prediction diffusion module that jointly denoises RGB frames and optical flow, providing temporal inductive biases to improve motion modeling from limited samples. In addition, a sparse visual encoder conditions the generation process on lightweight signals (e.g., sparse segmentation masks or RGB frames), enabling controllability without dense annotations. We validate our approach on three surgical datasets across tasks including action recognition, tool presence detection, and laparoscope motion prediction. Synthetic data generated by our method yields consistent gains of 10-20% over competitive baselines, establishing $SurgiFlowVid$ as a promising strategy to mitigate data imbalance and advance surgical video understanding methods.

Diffusion Posterior Sampling (DPS) provides a principled Bayesian approach to inverse problems by sampling from $p(x_0 \mid y)$. While posterior sampling is valuable for capturing uncertainty and multi-modality, many classical and practical inverse problem settings ultimately prioritize accurate point estimation – most notably the MAP estimator, which has long served as a standard reconstruction objective in imaging and scientific applications. We introduce Local MAP Sampling (LMAPS), a new inference framework that iteratively solves local MAP subproblems along the diffusion trajectory. This perspective clarifies their connection to global MAP and DPS, offering a unified probabilistic interpretation for optimization-based methods. Building on this foundation, we develop practical algorithms with a covariance approximation motivated by a Gaussian prior assumption, and a reformulated objective for stability and interpretability. Across a broad set of image restoration and scientific tasks, LMAPS achieves state-of-the-art performance.

Neural encoding models aim to predict fMRI-measured brain responses to natural images. fMRI data is acquired as a 3D volume of voxels, where each voxel has a defined spatial location in the brain. However, conventional encoding models often flatten this volume into a 1D vector and treat voxel responses as independent outputs. This removes spatial context, discards anatomical information, and ties each model to a subject-specific voxel grid. We introduce the Neural Response Function (NRF), a framework that models fMRI activity as a continuous function over anatomical space rather than a flat vector of voxels. NRF represents brain activity as a continuous implicit function: given an image and a spatial coordinate (x, y, z) in standardized MNI space, the model predicts the response at that location. This formulation decouples predictions from the training grid, supports querying at arbitrary spatial resolutions, and enables resolution-agnostic analyses. By grounding the model in anatomical space, NRF exploits two key properties of brain responses: (1) local smoothness – neighboring voxels exhibit similar response patterns; modeling responses continuously captures these correlations and improves data efficiency, and (2) cross-subject alignment – MNI coordinates unify data across individuals, allowing a model pretrained on one subject to be fine-tuned on new subjects. In experiments, NRF outperformed baseline models in both intrasubject encoding and cross-subject adaptation, achieving high performance while reducing the data size needed by orders of magnitude. To our knowledge, NRF is the first anatomically aware encoding model to move beyond flattened voxels, learning a continuous mapping from images to brain responses in 3D space.

To facilitate the widespread adoption of renewable energy, dispatchable, zero-emission power sources are essential for grid stability. This work performs a comprehensive techno-economic analysis of a self-sustainable thermophotovoltaic (TPV) system, an architecture that integrates solar charging to function as a standalone power generation asset. Using theory-based models for conventional air-bridge InGaAs and Si diode cells, our analysis reveals that while the system is not currently competitive from a pure levelized of storage cost (LCOS) perspective due to the high capital expenditure for thermal battery materials, its primary value lies in its competitive levelized cost of electricity (LCOE), which is comparable to that of conventional dispatchable generators such as gas turbines. Furthermore, we show that a full Si-based TPV system, utilizing a 50-{\mu}m-thick air-bridge cell for enhanced photon utilization, can also achieve an LCOE that is competitive with such conventional power sources at scales exceeding the gigawatt-hour level, despite its lower conversion efficiency relative to its InGaAs counterpart. This highlights a practical engineering pathway for leveraging the immense manufacturing scalability of Si, offering a lower-risk route to deployment compared to III-V materials. Ultimately, this work establishes the self-sustainable TPV architecture as a compelling pathway toward providing grid-scale, on-demand, zero-emission power.

This work presents a nonlinear system identification framework for modeling the power extraction dynamics of wind turbines, including both freestream and waked conditions. The approach models turbine dynamics using data-driven power coefficient maps expressed as combinations of compact radial basis functions and polynomial bases, parameterized in terms of tip-speed ratio and upstream conditions. These surrogate models are embedded in a first-order dynamic system suitable for model-based control. Experimental validation is carried out in two wind tunnel configurations: a low-turbulence tandem setup and a high-turbulence wind farm scenario. In the tandem case, the identified model is integrated into an adapted K\omega^2 controller, resulting in improved tip-speed ratio tracking and power stability compared to BEM-based and steady-state models. In the wind farm scenario, the model captures the statistical behavior of the turbines despite unresolved turbulence. The proposed method enables interpretable, adaptive control across a range of operating conditions without relying on black-box learning strategies.

Autonomous aerial robots are increasingly being deployed in real-world scenarios, where transparent obstacles present significant challenges to reliable navigation and mapping. These materials pose a unique problem for traditional perception systems because they lack discernible features and can cause conventional depth sensors to fail, leading to inaccurate maps and potential collisions. To ensure safe navigation, robots must be able to accurately detect and map these transparent obstacles. Existing methods often rely on large, expensive sensors or algorithms that impose high computational burdens, making them unsuitable for low Size, Weight, and Power (SWaP) robots. In this work, we propose a novel and computationally efficient framework for detecting and mapping transparent obstacles onboard a sub-300g quadrotor. Our method fuses data from a Time-of-Flight (ToF) camera and an ultrasonic sensor with a custom, lightweight 2D convolution model. This specialized approach accurately detects specular reflections and propagates their depth into corresponding empty regions of the depth map, effectively rendering transparent obstacles visible. The entire pipeline operates in real-time, utilizing only a small fraction of a CPU core on an embedded processor. We validate our system through a series of experiments in both controlled and real-world environments, demonstrating the utility of our method through experiments where the robot maps indoor environments containing glass. Our work is, to our knowledge, the first of its kind to demonstrate a real-time, onboard transparent obstacle mapping system on a low-SWaP quadrotor using only the CPU.

Load forecasting has always been a challenge for grid operators due to the growing complexity of power systems. The increase in extreme weather and the need for energy from customers has led to load forecasting sometimes failing. This research presents a Support Vector Regression (SVR) framework for electric load forecasting that outperforms the industry standard. The SVR model demonstrates better accuracy across all evaluation metrics that are important for power system operations. The model has a 54.2% reduction in Mean Squared Error (31.91 vs. 69.63), a 33.5% improvement in Mean Absolute Error, and performance benefits across other metrics. These improvements show significant benefits when integrated with power forecasting tools and show that the approach provides an additional tool for accuracy checking for system planning and resource allocation in times of need for resource allocation in electric power systems.

We investigate the use of a point cloud measurement in terrain-aided navigation. Our goal is to aid an inertial navigation system, by exploring ways to generate a useful measurement innovation error for effective nonlinear state estimation. We compare two such measurement models that involve the scanning of a digital terrain elevation model: a) one that is based on typical ray-casting from a given pose, that returns the predicted point cloud measurement from that pose, and b) another computationally less intensive one that does not require raycasting and we refer to herein as a sliding grid. Besides requiring a pose, it requires the pattern of the point cloud measurement itself and returns a predicted point cloud measurement. We show that the sliding grid achieves comparable accuracy to raycasting, especially at higher altitudes, while being orders of magnitude faster computationally. By eliminating the need for raycasting, the sliding grid removes the dependency on dedicated GPU hardware or high-performance CPUs, making it well-suited for real-time terrain-aided navigation on resource-constrained embedded platforms.

A hybrid detector that fuses both quantized and full-precision observations is proposed for weak signal detection under additive and multiplicative Gaussian noise. We first derive a locally most powerful test (LMPT)–based hybrid detector from the composite probability distribution of the compound observations received by the fusion center, and then analyze its asymptotic detection performance. Subsequently, we optimize the sensor-wise quantization thresholds to achieve near-optimal asymptotic performance at the local sensor level. Moreover, we propose a mixed-integer linear programming approach to solve the optimization problem of transmission bandwidth allocation accounting for bandwidth constraints and error-prone channels. Finally, simulation results demonstrate the superiority of the proposed hybrid detector and the bandwidth allocation strategy, especially in challenging error-prone channel conditions.

This paper presents a nonlinear integrated guidance and control (IGC) approach for flexible leader-follower formation flight of fixed-wing unmanned aerial vehicles (UAVs) while accounting for high-fidelity aerodynamics and thrust dynamics. Unlike conventional leader-follower schemes that fix the follower's position relative to the leader, the follower is steered to maintain range and bearing angles (which is the angle between its velocity vector and its line-of-sight (LOS) with respect to the leader) arbitrarily close to the prescribed values, enabling the follower to maintain formation on a hemispherical region behind the leader. The proposed IGC framework directly maps leader-follower relative range dynamics to throttle commands, and the follower's velocity orientation relative to the LOS to aerodynamic control surface deflections. This enables synergism between guidance and control subsystems. The control design uses a dynamic surface control-based backstepping approach to achieve convergence to the desired formation set, where Lyapunov barrier functions are incorporated to ensure the follower's bearing angle is constrained within specified bounds. Rigorous stability analysis guarantees uniform ultimate boundedness of all error states and strict constraint satisfaction in the presence of aerodynamic nonlinearities. The proposed flexible formation scheme allows the follower to have an orientation mismatch relative to the leader to execute anticipatory reconfiguration by transitioning between the relative positions in the admissible formation set when the leader aggressively maneuvers. The proposed IGC law relies only on relative information and onboard sensors without the information about the leader's maneuver, making it suitable for GPS-denied or non-cooperative scenarios. Finally, we present simulation results to vindicate the effectiveness and robustness of our approach.

The normal forms provide useful approximations for many trajectories of interest within the circular restricted three-body problem. This paper aims to thoroughly compare two of these forms: the Birkhoff normal form and the resonant normal form, highlighting the strengths of each for the representation of center manifold trajectories. A method of station-keeping is introduced, analogous to Floquet modes, in which the unstable component is minimized at specific points along a trajectory through impulsive maneuvers. Three different formulations of the same station-keeping approach are posed, collectively spanning Lyapunov, vertical, and halo orbits, as well as Lissajous and quasihalo trajectories.

Unmanned aerial vehicle (UAV) communications demand accurate yet interpretable air-to-ground (A2G) channel models that can adapt to nonstationary propagation environments. While deterministic models offer interpretability and deep learning (DL) models provide accuracy, both approaches suffer from either rigidity or a lack of explainability. To bridge this gap, we propose the Physics-Inspired Kolmogorov-Arnold Network (PIKAN) that embeds physical principles (e.g., free-space path loss, two-ray reflections) into the learning process. Unlike physics-informed neural networks (PINNs), PIKAN is more flexible for applying physical information because it introduces them as flexible inductive biases. Thus, it enables a more flexible training process. Experiments on UAV A2G measurement data show that PIKAN achieves comparable accuracy to DL models while providing symbolic and explainable expressions aligned with propagation laws. Remarkably, PIKAN achieves this performance with only 232 parameters, making it up to 37 times lighter than multilayer perceptron (MLP) baselines with thousands of parameters, without sacrificing correlation with measurements and also providing symbolic expressions. These results highlight PIKAN as an efficient, interpretable, and scalable solution for UAV channel modelling in beyond-5G and 6G networks.

Magnetic Resonance Imaging (MRI) is a critical tool in modern medical diagnostics, yet its prolonged acquisition time remains a critical limitation, especially in time-sensitive clinical scenarios. While undersampling strategies can accelerate image acquisition, they often result in image artifacts and degraded quality. Recent diffusion models have shown promise for reconstructing high-fidelity images from undersampled data by learning powerful image priors; however, most existing approaches either (i) rely on unsupervised score functions without paired supervision or (ii) apply data consistency only as a post-processing step. In this work, we introduce a conditional denoising diffusion framework with iterative data-consistency correction, which differs from prior methods by embedding the measurement model directly into every reverse diffusion step and training the model on paired undersampled-ground truth data. This hybrid design bridges generative flexibility with explicit enforcement of MRI physics. Experiments on the fastMRI dataset demonstrate that our framework consistently outperforms recent state-of-the-art deep learning and diffusion-based methods in SSIM, PSNR, and LPIPS, with LPIPS capturing perceptual improvements more faithfully. These results demonstrate that integrating conditional supervision with iterative consistency updates yields substantial improvements in both pixel-level fidelity and perceptual realism, establishing a principled and practical advance toward robust, accelerated MRI reconstruction.

The demand for energy-efficient high-speed wireless communication, coupled with the rapid rise of IoT devices, requires systems that integrate power harvesting with optical data reception to eliminate the need for charging or battery replacements. Recent advances have explored the use of solar cells as optical receivers for high-speed data detection alongside power harvesting. \acs{GaAs}-based \acp{PPC} provide six times greater electron mobility than silicon- or cadmium telluride-based cells, enabling faster data detection and improved power efficiency. However, their bandwidth is constrained by junction capacitance, which increases with active area, creating a trade-off between power output and data rate. To address this, we propose and test multi-segment \acs{GaAs}-based \Acp{PPC} that serve as both energy harvesters and data detectors. By segmenting the active area into 2, 4, or 6 subcells, forming circular areas with diameters of 1, 1.5, or 2.08~mm, we reduce capacitance and boost bandwidth while preserving light collection. Fabricated on a semi-insulating \ac{GaAs} substrate with etched trenches for electrical isolation, the series-connected subcells optimize absorption and minimize parasitic effects. The \Acp{PPC} were used for an eye-safe 1.5~m optical wireless link, employing \ac{OFDM} with adaptive bit and power loading. The system achieved a world record data rate of 3.8~Gbps, which is four times higher than prior works. The system converts 39.7% of optical power from a beam of 2.3~mW, although the segmentation increases the sensitivity of the alignment. These findings provide new solutions for off-grid backhaul for future communication networks, such as 6th generation (6G) cellular.

Modulations are a critical part of sound design and music production, enabling the creation of complex and evolving audio. Modern synthesizers provide envelopes, low frequency oscillators (LFOs), and more parameter automation tools that allow users to modulate the output with ease. However, determining the modulation signals used to create a sound is difficult, and existing sound-matching / parameter estimation systems are often uninterpretable black boxes or predict high-dimensional framewise parameter values without considering the shape, structure, and routing of the underlying modulation curves. We propose a neural sound-matching approach that leverages modulation extraction, constrained control signal parameterizations, and differentiable digital signal processing (DDSP) to discover the modulations present in a sound. We demonstrate the effectiveness of our approach on highly modulated synthetic and real audio samples, its applicability to different DDSP synth architectures, and investigate the trade-off it incurs between interpretability and sound-matching accuracy. We make our code and audio samples available and provide the trained DDSP synths in a VST plugin.

Machine Speech Chain, simulating the human perception-production loop, proves effective in jointly improving ASR and TTS. We propose TokenChain, a fully discrete speech chain coupling semantic-token ASR with a two-stage TTS: an autoregressive text-to-semantic model co-trained with ASR and a masked-generative semantic-to-acoustic model for synthesis only. End-to-end feedback across the text interface is enabled with straight-through argmax/Gumbel-Softmax and balanced with supervised ASR via dynamic weight averaging. Ablations examine optimal temperature schedules for in- and cross-domain transfer. Evaluation reveals TokenChain surpasses baseline accuracy 2-6 epochs earlier and yields 5-13% lower equal-epoch error with stable T2S on LibriSpeech, and reduces relative ASR WER by 56% and T2S WER by 31% on TED-LIUM with minimal forgetting, showing that chain learning remains effective with token interfaces and models.

Auto-regressive speech-text models pre-trained on interleaved text tokens and discretized speech tokens demonstrate strong speech understanding and generation, yet remain substantially less compute-efficient than text LLMs, partly due to the much longer sequences of speech tokens relative to text. This modality imbalance disproportionately allocates pre-training and inference compute to speech, potentially hindering effective cross-modal alignment and slowing performance scaling by orders of magnitude. We introduce the Latent Speech-Text Transformer (LST), which aggregates speech tokens into latent speech patches that serve as higher-level autoregressive units. This design aligns the sequence-modeling granularity between speech and text while improving computational efficiency. The resulting patches can align with textual units to facilitate cross-modal knowledge transfer and compactly capture recurring acoustic patterns such as silence. Across story-completion benchmarks under both compute-controlled and data-controlled settings, LST consistently improves speech accuracy while also improving text performance, achieving up to +6.5% absolute gain on speech HellaSwag in compute-controlled training (+5.3% in data-controlled training). Under compute-controlled scaling from 420M to 1.8B parameters in a near compute-optimal regime, gains grow with scale, and improvements persist up to 7B parameters under fixed-token budgets. These benefits extend to downstream tasks: LST stabilizes ASR adaptation and reduces the effective autoregressive sequence length during ASR and TTS inference, lowering computational cost without degrading reconstruction quality. The code is available at https://github.com/facebookresearch/lst.

Uncertainty quantification (UQ) over graphs arises in a number of safety-critical applications in network science. The Gaussian process (GP), as a classical Bayesian framework for UQ, has been developed to handle graph-structured data by devising topology-aware kernel functions. However, such GP-based approaches are limited not only by the prohibitive computational complexity, but also the strict modeling assumptions that might yield poor coverage, especially with labels arriving on the fly. To effect scalability, we devise a novel graph-aware parametric GP model by leveraging the random feature (RF)-based kernel approximation, which is amenable to efficient recursive Bayesian model updates. To further allow for adaptivity, an ensemble of graph-aware RF-based scalable GPs have been leveraged, with per-GP weight adapted to data arriving incrementally. To ensure valid coverage with robustness to model mis-specification, we wed the GP-based set predictors with the online conformal prediction framework, which post-processes the prediction sets using adaptive thresholds. Experimental results the proposed method yields improved coverage and efficient prediction sets over existing baselines by adaptively ensembling the GP models and setting the key threshold parameters in CP.

Differentiable model predictive control (MPC) offers a powerful framework for combining learning and control. However, its adoption has been limited by the inherently sequential nature of traditional optimization algorithms, which are challenging to parallelize on modern computing hardware like GPUs. In this work, we tackle this bottleneck by introducing a GPU-accelerated differentiable optimization tool for MPC. This solver leverages sequential quadratic programming and a custom preconditioned conjugate gradient (PCG) routine with tridiagonal preconditioning to exploit the problem's structure and enable efficient parallelization. We demonstrate substantial speedups over CPU- and GPU-based baselines, significantly improving upon state-of-the-art training times on benchmark reinforcement learning and imitation learning tasks. Finally, we showcase the method on the challenging task of reinforcement learning for driving at the limits of handling, where it enables robust drifting of a Toyota Supra through water puddles.

To analyze signals with rapid frequency variations or transient components, the time-reassigned synchrosqueezing transform (TSST) and its variants have been recently proposed. Unlike the traditional synchrosqueezing transform, TSST squeezes the time-frequency (TF) coefficients along the group delay (GD) trajectories rather than the instantaneous frequency trajectories. Although TSST methods perform well in analyzing transient signals, they are fundamentally limited in processing multicomponent signals with intersecting GD curves. This limitation compromises the accuracy of both feature extraction and signal component recovery, thereby significantly reducing the interpretability of time-frequency representations (TFRs). This is particularly problematic in broadband signal processing systems, where the linearity of the phase response is critical and precise measurement of group delay dispersion (GDD) is essential. Motivated by the superior capability of frequency-domain signal modeling in characterizing rapidly frequency-varying signals, this paper proposes a novel three-dimensional time-frequency-group delay dispersion (TF-GDD) representation based on the frequency-domain chirplet transform. A subsequent time-reassigned synchrosqueezing frequency-domain chirplet transform (TSFCT) is introduced to achieve a sharper TF-GDD distribution and more accurate GD estimation. For mode retrieval, a novel frequency-domain group signal separation operation (FGSSO) is proposed.The theoretical contributions include a derivation of the approximation error for the GD and GDD reference functions and an establishment of the error bounds for FGSSO-based mode retrieval. Experimental results demonstrate that the proposed TSFCT and FGSSO effectively estimate GDs and retrieve modes–even for modes with intersecting GD trajectories.

Smartphone-based iris recognition in the visible spectrum (VIS) remains difficult due to illumination variability, pigmentation differences, and the absence of standardized capture controls. This work presents a compact end-to-end pipeline that enforces ISO/IEC 29794-6 quality compliance at acquisition and demonstrates that accurate VIS iris recognition is feasible on commodity devices. Using a custom Android application performing real-time framing, sharpness evaluation, and feedback, we introduce the CUVIRIS dataset of 752 compliant images from 47 subjects. A lightweight MobileNetV3-based multi-task segmentation network (LightIrisNet) is developed for efficient on-device processing, and a transformer matcher (IrisFormer) is adapted to the VIS domain. Under a standardized protocol and comparative benchmarking against prior CNN baselines, OSIRIS attains a TAR of 97.9% at FAR=0.01 (EER=0.76%), while IrisFormer, trained only on UBIRIS.v2, achieves an EER of 0.057% on CUVIRIS. The acquisition app, trained models, and a public subset of the dataset are released to support reproducibility. These results confirm that standardized capture and VIS-adapted lightweight models enable accurate and practical iris recognition on smartphones.

Feature attributions are post-training analysis methods that assess how various input features of a machine learning model contribute to an output prediction. Their interpretation is straightforward when features act independently, but it becomes less clear when the predictive model involves interactions, such as multiplicative relationships or joint feature contributions. In this work, we propose a general theory of higher-order feature attribution, which we develop on the foundation of Integrated Gradients (IG). This work extends existing frameworks in the literature on explainable AI. When using IG as the method of feature attribution, we discover natural connections to statistics and topological signal processing. We provide several theoretical results that establish the theory, and we validate our theory on a few examples.

Mixtures of linear dynamical systems (MoLDS) provide a path to model time-series data that exhibit diverse temporal dynamics across trajectories. However, its application remains challenging in complex and noisy settings, limiting its effectiveness for neural data analysis. Tensor-based moment methods can provide global identifiability guarantees for MoLDS, but their performance degrades under noise and complexity. Commonly used expectation-maximization (EM) methods offer flexibility in fitting latent models but are highly sensitive to initialization and prone to poor local minima. Here, we propose a tensor-based method that provides identifiability guarantees for learning MoLDS, which is followed by EM updates to combine the strengths of both approaches. The novelty in our approach lies in the construction of moment tensors using the input-output data to recover globally consistent estimates of mixture weights and system parameters. These estimates can then be refined through a Kalman EM algorithm, with closed-form updates for all LDS parameters. We validate our framework on synthetic benchmarks and real-world datasets. On synthetic data, the proposed Tensor-EM method achieves more reliable recovery and improved robustness compared to either pure tensor or randomly initialized EM methods. We then analyze neural recordings from the primate somatosensory cortex while a non-human primate performs reaches in different directions. Our method successfully models and clusters different conditions as separate subsystems, consistent with supervised single-LDS fits for each condition. Finally, we apply this approach to another neural dataset where monkeys perform a sequential reaching task. These results demonstrate that MoLDS provides an effective framework for modeling complex neural data, and that Tensor-EM is a reliable approach to MoLDS learning for these applications.

The problem of regulation of the orientation angle of a remotely controlled differential-drive mobile robot with actuator dynamics and network-induced delays is studied. Using a preinstalled two-layer nonlinear control scheme that decouples linear and angular velocities and regulates heading, a third, delay-dependent layer that achieves exact model matching from the orientation angle command to the orientation angle is introduced. The proposed outer loop controller is a delay dependent dynamic measurable output-feedback controller with dynamic proper precompensator. Parameterization yields a simple characteristic quasi-polynomial with coefficients constrained to satisfy stability for all delays up to a computable bound. Computational experiments confirm accurate tracking, fast settling and bounded internal signals and control voltages. The approach offers an analytic design alternative to AI-based tuning for delayed robotic systems.

Stochastic processing networks (SPNs) have broad applications in healthcare, transportation, and communication networks. The control of SPN is to dynamically assign servers in batches under uncertainty to optimize long-run performance. This problem is challenging as the policy dimension grows exponentially with the number of servers, making standard reinforcement learning and policy optimization methods intractable at scale. We propose an atomic action decomposition framework that addresses this scalability challenge by breaking joint assignments into sequential single-server assignments. This yields policies with constant dimension, independent of the number of servers. We study two classes of atomic policies, the step-dependent and step-independent atomic policies, and prove that both achieve the same optimal long-run average reward as the original joint policies. These results establish that computing the optimal SPN control can be made scalable without loss of optimality using the atomic framework. Our results offer theoretical justification for the strong empirical success of the atomic framework in large-scale applications reported in previous articles.

The comparative evaluation between classical and quantum reinforcement learning (QRL) paradigms was conducted to investigate their convergence behavior, robustness under observational noise, and computational efficiency in a benchmark control environment. The study employed a multilayer perceptron (MLP) agent as a classical baseline and a parameterized variational quantum circuit (VQC) as a quantum counterpart, both trained on the CartPole-v1 environment over 500 episodes. Empirical results demonstrated that the classical MLP achieved near-optimal policy convergence with a mean return of 498.7 +/- 3.2, maintaining stable equilibrium throughout training. In contrast, the VQC exhibited limited learning capability, with an average return of 14.6 +/- 4.8, primarily constrained by circuit depth and qubit connectivity. Noise robustness analysis further revealed that the MLP policy deteriorated gracefully under Gaussian perturbations, while the VQC displayed higher sensitivity at equivalent noise levels. Despite the lower asymptotic performance, the VQC exhibited significantly lower parameter count and marginally increased training time, highlighting its potential scalability for low-resource quantum processors. The results suggest that while classical neural policies remain dominant in current control benchmarks, quantum-enhanced architectures could offer promising efficiency advantages once hardware noise and expressivity limitations are mitigated.

Diffusion models have demonstrated remarkable performance in speech synthesis, but typically require multi-step sampling, resulting in low inference efficiency. Recent studies address this issue by distilling diffusion models into consistency models, enabling efficient one-step generation. However, these approaches introduce additional training costs and rely heavily on the performance of pre-trained teacher models. In this paper, we propose ECTSpeech, a simple and effective one-step speech synthesis framework that, for the first time, incorporates the Easy Consistency Tuning (ECT) strategy into speech synthesis. By progressively tightening consistency constraints on a pre-trained diffusion model, ECTSpeech achieves high-quality one-step generation while significantly reducing training complexity. In addition, we design a multi-scale gate module (MSGate) to enhance the denoiser's ability to fuse features at different scales. Experimental results on the LJSpeech dataset demonstrate that ECTSpeech achieves audio quality comparable to state-of-the-art methods under single-step sampling, while substantially reducing the model's training cost and complexity.