Papers

Orthogonal frequency division multiplexing (OFDM) is a key waveform for integrated sensing and communication (ISAC) due to its spectral efficiency and compatibility with modern wireless standards. In multi-target and clutter-rich environments, however, payload-based OFDM-ISAC can suffer from data-dependent sidelobes induced by non-constant-modulus modulation symbols. To overcome these limitations, this paper proposes a region-of-interest mismatched filter (ROI-MMF) that suppresses sidelobes within a prescribed delay region while preserving the mainlobe response. By leveraging the Woodbury identity, the proposed design admits an efficient closed-form implementation whose complexity scales with the ROI size rather than the number of subcarriers. We theoretically provide the ranging mean-square error (MSE) of the designed ROI-MMF, which shows the superior performance compared to conventional matched filtering (MF) and reciprocal filtering (RF) sensing receivers. Simulations across various constellations show that the proposed sensing receiver achieves a ranging MSE approaching the Cramér-Rao bound (CRB), which notably confirms that our design preserves the target ranging performance even under the non-constant-modulus constellation. Finally, the framework is experimentally validated with our over-the-air OFDM-ISAC testbed.

At very low bitrates, image compression discards fine textures and local structures, while distortion-oriented reconstruction often produces over-smoothed images. Generative codecs synthesize missing details, but existing codebook-based controllable designs generally rely on single-codebook reconstruction priors. We propose Adaptive Fused Prior Transfer for Controllable Generative Image Compression (AFP-GIC), which transfers an image-adaptive fused prior from a frozen pretrained AdaCode model. Encoder-side prior features guide latent formation, while the decoder predicts a compatible fused prior from the compressed representation and control variables, without transmitting the prior itself. A motivating analysis shows that better decoder-side prior alignment tightens a reconstruction-error upper bound and that the fused-prior family includes single-codebook choices as special cases. A single pretrained model supports five evaluated bitrate operating points. Under the unified benchmark, AFP-GIC achieves 18.1% lower decoder latency and uses 31.10 million (20.5%) fewer inference parameters than DC-VIC. Experiments on Kodak, CLIC2020, and DIV2K show competitive PSNR and SSIM, with the clearest naturalness gains in NIQE scores and very-low-bitrate visual comparisons. Code: https://github.com/yifeipet/AFP_GIC.

Evaluating resilience in electric distribution systems under severe weather requires models that can connect network topology, hazard simulation, fragility modeling, restoration assumptions, repair strategy, and downstream consequences. This paper extends our prior graph-based resilience evaluation framework for power distribution systems in three ways: it adds analysis conditioned on historical events with real outage and weather data, introduces sensitivity studies for key modeling assumptions, and includes a coupled power-flooding extension for sewage-backup assessment. Historical wind events drive Monte Carlo simulations conditioned on real weather, and the observed outage trajectories are treated as realized historical samples for comparison. Wind-event resilience metrics stabilize at approximately 256 episodes, and outage peak, duration, and outage intensity change systematically with fragility parameters, network topology, restoration assumptions, and repair strategies. In a separate 1000-episode joint power-flooding simulation, episodes with at least one flooded customer occur in 1.9% of episodes overall, and both flood occurrence and flood intensity increase with outage intensity, showing a selective power-to-flood consequence pathway. Overall, the framework provides a practical basis for resilience assessment, comparative scenario analysis, and coupled power-flooding studies in a limited public-data setting, while also suggesting that more detailed utility data could further improve simulation realism.

As connected and autonomous driving technologies advance, vehicles increasingly rely on data from external sensors. Although this information can enhance state estimation, processing all available streams imposes significant communication and computational costs. To address this challenge, we introduce a Sensor Management Center (SMC) that selects a low-cost subset of external sensors in real time while satisfying chance-constrained error bounds derived from an Extended Kalman Filter (EKF) covariance. We formulate the selection problem as a multidimensional minimum knapsack problem and adopt a deficiency-weighted greedy algorithm as an approximate yet efficient solution. The proposed approach is validated through MATLAB simulations and experiments on a 1:15-scale cooperative driving testbed.

Coincident Peak (CP) pricing is widely used in U.S. electricity markets to allocate capacity and transmission costs. This paper develops a behavioral game-theoretic framework for CP-driven load shifting that couples a nonlinear cost-allocation model with day-ahead (one-shot) and real-time (sequential-learning) decision processes. We examine two update rules, namely best-response dynamics (BRD) and fictitious-play dynamics (FPD), across continuous and finite action spaces to quantify how flexibility, action resolution, and participation influence peak outcomes. Using ERCOT peak-day data, we find that FPD reliably reduces system peaks, whereas BRD is more variable and can increase peaks under tight-capacity conditions. Finer action resolution improves peak shaving, while the number of participants is largely neutral when aggregate flexibility is fixed. Meanwhile, information-provider signals can induce herding, whereas response-aware or diverse signals improve peak shaving. These results highlight both the potential and limits of CP pricing: smoothing information and enabling granular control are as important as the amount of available flexibility. The framework offers practical guidance for system operators and consumers: For ISOs, broadcasting smoothed CP signals and setting minimum controllable-capacity thresholds enhance coordination. For consumers, greater flexibility and finer control resolution improve both cost savings and peak-shaving performance.

Ocean exploration places high demands on autonomous underwater vehicles, especially when there's observation delay. We propose age of information optimized Markov decision process (AoI-MDP) to enhance underwater tasks by modeling observation delay as signal delay and including it in the state space. AoI-MDP also introduces wait time in the action space and integrates AoI with reward functions, optimizing information freshness and decision-making using reinforcement learning. Simulations show AoI-MDP outperforms the standard MDP, demonstrating superior performance, feasibility, and generalization in underwater tasks. To accelerate relevant research, we have made the codes available as open-source at https://github.com/Xiboxtg/AoI-MDP.

Semantic segmentation of multi-source remote sensing images is a fundamental task for Earth observation applications. Existing methods often struggle with insufficient multi-scale context modeling and suboptimal cross-modal feature fusion, limiting their performance in complex high-resolution scenes. To this end, we propose Axial-Relation Guided Fusion Mamba (ARG-Mamba), a state space model-based framework for optical-elevation remote sensing image segmentation. Specifically, we introduce a Multi-Scale State Space Module to capture both fine-grained local details and global contextual dependencies with linear computational complexity. Moreover, an Axial-Relation Guided Fusion Module is designed to explicitly model global cross-modal correlations along horizontal and vertical axes, enabling efficient feature fusion between optical and elevation modalities. Extensive experiments conducted on the ISPRS Vaihingen and Potsdam datasets demonstrate that our ARG-Mamba consistently outperforms state-of-the-art methods while maintaining favorable computational efficiency. The code will be made publicly available at \url{https://github.com/oucailab/ARG-Mamba}.

Vehicle-to-grid (V2G) technology empowers electric vehicles (EVs) to act as mobile energy resources, providing critical support to power systems, especially under stressed conditions. To understand the economic mechanism driving V2G participation and its benefits to power grid, this paper proposes a multi-player coupled equilibrium framework that models the bidirectional interactions between power grid operations and EV routing, incorporating charging and discharging choice in a preprocessed feasible path generation procedure. Energy prices are endogenously determined by market clearance conditions. We formulate the overall problem as a Variational Inequality that unite the decision-making of Distribution System Operator, Charging Network Operator, Load Serving Entities, and EV drivers. Numerical studies validate the framework under two stress scenarios: increased household load and power line outages. Results show that when EVs are incentivized by reduced generalized path costs, V2G is particularly effective in eliminating load shedding and reducing distribution locational marginal electricity prices. On the transportation side, V2G can lead to divergence in EV behavior between normal and scarcity conditions, and alter route choices yet improve overall trip economic.

Convolutional neural networks (CNNs) have been extensively and successfully applied to the task of synthetic aperture radar (SAR) image change detection. However, conventional convolutional layers are inherently limited by their local receptive fields, which mainly capture spatially localized patterns while neglecting the global context that is often crucial for accurately distinguishing subtle or large-scale changes in SAR imagery. To address these limitations, we propose a novel Global Dynamic Context-Aware Network (GDNet) specifically tailored for SAR image change detection. At the core of our approach lies a novel global dynamic convolution module, which adaptively modulates convolution kernel weights according to the global semantic information extracted from the input features. By dynamically incorporating long-range dependencies, this mechanism enables the network to integrate both local detail and global context, thus improving its ability to detect diverse change patterns. In addition, we introduce a carefully designed two-stage Mixup strategy for model training. Unlike conventional single-stage Mixup, our two-stage design generates more diverse and informative training samples, effectively regularizing the model and yielding more stable and reliable classification results even under limited data scenarios. Extensive experiments on three SAR datasets demonstrate the superiority of the proposed GDNet compared to other state-of-the-art methods. These findings highlight the potential of global dynamic modeling and advanced data augmentation strategies for advancing SAR image interpretation. Source codes are available at \url{https://github.com/oucailab/GDNet}.

Learning-based dynamical models face a persistent tension between expressiveness and formal guarantees: richer model classes improve predictive accuracy, but their stability properties are typically verified only empirically, if at all. This paper proposes Stable Fiber-Koopman Residual Dynamics (SFKD), a unified framework that simultaneously addresses environment-aware geometric consistency, latent-space stability certification, and bounded residual perturbation propagation. Concretely, SFKD constructs a fiber bundle latent manifold whose fibers encode environment-specific dynamics; an environment-conditioned Koopman operator governs the dominant linear evolution on each fiber; and a contraction-constrained residual neural network captures unmodeled nonlinear effects while admitting an explicit input-to-state stability (ISS) certificate. The resulting model is embedded in a sampling-based MPPI controller for autonomous vehicle path tracking under variable surface conditions and wind disturbances. Theoretical analysis establishes ISS of the latent dynamics and a finite ultimate bound on tracking error. Numerical experiments against five baselines – Koopman MPC, Neural ODE, ICODE, ControlSynth, and ICODE-MPPI – demonstrate a 31% reduction in tracking RMSE, a 44% improvement in control smoothness, and near-zero latent stability violation rate across environment-switching scenarios.

Coded computing is a distributed paradigm that uses coding theory to introduce redundancy and overcome bottlenecks in large-scale systems. In the same vein, randomized numerical linear algebra employs probabilistic methods to compress and accelerate linear algebraic operations, addressing challenges in high-dimensional data analysis. This article reviews the foundations of both fields and presents distributed schemes that combine techniques from both to speed up optimization and machine learning algorithms, in the presence of slow or non-responsive servers. Along the way, we touch on various related topics and mathematical concepts.

The rapid advancement of Vehicle-to-Everything (V2X) communications and Tele-Operated Driving (ToD) demands ultra-low-latency, 8K60 video telemetry. However, deploying modern hardware at the vehicular edge is frequently hindered by supply chain constraints, high power budgets, and growing e-waste concerns. This paper investigates a highly sustainable alternative: repurposing legacy NVIDIA Pascal GPUs for real-time 8K HEVC edge encoding. We demonstrate that triggering 2-Way Split Frame Encoding (SFE) on dual-NVENC GP104 and GP102 silicon successfully unlocks real-time 8K60 throughput with a negligible Rate-Distortion penalty of under 1%. Crucially, our micro-architectural analysis reveals that smaller GPU dies significantly outperform larger flagship models in both raw throughput and energy efficiency. Because fixed-function encoding forces general-purpose Streaming Multiprocessor (SM) cores to sustain maximum frequencies while remaining idle, GPUs with fewer CUDA cores waste drastically less power. While benchmarking against the state-of-the-art RTX PRO 6000 Blackwell highlights a generational compression efficiency gap, Pascal's functional HEVC architecture and native lack of B-frames align perfectly with ultra-low-latency V2X pipelines. Ultimately, repurposed mid-range Pascal GPUs present a highly capable, cost-effective, and e-waste mitigating solution for modern Intelligent Transportation Systems.

AI-native 6G visions increasingly invoke wireless foundation models, large multimodal models, and wireless world models as the natural endpoint of AI-native networking, drawing an analogy to recent developments in large language models (LLMs). We argue that this analogy is structurally incomplete. The success of LLMs is based on a broad, reusable, and largely self-contained tokenized data substrate, whereas the wireless domain lacks an equivalent data foundation. Unlike text, code, or images, wireless data such as CSI tensors, IQ samples, or scheduler logs are not self-contained: their meaning is configuration-dependent, simulator-conditioned, task-disaggregated, and weakly grounded in operational feedback, all structural bottlenecks that undermine current pre- and post-training recipes. We therefore argue that monolithic models, including mixture-of-experts (MoE) and wireless world models, are not the most realistic near-term path toward deployable AI-native networks. Instead, emerging evidence points toward composable and agentic network architectures, where general reasoning models orchestrate specialized signal processing models, classical algorithms, digital twins, standards-aware retrieval, and safety checks through explicit programmable interfaces.

Fast charging of lithium-ion batteries is limited by lithium plating, which occurs when the anode potential drops below 0 V vs Li/Li+. Model-based control aims to maximize charging current while maintaining anode potentials above this threshold. In this work, a plating-free fast charging strategy is demonstrated using a Homogenized Model (HM) coupled with a classical PID controller. The HM, derived from homogenization theory applied to the Poisson-Nernst-Planck equations, retains the physics of the Doyle-Fuller-Newman model while capturing electrode microstructural heterogeneity in a one-dimensional double-continua formulation. By reconstructing three-dimensional distributions of electrochemical variables from precomputed closure variables, the HM enables non-invasive estimation of heterogeneous anode potentials, acting as a virtual sensor. Through MATLAB-COMSOL co-simulation, a PID controller regulates current to maintain the full 3D anode potential distribution above the plating limit, achieving model-based fast charging at a fraction of the computational cost of high-fidelity models. The results demonstrate the potential of HM-based control for safe, degradation-aware, and efficient fast charging of lithium-ion batteries.

Audio super-resolution (SR), also referred to as bandwidth extension (BWE), aims to reconstruct high-fidelity signals from low-resolution (LR) or band-limited (BL) observations, an inherently ill-posed task due to the ambiguity of missing high-frequency (HF) content. This survey provides a comprehensive overview of the field, with a particular focus on the paradigm shift from discriminative mapping to modern generative modeling. We first review early discriminative deep neural network (DNN) models, which formulate BWE/SR as a deterministic mapping problem and are prone to regression-to-the-mean effects and spectral over-smoothing. We then systematically review generative approaches, including autoregressive (AR) models, variational autoencoders (VAEs), generative adversarial networks (GANs), diffusion and score-based models, flow-based methods, and Schrödinger bridges. Across these approaches, we examine key design aspects, including representation domain, architecture, conditioning mechanisms, and trade-offs among reconstruction fidelity, perceptual quality, robustness, and computational efficiency. We further conduct unified experiments on representative discriminative and generative methods to provide controlled empirical evidence for these trade-offs. Furthermore, we discuss emerging directions involving large language models (LLMs) and multimodal foundation models, and highlight open challenges in perceptual evaluation, practical deployment, and real-world generalization. By providing a structured taxonomy and unified perspective, this survey establishes a comprehensive foundation and offers a practical roadmap for advancing BWE/SR from deterministic point estimation toward distribution-aware generative modeling.

Quantum key distribution (QKD) provides information-theoretic security and satellite-based quantum key distribution (SatQKD) has demonstrated the potential to extend this communication security to intercontinental scales. However, atmospheric turbulence induces significant distortion in the spatial distribution of received optical beams, while background noise remains approximately uniform across the detector plane. As a result, single-element qubit (quantum bit) detection can be frequently dominated by noise due to the random spatial pattern of the imaged wavefront, thereby degrading the system performance. To address this limitation, we propose to exploit the spatial degrees of freedom of single-photon detector arrays to reject the excessive noise while adapting to channel variations induced by turbulence. We develop a threshold-based selection method that only activates detector elements that have higher probability of registering qubits. We evaluate the performance of the proposed noise-rejection QKD schemes using Monte Carlo simulations considering the impact of diffraction and atmospheric turbulence on the transmitted optical beam in the presence of background and dark noise. The results show that, compared to conventional schemes, the proposed noise-rejection strategy effectively reduces the quantum bit error rate (QBER) and improves the secret key rate (SKR) performance, while the performance gains depend on the turbulence condition. These findings demonstrate the potential of adaptive array receiver design to enhance the robustness of the SatQKD system under realistic atmospheric conditions.

This paper presents a novel data-driven framework for the robust safety verification and safe control synthesis of unknown monotone discrete-time systems. While existing data-driven safety analysis approaches are often either heuristic in nature or require large amounts of data to provide rigorous guarantees, we leverage the structural property of monotonicity to significantly reduce data requirements while still ensuring formal safety guarantees. Our approach is built upon a new class of certificates called dominance functions, constructed directly from collected system trajectories, which themselves need not be safe. By exploiting the monotone structure of the dynamics, we show that dominance functions are (i) dissipative, meaning that they decrease monotonically along system trajectories, and (ii) sufficiently \expressive to characterize safety certificates for monotone systems. Together, these properties establish dominance functions as principled building blocks for the systematic construction of formal safety certificates directly from trajectory data. For both robust safety verification and safe control synthesis, we develop an efficient sampling-based optimization framework that searches for safety certificates represented as linear combinations of dominance functions constructed from collected trajectories. We validate our data-driven framework on two monotone systems by successfully deriving safety certificates from a small number of trajectories.

A central obstacle in nonlinear Bayesian filtering is representing the belief distribution. Moment-based filters address this by propagating polynomial moments and reconstructing a density from them. Recent work completes the predict-update loop via the maximum-entropy (MaxEnt) principle, but each step requires the partition function and its gradient, both $n$-dimensional integrals whose cost scales exponentially, restricting the demonstrated MaxEnt moment filtering to $n \le 4$. We avoid the partition function entirely by combining score matching with Stein's identity. In our setting, score matching reduces the density fit to a single linear solve whose coefficients are assembled directly from the propagated moments. The same parameters then drive Stein's identity to close the moment hierarchy during prediction and to recover posterior moments after each Bayesian update, keeping the full predict-update loop free of partition function evaluation. The resulting Score Kalman Filter (SKF) reduces to the classical information-form Kalman filter as a special case and performs every step through linear algebra. On nonlinear coupled-oscillator networks, the SKF runs through $n=20$ and reports lower RMSE than the EKF, UKF, EnKF, and particle-filter baselines on the tested synthetic benchmarks.

Electrified powertrains rely heavily on magnetics for power conversion, where cost, volume, and weight concerns make integrated multi-use designs an attractive solution. With EV powertrain architectures requiring a boost stage being a major market segment, the proposed Coupled Inductor-Based Multi-Port DC-DC Converter (CI-MPC) leverages the existing magnetic framework of a conventional topology to realize independent, isolated, and simultaneously regulated converters without additional magnetic cores or cascaded stages. Unlike existing architectures that use secondary windings solely for voltage gain or passive rectification, the proposed topology integrates an actively controlled full bridge on the secondary side to create a distinct, independently regulated auxiliary converter. Primary output regulation is achieved via duty-cycle control, while the auxiliary converter employs phase-shift modulation synchronized with the primary switching to enable active rectification and flexible voltage or current regulation. A unified control framework ensures decoupled operation with minimal interaction between the primary and auxiliary loops, while also avoiding high step-down conversion ratios from high voltages to lower auxiliary levels. The operating principles and coordinated control strategies are validated through simulation and experimental results on a hardware prototype, demonstrating enhanced controllability, decoupled regulation, and a scalable pathway toward generalized multi-port power conversion within a unified magnetic framework.

Fluid reconfigurable intelligent surfaces (FRISs) have recently emerged as a promising paradigm for wireless communications, wherein the reflecting elements can dynamically select their effective radiating positions from a dense preset grid, thereby introducing an additional degree of freedom. In contrast to conventional RIS architectures, FRISs can achieve spatial diversity with fewer physical elements. However, beyond the cascaded channel structure, FRIS-assisted systems are also affected by uncertainties arising from element-position mismatches caused by calibration inaccuracies or motion errors, which may degrade channel state information. To the best of our knowledge, channel estimation (CE) for FRIS-assisted systems under position uncertainty remains unexplored. To fill this gap, we propose a CE framework for a multi-user FRIS-assisted uplink system based on a two-time-scale FRIS configuration protocol that captures both reflection phase-shift and element-motion dynamics. By capitalizing on orthogonal pilot sequences and tensor modeling, we derive a closed-form solution that jointly estimates the individual channels and the motion-induced phase coefficients. Numerical results demonstrate notable performance in the presence of unknown position deviations.

Safety-critical autonomy in unstructured environments poses significant challenges for online safety certification under evolving constraints. We propose Policy Library Control Barrier Function~(PL-CBF), a runtime safety filter that evaluates a library of fallback policies via parallel finite-horizon rollouts, selects the least invasive safe mode, and enforces safety by solving a quadratic program that minimally modifies a nominal policy. We provide a theoretical analysis based on a finite-horizon language metric over closed-loop behaviors, characterizing policy-library coverage requirements for certifying finite-horizon safety. Simulations on a planar double-integrator (4 states), highway driving with abrupt friction changes using a realistic nonlinear vehicle model (8 states), and 3D quadrotor navigation in crowded dynamic environments (12 states) demonstrate improved safety coverage over single-policy safety filters while retaining millisecond-level runtime.

Shear-horizontal surface acoustic wave (SH-SAW) filters have shown strong potential for low-loss, compact, GHz-frequency RF front ends. In this work, we demonstrate a high-performance SH-SAW filter design at 4.35 GHz utilizing 42{\deg}Y-cut thin-film lithium tantalate (LiTaO3) on a SiO2/Si platform. Despite the limitations of thin aluminum metallization and its associated ohmic losses, we show that implementing a Bartlett window apodization technique, primarily intended for in-band spurious-mode suppression, yields a significantly improved quality factor (Q) of 1,522 from 688 in conventional interdigitated SH-SAW resonators. This enhancement enables a third-order ladder filter at 4.3 GHz with an insertion loss of 1.59 dB, compared with 1.65 dB for a conventional SH-SAW filter. In addition, our filter with apodized resonator designs achieves a 3 dB fractional bandwidth (FBW) of 3.24% and out-of-band rejection exceeding 14 dB, all within a compact footprint of 0.4 mm2. These results suggest that apodized thin-film LiTaO3 designs are highly promising for low-loss, miniaturized, cost-effective radio frequency acoustic solutions in next-generation communication and sensing applications.

This paper focuses on learning efficient sensor allocations that ensure observability of unknown high-dimensional linear systems using only a small number of sensors. Existing methods either require an impractically large number of sensors or assume access to an observable allocation in advance. We propose a two-stage framework that overcomes these limitations: first, a novel system identification algorithm integrates information from multiple trajectories, each observing different subsets of state coordinates; then, a classic sensor allocation method is adapted to operate on the learned system parameters. Our non-asymptotic guarantees show that the proposed approach learns a sensor allocation with a near-optimal number of sensors when sensors can be allocated on any state coordinate. We further extend the results to settings with inaccessible state coordinates that are unavailable for sensor allocation.

Conventional techniques for compression and encryption are frequently laborious and resource-intensive, rendering them inappropriate for real-time applications. A plethora of research has been presented in the current literature to address these difficulties together; yet, it fails to propose any suitable strategy. Therefore, this study introduces an innovative simultaneous data compression and encryption (SDCE) system specifically designed for large video files. The methodology amalgamates chaotic map-based encryption with Huffman encoding for lossless compression into a cohesive framework, markedly diminishing computational overhead and processing duration while augmenting data security. The logistic map is utilized to produce a pseudo-random chaotic sequence for XOR-based encryption, guaranteeing robust security against unwanted access. The research findings demonstrate its efficacy in enhancing data privacy compared to other existing and related strategies, particularly in terms of generating greater entropy and avalanche effects. It produces superior throughput, compression ratio, peak signal-to-noise ratio (PSNR), and reduced bits per rate (BPC), along with a smaller percentage of data loss, which further supports its ability to provide enhanced data integrity compared to other existing methods.

We present MedASR, an open-source 105M-parameter model engineered for high-accuracy medical dictation. Prioritizing a "small, fast, and accurate" design, MedASR addresses 3 core pillars (1) Data: overcoming clinical corpora scarcity and class imbalance; (2) Modeling: efficient long-form training; and (3) Inference: accurate transcription via a pseudo-streaming sliding-window approach. Our evaluation shows that MedASR achieves a 58% relative WER reduction on Eye Gaze compared to Whisper Large-v3. By open-sourcing MedASR, we provide a transparent, high-performance backbone for specialized health-care applications, breaking down the barriers to clinical documentation often obscured by proprietary systems.

In adversarial settings, a mobile agent may strategically plan its motion to influence an opponent's inference about its intended goal. We study deceptive path planning in a scenario where a mobile agent aims to reach a privately selected goal while an adversarial observer allocates limited defensive resources based on the observed trajectory. Unlike classical path-planning and goal-recognition approaches that model observers as passive inference process, our game-theoretic formulation models them as strategic decision-makers. For the resulting dynamic asymmetric-information game, we develop an efficient solution method that combines a linear programming formulation with the Double Oracle algorithm. To evaluate performance, we introduce metrics that quantify both the risk and the effectiveness of deception and provide illustrative numerical examples.

Accurate polyp segmentation in colonoscopy is essential for early colorectal cancer detection, yet real-world clinical environments pose persistent challenges such as motion blur, specular reflections, and illumination instability. Most existing methods are optimized on clean benchmark images and suffer noticeable performance degradation when deployed in authentic surgical scenarios. We propose DepthPolyp, a lightweight and robust segmentation framework based on pseudo-depth-guided multi-task learning and efficient feature modulation. The architecture combines hierarchical Ghost factorization for compact feature generation, Interleaved Shuffle Fusion for low-cost cross-scale interaction, and Dynamic Group Gating for adaptive group-wise feature weighting. Extensive experiments demonstrate that DepthPolyp achieves strong cross-dataset generalization when trained on degraded data and evaluated on both clean and noisy target domains, consistently outperforming lightweight baselines and remaining competitive with substantially larger models. In real surgical video evaluation on PolypGen, DepthPolyp achieves better segmentation performance than models up to $20\times$ larger while preserving real-time inference speed. With only 3.57M parameters and 0.86 GMACs, the proposed method runs at over 180 FPS on mobile devices, making it well suited for real-time deployment in resource-constrained clinical environments. Code and pretrained weights are available at: https://github.com/ReaganWu/DepthPolyp/

Through-plane resolution in clinical MRI is typically much coarser than in-plane resolution, limiting diagnostic utility. This work investigates deep learning approaches to interpolate intermediate MRI slices in prostate imaging, effectively doubling through-plane resolution. I evaluated five architectures (CNN, U-Net, two GAN variants, and DDPM) and discovered that problem formulation has dramatically more impact than architectural complexity. By reformulating the interpolation task to use adjacent slices (i-1, i+1) rather than distant slices (i-2, i+2), I achieved a 58% improvement in SSIM performance across all deterministic architectures. The U-Net model achieved the best results with PSNR of 30.08 dB and SSIM of 0.898, representing a 10.1% improvement over linear interpolation baseline. A DDPM was also evaluated but showed poor reconstruction quality due to fundamental mismatch between stochastic generation and deterministic reconstruction requirements. These findings demonstrate that problem formulation can have 290x more impact than architectural sophistication in medical imaging tasks.

Rare diseases dominate the diagnostic challenge in medical imaging yet are severely underrepresented in clinical datasets, causing classifiers to fail on exactly the conditions where reliable detection matters most. Generative augmentation can supply the missing tail-class coverage, but coarse disease labels aggregate diverse subtypes and acquisition settings into multi-modal conditionals that bias generators toward dominant submodes, while a shared Gaussian source forces rare subpopulations through disproportionately long transport paths. We propose an offline strategy that introduces informative priors at two levels: first, we partition each coarse label into coherent submodes via Gaussian mixture modeling in the generative model's latent space; second, we learn subclass-conditioned source distributions that re-center and re-scale the starting distribution per submode, shortening trajectories and reducing within-subclass dispersion. To prevent degenerate solutions we impose explicit geometric control, moderately concentrating normalized displacement directions around learnable prototypes while capping path-length outliers. On long-tailed chest X-ray (MIMIC-LT, NIH-LT) and CT slice (CT-RATE) benchmarks the proposed method consistently improves tail-class generation fidelity and diversity (FID, IRS) and is a promising augmentation strategy that reliably improves downstream balanced accuracy and macro-F1 over a non-augmented baseline across modalities.

Generative models are capable to address difficult problems with non-unique solutions like bandwidth extension and gap filling, removing highly non-linear artifacts from codecs, clipping and distortion, as opposed to removing linear additive components like noise and reverb. While large offline processing models have shown impressive results, these tasks have not been solved with real-time capable models with low latency and compute. We propose a few-step flow matching model using Data Prediction Mean Flows in combination with suitable novel low-latency architecture to make flow matching models an attractive choice under theses constraints. Compared to state-of-the-art, our proposed mean flow model uses 120x less compute and introduces no algorithmic latency other than the STFT, while achieving similar audio quality.