Papers

Artificial intelligence-enabled radio access networks (AI-RANs) are envisioned to consist of multiple AI-based modules, potentially developed independently by different vendors. In this work, we study AI-RAN-enabled cell-free MIMO systems, with a particular focus on the system implications of modern AI models. Specifically, we focus on the phenomenon of test-time scalability popularized by large language models (LLMs), under which model performance improves as additional computational resources are allocated at testing time. By noting that the optimal amount of additional computational resources for each AI module should in general depend on its interaction with the other modules as well as with the underlying wireless channels, we propose a generic framework that enables optimal resource allocation for each test-time scalable module in cell-free MIMO systems. Experimental results demonstrate the effectiveness of the proposed framework in fully exploiting the potential of test-time scalable AI-RANs in cell-free MIMO systems.

Virtual contrast enhancement (VCE) synthesizes enhanced breast MR images from pre-contrast acquisitions. Modern latent generators offer strong image priors, but their bounded natural-image autoencoders conflict with the non-canonical intensity scale of MRI. We show that the upper bound can alter radiomic fidelity before generation, while scaling source and target independently creates a coordinate inconsistency. We propose Predictive Enhancement Calibration (PEC), which represents each pair in a shared, case-adaptive coordinate during training and predicts its unavailable upper endpoint from the pre-contrast image at inference. We integrate PEC with a pretrained FLUX latent flow transformer via parameter-efficient reference conditioning. Target round trips first isolate representation loss before generation; near-matched conditional models then compare PEC with fixed-wide and separate coordinates under comparable training budgets and backbone settings. On the fixed internal MAMA100 development cohort, PEC improves all eight point estimates in this source-only VCE setting, with paired evidence strongest for MSE and LPIPS.\noindentCode: https://github.com/tanlei0/pec-breast-mri-vce

Modern LLM-based ASR systems have established multilingual capability as a standard feature, leveraging large-scale multilingual corpora and LLMs' cross-lingual knowledge to achieve competitive performance across multilingual benchmarks. However, jointly modeling languages with heterogeneous acoustic, phonological, and lexical characteristics inevitably introduces optimization conflicts, undermining language-wise specialization. To address this challenge, we propose Language-Specialized Multi-Teacher On-Policy Distillation (LS-MOPD), which decouples language-specific knowledge acquisition from multilingual capability integration: language-specialized teachers are independently optimized via reinforcement learning (RL), with their expertise then integrated into a generalist multilingual student through language routing and token-level multi-teacher distillation, thereby reducing direct cross-lingual optimization conflicts. We further explore static and dynamic acoustic-prefix configurations to examine how teacher-student prefix consistency influences the efficacy of on-policy distillation. Experiments on benchmarks covering Mandarin, Mandarin subdialects, Cantonese, and English demonstrate that LS-MOPD substantially outperforms RL baselines and surpasses the empirical performance envelope defined by the best-performing RL teachers on nearly all benchmarks, revealing its potential to generalize beyond all teachers in multilingual ASR.

Autonomous robots are moving rapidly from research labs into everyday life - on roads, in the air, in warehouses, and in space. Robot autonomy is no longer solely an academic pursuit, but a collection of mature, field-tested methods and tools that practitioners rely on in real-world deployments. This book offers a clear, unified introduction to the methods that make this possible. Built on decades of teaching at Stanford, the text develops the core elements of modern autonomy stacks within a single conceptual framework, bridging classical robotics and modern physical AI. Every major topic is paired with hands-on Jupyter notebooks and implementation-driven exercises, so readers build practical intuition alongside theoretical understanding. The result is a principled, accessible, and deployment-aware foundation for anyone seeking to design, analyze, or contribute to the next generation of autonomous systems. This is a comprehensive resource for students, engineers, and researchers entering one of today's fastest-growing fields.

Infrared thermography provides a contact-free, restraint-free method to record surface temperatures. It serves as a valuable marker for thermoregulatory responses in laboratory animal stress and pharmacology research. However, the analysis of these images is currently bottlenecked by the manual delineation of anatomical regions. To date, no public dataset has provided paired radiometric thermal frames of rats with pixel-level body-part labels. We present a dataset of 1,655 quality-controlled radiometric thermal frames from 25 laboratory rats. Each frame is paired with a dense four-class anatomical segmentation mask (background, head, body, and tail) and the raw $480 \times 640$ temperature matrix (rows $\times$ columns) in degrees Celsius. This ensures every label is registered directly to the physical temperature it describes rather than a color-mapped rendering. The frames originate from two pharmacological cohorts where interventions alter thermoregulation in opposite directions: ethanol, which induces peripheral vasodilation, and ketamine, which affects central thermoregulation. This provides a wide and physiologically diverse range of surface temperature regimes. Aggregated across the dataset, the per-class temperatures follow a head~$>$~body~$>$~tail ordering in physical units. To demonstrate that the data support pixel-level segmentation directly from the radiometric channel, we present an exploratory U-Net segmentation pipeline that attains a subject-level cross-validated mean intersection-over-union of $0.895 \pm 0.006$. The dataset provides a reuse-ready benchmark for thermal semantic segmentation and for downstream physiological and stress-phenotyping analyses.

Audio-based piano transcription performs well on onset, pitch, and velocity, but the sustain pedal lets sound persist long after key release, so audio systems predict pedal-extended offsets rather than physical key release. Yet existing Visual Piano Transcription (VPT) systems focus on onset detection from short video windows, offset accuracy lags onset by a wide margin, and note-level velocity has not been reported. To address these gaps, we present V2N (Video to Notes), the first complete VPT system: a shared temporal backbone feeds task-specific heads for onset, offset, key hold, and velocity, jointly trained with per-frame supervision rather than only at the window center. Ablations show that multi-task supervision enables offset and velocity prediction while improving onset accuracy; longer temporal context yields further improvements. V2N sets new state-of-the-art results on PianoVAM and R3.

The development and testing of advanced aerial robots require experiments in controlled environments with tailored airflow profiles. This paper presents an online learning algorithm for controlling the complex airflow field in a multi-fan vertical wind tunnel. Our method combines a simplified physical model with iterative, measurement-based learning, enabling sample-efficient convergence to desired airflow distributions. We demonstrate the method's versatility by generating complex airflow, such as uniform, Gaussian, and parabolic profiles. Crucially, we show that our algorithm can produce an airflow profile specifically designed for passive soaring, greatly enhancing flight performance of a soaring robot. Variability, practical utility, and robustness of our approach are further highlighted by successful operation with a varying number of fans.

Future integrated sensing and communication (ISAC) architectures separate the sensing entity (SE) that acquires measurements from the sensing function (SF) that performs inference, creating a need for compact, task-oriented feedback on the SE-SF interface. Forwarding the raw channel frequency response or full per-link delay-Doppler-azimuth-elevation (DDAE) tensor is prohibitively expensive, while peak-only reporting discards target-discriminative structure under clutter. We propose a learning-based coarse-to-fine sensing pipeline with candidate-latent feedback for single-target estimation. At the SE, a lightweight convolutional scorer produces a dense delay-Doppler proposal map from pilot-based OFDM channel estimates, and a learned encoder constructs K compact C-dimensional candidate tokens by fusing per-candidate azimuth-elevation patches, normalized position, and confidence cues. The latents are uniformly quantized post-training to b bits and transmitted under a finite budget B_fb = bKC + 18K + 16 bits to the SF, which performs cross-candidate refinement, reranking, and joint four-parameter estimation. On a ray-traced urban scene with static and dynamic clutter, three operating points in the (K, C, b) design space achieve 96.33-98.88% detection at 107-806 bytes per coherent processing interval, compression ratios of 1.2-9.2 x 10^4 over the 8-bit DDAE magnitude tensor, reducing the SE-SF interface from multi-Gbit/s to sub-Mbit/s rates. Cross-scene evaluation on an independent campus-scale environment achieves 98.79-99.50% detection and at-or-better angular accuracy without retraining, indicating that the learned representation captures target-relevant structure that transports across scenes of comparable or lower clutter density.

We study cutting planes for nonconvex quadratically constrained quadratic programs (QCQPs) through a project-then-lift approach inspired by mixed-integer rounding (MIR) inequalities. Given two base valid inequalities for the extended QCQP formulation, we project the associated two-row relaxation into a two-dimensional set and analyze the joint range of quadratic functions in two base inequalities. For the nonconvex joint range, we give a closed-form convex hull description of the projected set; for the convex joint range, we give its semidefinite representation. This yields a new family of joint-range inequalities, which can be lifted back to the extended QCQP formulation. MIR inequalities can handle “mixed” terms: continuous variables or fractional linear combinations of integer variables. Similarly, we propose more flexible secant mixed-joint-range inequalities, which better expose and exploit the nonconvex joint range. The proposed approach preserves sparsity, since the support of each lifted inequality is controlled by that of the base inequalities. In preliminary geometric experiments, the joint-range inequalities yield substantial area reduction of the projected relaxation constructed via reformulation-linearization-technique.

The growing demand for mobile video streaming requires edge delivery systems that adapt efficiently to rapid network fluctuations and diverse user preferences. Existing approaches such as FlyCache rely on reactive ABR heuristics and loosely coupled cache policies, limiting their responsiveness and coordination under real-world wireless dynamics. We propose ProCAVE (Proactive Caching with Adaptive Video Experience), a self-adaptive DRL-based framework that unifies predictive bandwidth modeling, proactive bitrate selection, and preference-aware cache control. ProCAVE employs: (i) a lightweight Transformer for short-term throughput forecasting; (ii) a PPO-driven ABR agent; and (iii) a DDPG-based continuous cache controller operating on a high-dimensional global state. Experiments using MovieLens preference traces and Ghent 4G bandwidth measurements show that ProCAVE improves byte hit rate, reduces backhaul load, and enhances QoE compared with FlyCache and other baselines. These results highlight the benefits of predictive, DRL-coordinated control for efficient and user-centric edge video delivery.

Orthogonal time frequency space (OTFS) modulation has emerged as a promising solution to mitigate the severe Doppler shift in low Earth orbit (LEO) satellite communications. However, the frequency-dependent Doppler shift induced by the high mobility of LEO satellites leads to the Doppler squint effect (DSE). This effect compromises the channel sparsity in the delay-Doppler (DD) domain, rendering existing channel estimation methods ineffective. To overcome this challenge, this paper proposes a DSE-resilient transmission scheme for cyclic prefix OTFS (CP-OTFS)-based LEO satellite systems. Specifically, we analyze the input-output relationship of the CPOTFS- based LEO satellite communication system and derive a DSE-aware representation of the satellite-terrestrial channel in the DD domain. To efficiently capture DSE-aware channel characteristics, we propose a novel OTFS frame structure that allows the energy distribution of the received signal to serve as prior information for channel estimation. Meanwhile, this frame structure strategically allocates pilot symbols to achieve uniform energy distribution and reduce the peak-to-average power ratio (PAPR), while imposing a time-domain waveform continuity constraint to suppress out-of-band emission (OOBE) caused by rectangular pulses. Based on the frame structure, we propose a prior-aided iterative channel reconstruction (PAICR) algorithm to mitigate the severe power leakage induced by DSE. The proposed algorithm iteratively extracts and removes dominant channel components using Doppler-domain received signal energy observations, with a convergence criterion ensuring reliable termination. Furthermore, a Cramer-Rao lower bound is derived to provide a theoretical benchmark for evaluating the algorithm's performance.

This paper investigates energy efficiency (EE) maximization for the downlink of cell-free massive multiple-input multiple-output systems under quality-of-service and per-access point power constraints. We first derive closed-form gradient expressions of the objective function with respect to the power allocation coefficients, and then propose an accelerated projected gradient (APG) approach to solve this problem. To reduce the computational complexity and runtime of APG, we propose a deep-unfolded APG framework that maps iterative APG updates onto a finite number of neural network layers, where parameters such as step sizes and penalty coefficients are learned from data. The proposed approach produces power allocation solutions through a fixed number of gradient-based updates without the need for line search or manual parameter tuning. Numerical results show that the method achieves EE performance comparable to the iterative APG approach while requiring significantly lower computational cost, with up to a 30-fold reduction in floating-point operations under the considered system settings.

Local Flexibility Markets (LFMs) require Distribution System Operators (DSOs) to determine both the quantity of flexibility to procure and the corresponding willingness to pay during market clearing. Existing approaches typically rely on unrealistic centralized AC-OPF clearing algorithms or strictly localized, static flexibility requests driven primarily by congestion management, while the economic value of flexibility is largely neglected. This paper proposes a dynamic flexibility-request methodology in which the DSO's willingness to pay is embedded directly into the market-clearing objective by monetizing transformer and cable aging, network losses, and voltage congestion. To enable computationally efficient clearing, exact convex piecewise-linear epigraph reformulations of the IEEE C57.91 transformer aging model and an Arrhenius-based cable aging model are developed and formally proven to preserve exactness. The proposed framework is validated on a modified CIGRE MV benchmark and compared with a recent state-of-the-art flexibility-request methodology. The results demonstrate significantly higher market liquidity, more efficient flexibility procurement, and improved network operations while preserving the market's transparency and non-discrimination principles.

Reinforcement learning for flow-matching text-to-speech is complicated by deterministic ODE sampling: trajectory-level policy-gradient methods typically convert the ODE into an SDE and track per-step likelihood ratios, introducing stochastic perturbations and substantial overhead. We propose GROW, a group-relative advantage-weighted on-policy RL method that acts directly on the standard flow-matching objective. For each prompt, GROW samples a group of on-policy utterances, separately standardizes intelligibility and speaker-similarity rewards within the group, and combines them to reweight flow-matching regression. A Wasserstein-2 velocity penalty anchors the updated model to a frozen pretrained reference. A group-mean reward baseline is introduced to convert reward weighting into advantage weighting. For strong pretrained TTS models with concentrated rewards, positive exponential weighting is dominated by reward-agnostic self-imitation, whereas a zero-mean signed advantage preserves effective within-group credit assignment. Instantiated on DiTAR and evaluated on LibriSpeech and Seed-TTS EN/ZH, GROW reduces average WER from 2.016 to 1.558 and raises speaker similarity from 0.676 to 0.715 while keeping UTMOS. With 10-NFE training rollouts and 32-NFE evaluation, GROW retains comparable performance while training 2.9x faster than 32-NFE DiTAR-GRPO. We will open-source complete GROW codes, faithful DiTAR reproduction, and all model checkpoints.

Parameter-dependent linear matrix inequalities (PD-LMIs) require holding over a continuous domain. When the scheduling parameters vary with time, derivatives of parameter-dependent decisions may also enter the conditions. Since semidefinite programming solvers require finitely many constraints, we introduce GriD-LMIA, the Gridding-based Differentiable PD-LMI Assembler. It converts the conditions that need to hold on a continuous domain into finitely many sufficient LMIs in MATLAB. It first partitions the domain with a hyper-rectangular grid and represents known data and decisions on each cell with tensor Bernstein polynomials. The package exports direct Bernstein, Pólya-elevated, and sum-of-squares-based certificates through YALMIP. Examples are given to examine the balance among grid density, decision degree, and certificate choice.

We introduce an approach for derivation and smoothing of macroscopic densities and velocities from people trajectories, obtained from microscopic position data of individuals within a football stadium. We compute macroscopic densities specifically for susceptible, infected, and exposed individuals, via detection of exposed individuals based on the duration of critical contacts between susceptible and infected. We then present and numerically solve a crowd flow - epidemic spreading PDE model using a finite volume scheme. Finally, we calibrate the model using the smoothed densities computed.

Steelmaking process loads (SPLs) are flexible resources that enhance local renewable-energy utilization and reduce electricity procurement costs in industrial microgrids. However, strong multistage coupling makes current decisions affect subsequent feasibility, challenging conventional deep reinforcement learning to reduce costs while maintaining process feasibility throughout production. This paper proposes a process-knowledge-embedded safe deep reinforcement learning framework for the real-time dispatch of SPLs in industrial microgrids. Specifically, a lossless active-frontier action space is constructed, and a process-distance-guided action-processing mechanism reallocates excluded-action probabilities according to process distance and the actor's safe-action preference. Recursive process feasibility is established to guarantee admissible execution and feasible continuation. Furthermore, the expected process-correction distance is incorporated into PPO through a correction budget and a primal-dual update to internalize process knowledge into the raw policy, while a derived bound quantifies the raw policy's dependence on safety processing. Case studies using real-world data demonstrate zero process losses, electricity-cost reductions of 49.2% and 25.9% relative to rule-based scheduling and rolling MILP, respectively, within an acceptable computation time.

This paper proposes a geometry-based joint cross-modal token selection framework for latency-constrained multimodal token communications. To capture cross-modal token dependencies, we leverage the cross-attention mechanism to project modality-specific tokens into a shared query-key space, where the modality with the fewest tokens serves as the anchor modality and the others as non-anchor modalities. Inspired by germ-grain models, we define an angular-distance metric and construct semantic grain regions around anchor queries. Based on this geometric representation, we identify cross-modal evidence shared across multiple anchor queries in this space and develop an intersection-based token selection (IBS) strategy that prioritizes non-anchor tokens whose key are covered by multiple grain regions. We further develop an erasure-aware extension, termed robust-IBS (R-IBS), for token-wise erasure channels using an expected angular-distance formulation. In both IBS and R-IBS, the grain regions are optimized for individual queries under a latency constraint, using block coordinate descent and a low-complexity greedy algorithm. Simulations corroborate the effectiveness of IBS and R-IBS under latency-constrained and token-wise erasure channels, achieving up to 31.6% and 29.2% task accuracy gains on visual question answering (VQA) and audio-visual question answering (AVQA) tasks, respectively, over existing token selection baselines.

Motion retargeting approaches often prioritize kinematic similarity over whole-body dynamics, contact consistency, and actuation limits, yielding references that are difficult for reinforcement learning (RL) policies to reproduce, particularly for contact-rich behaviors. We present a contact-implicit, direct simulation-based multiple shooting (DSMS) framework that transforms kinematically feasible references into dynamically feasible whole-body trajectories. By embedding a differentiable simulator within a nonlinear program, DSMS resolves contact, friction, impacts, self-collision, and joint limits internally while enforcing tracking, actuation, and task constraints without prescribing a contact schedule or introducing explicit contact constraints. Compared with existing retargeting methods, DSMS accelerates motion-imitation RL training and yields policies with high success rates and low tracking error. We further demonstrate zero-shot sim-to-real transfer on the Unitree G1 through command-conditioned contact-rich crawling and a highly dynamic 180-degree jump-turn.

Microwave ablation (MWA) is a promising minimally invasive treatment for liver tumors, but its therapeutic outcome strongly depends on patient-specific planning of antenna insertion trajectory, power, and treatment duration. Accurate numerical simulation can provide physically reliable ablation predictions; however, its high computational cost limits its use in optimization-based planning, where repeated forward evaluations are required. To address this issue, we propose a digital twin-based automatic planning framework that combines a neural ablation prediction model with a genetic algorithm. The model was trained on multiphysics simulation data generated from patient-specific tumor and vessel structures, antenna configurations, and treatment conditions, and was used as a fast forward model during planning. The prediction model achieved a Dice score of 95.1%, enabling accurate deep learning-based optimization. In 13 unseen planning cases, the proposed method improved ablation efficiency by 54.3% and reduced organ damage by 55.0% compared with clinician-defined planning, while slightly shortening the insertion path length by 3.3%. Most generated plans were also judged clinically applicable by MWA specialists. Furthermore, the framework enabled approximately 420-fold faster planning than numerical-simulation-based planning, demonstrating its potential as a fast digital twin for quantitative and personalized MWA treatment planning. The code is available at: https://github.com/SeonAengCho/MWA-Planning.git

Model Predictive Control (MPC) delivers constraint-aware control, but its reliance on online optimization limits its use on systems with fast dynamics, high-dimensional models, or long horizons. Existing GPU implementations typically treat the device as a linear-algebra accelerator, leaving the optimization loop dependent on repeated kernel launches and high-latency memory transfers. This paper introduces CUDA MPC, a GPU-native MPC framework that co-designs the optimization algorithm, execution model, and memory architecture for CUDA hardware. CUDA MPC pairs a parallel-in-horizon alternating direction method of multipliers (ADMM) splitting with a fused CUDA kernel that runs the entire iterative solve on the device. Intermediate optimization variables stay in low-latency, on-chip shared memory, and a localized atomic-flag protocol synchronizes only adjacent horizon blocks, minimizing host intervention, kernel-dispatch overhead, and global-memory traffic. Across six nonlinear robotics benchmarks spanning increasing state dimension and constraint density, CUDA MPC sustains real-time rates at horizons one to two orders of magnitude longer than CPU solvers: it solves an optimization-based collision-avoidance parking problem with 100 s of lookahead within a 0.1 s sampling interval, and is the only solver evaluated that achieves both real-time execution and collision-free coordination for a centralized 10-agent swarm, where acados and CasADi return no feasible solution and require 3.5 s and 4.5 s per solve. Against tensor-framework implementations of the same ADMM splitting, the fused kernel is up to $965\times$ faster.

What is music style? Though often described using text labels such as "swing," "classical," or "emotional," the real style remains implicit and hidden in concrete music examples. In this paper, we introduce a cross-modal framework that learns implicit music styles from raw audio and applies them to symbolic music generation. Inspired by BLIP-2, our model leverages a Querying Transformer (Q-Former) to extract style representations from a large, pre-trained audio language model (LM), and further applies them to condition a symbolic LM for generating piano arrangements. We adopt a two-stage training strategy: contrastive learning to align auditory style with symbolic expression, followed by generative modeling for music arrangement. Our model generates piano performances jointly conditioned on a lead sheet (content) and a reference audio example (style), enabling controllable and stylistically faithful arrangement. Experiments demonstrate the effectiveness of our approach in piano cover generation, style transfer, and audio-to-MIDI retrieval, achieving substantial improvements in style-aware alignment and music quality.

Non-linear functions such as exponential and sigmoid are essential in AI and LLM acceleration, although implementing them efficiently on FPGAs is still costly. This paper proposes a PWL interpolation framework based on partial reconfiguration to reduce hardware cost while preserving flexibility. The architecture separates the design into a static region for communication and control, and a reconfigurable region where different interpolation modules can be dynamically loaded. Uniform and non-uniform segmentation strategies are evaluated for exponential and sigmoid functions using FP16 and FP32 arithmetic. Results show that non-uniform segmentation can improve accuracy in high-curvature regions, while uniform segmentation offers lower hardware overhead. At the system level, the reconfigurable implementation achieved significant area savings, reaching up to 43% less LUTs, 50% less flip-flops, BRAMs and DSPs cells, compared against a static design containing both operators; all this with predictable reconfiguration latency. These results show that partial reconfiguration is a practical approach for exploring area-latency trade-offs in FPGA-based acceleration of non-linear functions for LLM workloads.

Pretrained large language models (LLMs) have demonstrated in-context learning (ICL) capabilities for numerical inference over sequences serialized as text. Prior work has identified and characterized this form of numerical inference primarily through output-level evaluations such as prediction error. However, how numerical information is organized within LLM representations remains much less understood. To study this internal organization, we adopt a graph signal processing perspective in which attention induces a weighted graph over tokens, while token hidden states define signals on its nodes. Quantitative graph-spectral diagnostics and qualitative token-graph visualizations reveal that representations become more clearly differentiated by input dynamical complexity as context length increases. Simpler inputs produce attention-induced token graphs with stronger global connectivity and smoother, spectrally concentrated hidden-state signals, whereas more complex inputs produce more localized graphs and hidden-state signals with broader spectral support and greater high-frequency energy. Together, these findings point to systematic, context-dependent internal signatures associated with numerical ICL that are conserved across model families.

Orthogonal frequency-division multiplexing (OFDM) is widely adopted in frequency-selective channels for its ability to simplify equalization, yet it also causes large signal peaks, out-of-band (OOB) emissions, and spectral leakage. We study downlink precoding/combining for multi-user multiple-input multiple-output (MU-MIMO)–OFDM systems by minimizing the sum of the users' mean-squared errors (MSEs) under per-subcarrier transmit-power limits, per-antenna OOB spectral-mask constraints, and per-antenna peak-amplitude (clipping) constraints, which confine the emitted spectrum and limit waveform peaks to reduce power-amplifier saturation, nonlinear distortion, and spectral regrowth. The resulting nonconvex problem is handled by a minimum mean-squared error (MMSE) based block coordinate descent (BCD), with a closed-form combiner update and an alternating direction method of multipliers (ADMM) algorithm with closed-form updates for the precoder subproblem. Simulations show clear gains over well-known benchmark schemes.

Recent zero-shot text-to-speech (TTS) systems achieve remarkable naturalness and speaker similarity but typically require high-quality speaker prompts and either strip away or entangle the acoustic environment with speaker characteristics, limiting their real-world applicability. We present an extended DAIEN-TTS, an environment-aware zero-shot TTS framework that disentangles and jointly models speech, background noise, and reverberation, enabling independent control over timbre and acoustic environment through separate speaker and environment prompts. Built upon the flow-matching-based F5-TTS, it uses a speech-environment separation module to decompose environmental speech into speech, noise, and reverberation components, which are injected into the Diffusion Transformer for environment-aware generation. Training uses simulated data constructed by mixing clean speech with noise and room impulse responses, together with a cross-speaker conditioning strategy that suppresses speaker information leakage from the environment branch. When real-world data are available, the system can be further fine-tuned to bridge the simulated-to-real domain gap.At inference, a triple classifier-free guidance mechanism enables fine-grained control over speech, noise, and reverberation, and a signal-to-noise-ratio adaptation strategy aligns the synthesized speech with the environment prompt. Experiments on simulated and real-world test sets show that DAIEN-TTS generates environmental personalized speech with high naturalness, strong speaker similarity, and faithful noise and reverberation reproduction, while offering controllability beyond prior environment-aware TTS systems.

Nonlinear activation functions are widely used in machine learning workloads, but their direct hardware implementation is often costly, function-specific, or difficult to reuse across different models. This work introduces CAMTA, a 16-bit reconfigurable multi-region activation unit for nonlinear function approximation in FPGA and ASIC accelerators. CAMTA combines independent region thresholds, per-region polynomial degrees, coefficient sets, and execution modes over a shared Horner-based datapath. Unlike conventional polynomial or piecewise approximation units that mainly reconfigure coefficients or segment selection, CAMTA also reconfigures the computational behavior of each region through HORNER, CONST, ZERO, and IDENTITY modes, enabling the same hardware to support functions with different symmetry and tail behavior without resynthesis. FPGA validation on an AMD Alveo platform shows RMSE as low as \(3.60\times10^{-6}\) for CAMTA-assisted Softmax, outperforming the CORDIC-based Softmax baseline considered in this work by nearly one order of magnitude. FPGA HLS synthesis reports 3 DSPs, 802 FFs, 1756 LUTs, and an 11-cycle datapath latency. ASIC synthesis in TSMC 65~nm at 250~MHz reports \(6632.40~\mu\mathrm{m}^2\) total cell area and \(1.3634~\mathrm{mW}\) total power. Compared with a same-node, function-specific PLAC implementation, CAMTA incurs \(2.20\times\) area and \(1.75\times\) power overhead, in exchange for runtime configurability and reuse across multiple nonlinear functions.

This paper proposes a new automated decision-making framework to enhance the resilience of electrical systems against wildfires by applying operational strategies that account for decision-dependent uncertainty (DDU). The proposed framework incorporates both preventive and corrective measures, enabling adaptive and automated decision-making throughout the course of evolving wildfire scenarios. First, a baseline multistage optimization model is presented as a foundation to support wildfire-driven operational decision-making. The model then incorporates DDU, wherein Public Safety Power Shutoff (PSPS) decisions made in earlier stages influence the probabilities and parameters of future wildfire scenarios. To efficiently solve the resulting complex optimization problem, a mathematical decomposition algorithm is employed. The effectiveness of the proposed approach is demonstrated through case studies on the IEEE 30-bus system. Simulation results confirm that incorporating the impact of DDU into the optimization process provides more realistic, and operationally resilient solutions in the face of evolving wildfire threats.

This paper proposes a novel automated decision-support framework aimed at enhancing the resilience of power systems and operational resilience against wildfires by formulating the decision-making process as a stochastic multi-stage programming during a progressive wildfire. The paper develops a framework that takes into account both preventive and corrective actions, enabling automated and adaptive decisions based on potential scenarios over the course of a wildfire's progression. This approach considers the evolving nature of the wildfire threat and seeks to optimize the response strategies accordingly throughout its duration. The objective is to minimize wildfire risk and operational costs while reducing load curtailment. The framework accounts for potential contingencies caused by progressive wildfires. A novel algorithm is proposed to construct a decision tree based on wildfire progression and system geographical information. Additionally, a novel stochastic dual dynamic programming approach is deployed to solve the proposed optimization problem, achieving a global optimum for the framework. The effectiveness of the proposed method is demonstrated on the IEEE 30-bus system under various wildfire impact scenarios and is then applied to the IEEE 300-bus system to illustrate the scalability of the proposed approach. The results highlight the advantages of the proposed automated framework over a single-stage operational optimization strategy in enhancing power grid resilience under wildfire conditions.

The inertia constant H[s] is a fundamental indicator of power system resilience, linking power imbalance between generation and load to frequency deviation. It is essential in frequency reserve dispatch under stability-constrained optimal power flow (OPF), demand response (DR) in ancillary service, system decoupling and frequency control in modern power system. While the inertia constant is traditionally defined as the intrinsic kinetic energy of synchronous generators on bar normalized to the power base, this neglects the releasable power under nonlinear dynamics and control inside HVDC and Inverter-based Resources (IBRs). Accurate real-time inertia estimation is therefore essential to perform proper frequency control and to indicate the risks of failure in frequency restoration. It, however, is challenging with noisy frequency measurement under event-driven parameter jumps and locational transient responses. This paper presents a systematic comparative analysis on inertia estimation algorithms (IEAs) for frequency response applications. Classical methods such as filtering and fitting under measurement-based methods are benchmarked against data-based parameter estimation techniques such as recursive least squares (RLS) and model-based methods such as Kalman filtering (KF). The main contributions are: (i) a holistic review of model- and data-based inertia estimation methods, (ii) exploration on the effect of IEA to wind-based inertia emulation strategies. The findings underscore the need for robust, adaptive, and data-driven estimation frameworks to ensure secure operation of future low-inertia grids.