6760 papers
This paper addresses the sub-wavelength sensing accuracy limitations in bistatic wireless systems caused by clock asynchronism by deriving a quantitative mapping between distorted channel ratios and ideal features, enabling a robust framework that leverages signal amplitude to reconstruct fine-grained displacement details with nearly an order-of-magnitude improvement.
This paper proposes an enhanced Random Subspace Local Projection (RSLP) framework that integrates weighted aggregation, category-aware sampling, adaptive sizing, and bootstrap inference to achieve robust impulse response estimation and reliable finite-sample inference for high-dimensional time series, significantly reducing estimator variability and narrowing confidence intervals compared to traditional methods.
This paper introduces BoT, a unified, size-agnostic framework that treats model weights as continuous signals to enable efficient bidirectional knowledge transfer between models of different sizes using Discrete Wavelet Transforms, achieving significant pre-training FLOPs savings and state-of-the-art performance.
This paper presents OCLADS, a novel communication framework that combines intelligent sample selection on resource-constrained IoT devices with distribution-shift detection at an edge server to enable efficient online continual learning for anomaly detection in non-stationary environments.
This paper establishes a unified theoretical framework demonstrating that drifting models, which optimize kernel-based mean-shift discrepancies, are mathematically equivalent to score-matching objectives on kernel-smoothed distributions, thereby precisely connecting them to diffusion models and clarifying their relationship with Distribution Matching Distillation.
This study proposes a reinforcement learning-based framework using Proximal Policy Optimization (PPO) and Soft Actor-Critic (SAC) to dynamically optimize solar panel cleaning schedules in arid regions, demonstrating that PPO achieves up to 13% cost savings compared to traditional methods by effectively adapting to uncertain environmental conditions.
This paper proposes a full-data, privacy-preserving conformal prediction framework that leverages differential privacy-induced stability to avoid the sample size reduction inherent in data-splitting methods, achieving sharper prediction sets and asymptotic recovery of nominal coverage levels.
This paper introduces FRONT, a training-free framework that extracts a model's task-agnostic "learngene" from the low-frequency components of its weights using Discrete Cosine Transform, enabling efficient initialization of downstream models of arbitrary scales while significantly accelerating convergence and reducing training costs.
This paper proposes a neural dynamics-informed pre-trained framework that overcomes the limitations of traditional atlas-based methods by extracting personalized neural activity representations to guide brain parcellation and correlation estimation, thereby achieving superior performance in constructing personalized brain functional networks across heterogeneous scenarios.
This paper proposes a data-driven surrogate model combining convolutional autoencoders and neural ordinary differential equations to generate rapid, accurate spatiotemporal predictions of laser-induced rocket ignition, thereby enabling efficient exploration of complex design spaces and uncertainty quantification at a fraction of the computational cost of traditional simulations.
This paper introduces Obliviator, an iterative post-hoc concept erasure method that effectively removes unwanted attributes against nonlinear adversaries while preserving task utility, thereby quantifying and revealing the dynamics of the utility-erasure trade-off.
DreamSAC is a framework that enhances extrapolative generalization in physics simulations by combining an unsupervised symmetry exploration strategy, which actively probes conservation laws via a Hamiltonian-based curiosity bonus, with a Hamiltonian-based world model that learns invariant physical states from raw observations through a novel contrastive objective.
The paper introduces COOL-MC, a framework that verifies and explains reinforcement learning policies for multi-bridge network maintenance by applying probabilistic model checking and explainability methods to a PRISM-encoded Markov decision process, thereby revealing safety violation probabilities and systematic policy biases.
This paper demonstrates that a data-centric approach utilizing careful preprocessing, class balancing, and a simplified CNN-VAE architecture can achieve competitive ECG classification performance on the PTB-XL dataset with significantly reduced model complexity, highlighting the importance of data quality over architectural intricacy in medical signal analysis.
The paper proposes GRD-Net, a novel architecture combining a generative adversarial network with a region-of-interest attention module to improve industrial surface anomaly detection and localization by learning from normal products and synthetic defects while focusing on relevant areas, thereby reducing reliance on biased post-processing algorithms.
This paper re-evaluates the state-of-the-art LiRA membership inference attack under realistic conditions, demonstrating that its effectiveness is significantly overestimated in prior studies due to overconfident models, improper threshold calibration, and unrealistic priors, thereby revealing that reliable privacy auditing requires protocols that reflect practical training practices and reproducibility constraints.
This paper introduces a novel generative neural solver that fuses discrete noise graph diffusion models with autoregressive reinforcement learning to dynamically learn and integrate constraint assignment matrices, thereby overcoming the robustness and generalization limitations of existing attention-based methods and achieving state-of-the-art performance across a comprehensive 378-combinatorial space of vehicle routing problem benchmarks.
This paper systematically evaluates four training objectives—Cross-Entropy, Prototype, Triplet, and Average Precision Losses—for out-of-distribution detection in image classification, revealing that while they achieve comparable in-distribution accuracy, Cross-Entropy Loss delivers the most consistent performance across both near- and far-OOD scenarios under standardized protocols.
This paper introduces TS-MLLM, a novel multi-modal large language model framework that integrates temporal signals, frequency-domain images, and textual knowledge through specialized patch modeling and attention fusion mechanisms to significantly enhance industrial time-series analysis and prognostics.
This paper presents a semi-supervised deep generative anomaly detection framework, utilizing a residual autoencoder with a dense bottleneck, that achieves high-accuracy, real-time defect detection and localization on high-speed pharmaceutical Blow-Fill-Seal production lines while operating within strict 500 ms timing constraints.