Frequency-Aware Attention-LSTM for PM$_{2.5}$ Time Series Forecasting

To enhance the accuracy and robustness of PM$_{2.5}$ concentration forecasting, this paper introduces FALNet, a Frequency-Aware LSTM Network that integrates frequency-domain decomposition, temporal modeling, and attention-based refinement. The model first applies STL and FFT to extract trend, seasonal, and denoised residual components, effectively filtering out high-frequency noise. The filtered residuals are then fed into a stacked LSTM to capture long-term dependencies, followed by a multi-head attention mechanism that dynamically focuses on key time steps. Experiments conducted on real-world urban air quality datasets demonstrate that FALNet consistently outperforms conventional models across standard metrics such as MAE, RMSE, and $R^2$. The model shows strong adaptability in capturing sharp fluctuations during pollution peaks and non-stationary conditions. These results validate the effectiveness and generalizability of FALNet for real-time air pollution prediction, environmental risk assessment, and decision-making support.

Annealing Flow Generative Model Towards Sampling High-Dimensional and Multi-Modal Distributions

Sampling from high-dimensional, multi-modal distributions remains a fundamental challenge across domains such as statistical Bayesian inference and physics-based machine learning. In this paper, we propose Annealing Flow (AF), a continuous normalizing flow-based approach designed to sample from high-dimensional and multi-modal distributions. The key idea is to learn a continuous normalizing flow-based transport map, guided by annealing, to transition samples from an easy-to-sample distribution to the target distribution, facilitating effective exploration of modes in high-dimensional spaces. Unlike many existing methods, AF training does not rely on samples from the target distribution. AF ensures effective and balanced mode exploration, achieves linear complexity in sample size and dimensions, and circumvents inefficient mixing times. We demonstrate the superior performance of AF compared to state-of-the-art methods through extensive experiments on various challenging distributions and real-world datasets, particularly in high-dimensional and multi-modal settings. We also highlight the potential of AF for sampling the least favorable distributions.

Bayesian-Boosted MetaLoc: Efficient Training and Guaranteed Generalization for Indoor Localization

Existing localization approaches utilizing environment-specific channel state information (CSI) excel under specific environment but struggle to generalize across varied environments. This challenge becomes even more pronounced when confronted with limited training data. To address these issues, we present the Bayes-Optimal Meta-Learning for Localization (BOML-Loc) framework, inspired by the PAC-Optimal Hyper-Posterior (PACOH) algorithm. Improving on our earlier MetaLoc~\cite{MetaLoc}, BOML-Loc employs a Bayesian approach, reducing the need for extensive training, lowering overfitting risk, and offering per-test-point uncertainty estimation. Even with very limited training tasks, BOML-Loc guarantees robust localization and impressive generalization. In both LOS and NLOS environments with site-surveyed data, BOML-Loc surpasses existing models, demonstrating enhanced localization accuracy, generalization abilities, and reduced overfitting in new and previously unseen environments.

MetaLoc: Learning to Learn Wireless Localization

The existing indoor fingerprinting localization methods are rather accurate after intensive offline calibration for a specific environment, no matter based on received signal strength (RSS) or channel state information (CSI), but the well-calibrated localization model (can be a pure statistical one or a data-driven one) will present poor generalization ability in the highly variable environments, which results in big loss in knowledge and human effort. To break the environment-specific localization bottleneck, we propose a new-fashioned data-driven fingerprinting method for localization based on model-agnostic meta-learning (MAML), named by MetaLoc. Specifically, MetaLoc is char acterized by rapldly adapting itself to a new, possibly unseen environment with very little calibration. The underlying localization model is taken to be a deep neural network, and we train an optimal set of environment-specific meta-parameters by leveraging previous data collected from diverse well-calibrated indoor environments and the maximum mean discrepancy criterion. We further modify the loss function of vanilla MAML and propose a novel framework named as MAML-DG, which is able to achieve faster convergence and better adaptation abilities by forcing the loss on different training domains to decrease in similar directions. Experiments from simulation and site survey confirm that the meta-parameters obtained for MetaLoc achieves very rapid adaptation to new environments, competitive localization accuracy, and high resistance to significantly reduced reference points (RPs), saving a lot of calibration effort.