Archives AI News

arXiv:2509.00049v1 Announce Type: new Abstract: Accurate prediction of hydrogen sorption in clays, shales, and coals is vital for advancing underground hydrogen storage, natural hydrogen exploration, and radioactive waste containment. Traditional experimental methods, while foundational, are time-consuming, error-prone, and limited in capturing geological heterogeneity. This study introduces an adaptive physics-informed neural network (PINN) framework with multi-category feature engineering to enhance hydrogen sorption prediction. The framework integrates classical isotherm models with thermodynamic constraints to ensure physical consistency while leveraging deep learning flexibility. A comprehensive dataset consisting of 155 samples, which includes 50 clays, 60 shales, and 45 coals, was employed, incorporating diverse compositional properties and experimental conditions. Multi-category feature engineering across seven categories captured complex sorption dynamics. The PINN employs deep residual networks with multi-head attention, optimized via adaptive loss functions and Monte Carlo dropout for uncertainty quantification. K-fold cross-validation and hyperparameter optimization achieve significant accuracy (R2 = 0.979, RMSE = 0.045 mol per kg) with 67% faster convergence despite 15-fold increased complexity. The framework demonstrates robust lithology-specific performance across clay minerals (R2 = 0.981), shales (R2 = 0.971), and coals (R2 = 0.978), maintaining 85-91% reliability scores. Interpretability analysis via SHAP, accumulated local effects, and Friedman's H-statistics reveal that hydrogen adsorption capacity dominates predictions, while 86.7% of feature pairs exhibit strong interactions, validating the necessity of non-linear modeling approaches. This adaptive physics-informed framework accelerates site screening and enables risk-informed decision-making through robust uncertainty quantification.

arXiv:2509.00036v1 Announce Type: new Abstract: Diffusion models deliver state-of-the-art generative performance across diverse modalities but remain computationally expensive due to their inherently iterative sampling process. Existing training-free acceleration methods typically improve numerical solvers for the reverse-time ODE, yet their effectiveness is fundamentally constrained by the inefficiency of the underlying sampling trajectories. We propose A-FloPS (Adaptive Flow Path Sampler), a principled, training-free framework that reparameterizes the sampling trajectory of any pre-trained diffusion model into a flow-matching form and augments it with an adaptive velocity decomposition. The reparameterization analytically maps diffusion scores to flow-compatible velocities, yielding integration-friendly trajectories without retraining. The adaptive mechanism further factorizes the velocity field into a linear drift term and a residual component whose temporal variation is actively suppressed, restoring the accuracy benefits of high-order integration even in extremely low-NFE regimes. Extensive experiments on conditional image generation and text-to-image synthesis show that A-FloPS consistently outperforms state-of-the-art training-free samplers in both sample quality and efficiency. Notably, with as few as $5$ function evaluations, A-FloPS achieves substantially lower FID and generates sharper, more coherent images. The adaptive mechanism also improves native flow-based generative models, underscoring its generality. These results position A-FloPS as a versatile and effective solution for high-quality, low-latency generative modeling.

arXiv:2509.00046v1 Announce Type: new Abstract: The performance of Large Language Models is influenced by their characteristics such as architecture, model sizes, decoding methods and so on. Due to differences in structure or function, the weights in different layers of large models have varying distributions. This paper explores the correlations between different types of layers in terms of weights distribution and studies the potential impact of these correlations on LoRA training effectiveness. Firstly, the study reveals that in the model the cosine distances between weights of different layers manifest power-law distribution. We extract Query-projection, down-projection and other weight matrices from the self-attention layers and MLP layers, calculate the singular values of the matrices using singular value decomposition, and organize a certain number of singular values into matrices according to projection's type. By analyzing the probability distribution of the cosine distances between these matrices, it is found that the cosine distances values between them have distinct power-law distribution characteristics. Secondly, based on the results of distance calculations and analysis across different layers of model, a qualitative method is proposed to describe the distribution characteristics of different models. Next, to construct weights that align with the distribution characteristics, a data generator is designed using a combination of Gaussian process and Pareto distribution functions. The generator is used to simulate the generation of data that aligns with specific distribution characteristics. Finally, based on the aforementioned distribution characteristics and data generation method, the weights in LoRA initialization are reshaped for training. Experimental results indicate that, without altering the model structure or training process, this method achieves a certain improvement in the performance of LoRA training.

arXiv:2509.00035v1 Announce Type: new Abstract: Accurate prediction of chip performance is critical for ensuring energy efficiency and reliability in semiconductor manufacturing. However, developing minimum operating voltage ($V_{min}$) prediction models at advanced technology nodes is challenging due to limited training data and the complex relationship between process variations and $V_{min}$. To address these issues, we propose a novel transfer learning framework that leverages abundant legacy data from the 16nm technology node to enable accurate $V_{min}$ prediction at the advanced 5nm node. A key innovation of our approach is the integration of input features derived from on-chip silicon odometer sensor data, which provide fine-grained characterization of localized process variations -- an essential factor at the 5nm node -- resulting in significantly improved prediction accuracy.

arXiv:2509.00034v1 Announce Type: new Abstract: Steel casting processes are vulnerable to financial losses due to slag flow contamination, making accurate slag flow condition detection essential. This study introduces a novel cross-domain diagnostic method using vibration data collected from an industrial steel foundry to identify various stages of slag flow. A hybrid deep learning model combining one-dimensional convolutional neural networks and long short-term memory layers is implemented, tested, and benchmarked against a standard one-dimensional convolutional neural network. The proposed method processes raw time-domain vibration signals from accelerometers and evaluates performance across 16 distinct domains using a realistic cross-domain dataset split. Results show that the hybrid convolutional neural network and long short-term memory architecture, when combined with root mean square preprocessing and a selective embedding data loading strategy, achieves robust classification accuracy, outperforming traditional models and loading techniques. The highest test accuracy of 99.10 +/- 0.30 demonstrates the method's capability for generalization and industrial relevance. This work presents a practical and scalable solution for real-time slag flow monitoring, contributing to improved reliability and operational efficiency in steel manufacturing.

arXiv:2509.00031v1 Announce Type: new Abstract: Quantization is an effective technique to reduce the deployment cost of large language models (LLMs), and post-training quantization (PTQ) has been widely studied due to its efficiency. However, existing low-bit PTQ methods suffer from accuracy degradation because their layer-wise optimization introduces cumulative error propagation and misalignment between local reconstruction objectives and downstream performance. While quantization-aware training (QAT) provides a principled solution, its reliance on backpropagation incurs prohibitive data, time, and memory costs, limiting its practicality. To address these challenges, we propose ZeroQAT, a zeroth-order optimization-based QAT framework. ZeroQAT leverages forward-only gradient estimation to eliminate the need for backpropagation, significantly reducing computational and memory overhead while retaining the benefits of end-to-end optimization. Moreover, ZeroQAT jointly learns quantized weights, weight clipping thresholds, and equivalent transformations to mitigate quantization error and handle activation outliers. Experiments demonstrate that ZeroQAT achieves the efficiency of PTQ while retaining the accuracy of QAT, offering a practical solution for high-quality low-bit quantization of LLMs.

arXiv:2410.23300v3 Announce Type: replace-cross Abstract: Collaborative Filtering (CF) methods dominate real-world recommender systems given their ability to learn high-quality, sparse ID-embedding tables that effectively capture user preferences. These tables scale linearly with the number of users and items, and are trained to ensure high similarity between embeddings of interacted user-item pairs, while maintaining low similarity for non-interacted pairs. Despite their high performance, encouraging dispersion for non-interacted pairs necessitates expensive regularization (e.g., negative sampling), hurting runtime and scalability. Existing research tends to address these challenges by simplifying the learning process, either by reducing model complexity or sampling data, trading performance for runtime. In this work, we move beyond model-level modifications and study the properties of the embedding tables under different learning strategies. Through theoretical analysis, we find that the singular values of the embedding tables are intrinsically linked to different CF loss functions. These findings are empirically validated on real-world datasets, demonstrating the practical benefits of higher stable rank, a continuous version of matrix rank which encodes the distribution of singular values. Based on these insights, we propose an efficient warm-start strategy that regularizes the stable rank of the user and item embeddings. We show that stable rank regularization during early training phases can promote higher-quality embeddings, resulting in training speed improvements of up to 66%. Additionally, stable rank regularization can act as a proxy for negative sampling, allowing for performance gains of up to 21% over loss functions with small negative sampling ratios. Overall, our analysis unifies current CF methods under a new perspective, their optimization of stable rank, motivating a flexible regularization method.

arXiv:2509.00050v1 Announce Type: new Abstract: We apply deep learning techniques for anomaly detection to analyze activity of Russian-owned resident space objects (RSO) prior to the Ukraine invasion and assess the results for any findings that can be used as indications and warnings (I&W) of aggressive military behavior for future conflicts. Through analysis of anomalous activity, an understanding of possible tactics and procedures can be established to assess the existence of statistically significant changes in Russian RSO pattern of life/pattern of behavior (PoL/PoB) using publicly available two-line element (TLE) data. This research looks at statistical and deep learning approaches to assess anomalous activity. The deep learning methods assessed are isolation forest (IF), traditional autoencoder (AE), variational autoencoder (VAE), Kolmogorov Arnold Network (KAN), and a novel anchor-loss based autoencoder (Anchor AE). Each model is used to establish a baseline of on-orbit activity based on a five-year data sample. The primary investigation period focuses on the six months leading up to the invasion date of February 24, 2022. Additional analysis looks at RSO activity during an active combat period by sampling TLE data after the invasion date. The deep learning autoencoder models identify anomalies based on reconstruction errors that surpass a threshold sigma. To capture the nuance and unique characteristics of each RSO an individual model was trained for each observed space object. The research made an effort to prioritize explainability and interpretability of the model results thus each observation was assessed for anomalous behavior of the individual six orbital elements versus analyzing the input data as a single monolithic observation. The results demonstrate not only statistically significant anomalies of Russian RSO activity but also details anomalous findings to the individual orbital element.

arXiv:2505.12552v2 Announce Type: replace-cross Abstract: Reconstructing natural images from functional magnetic resonance imaging (fMRI) data remains a core challenge in natural decoding due to the mismatch between the richness of visual stimuli and the noisy, low resolution nature of fMRI signals. While recent two-stage models, combining deep variational autoencoders (VAEs) with diffusion models, have advanced this task, they treat all spatial-frequency components of the input equally. This uniform treatment forces the model to extract meaning features and suppress irrelevant noise simultaneously, limiting its effectiveness. We introduce FreqSelect, a lightweight, adaptive module that selectively filters spatial-frequency bands before encoding. By dynamically emphasizing frequencies that are most predictive of brain activity and suppressing those that are uninformative, FreqSelect acts as a content-aware gate between image features and natural data. It integrates seamlessly into standard very deep VAE-diffusion pipelines and requires no additional supervision. Evaluated on the Natural Scenes dataset, FreqSelect consistently improves reconstruction quality across both low- and high-level metrics. Beyond performance gains, the learned frequency-selection patterns offer interpretable insights into how different visual frequencies are represented in the brain. Our method generalizes across subjects and scenes, and holds promise for extension to other neuroimaging modalities, offering a principled approach to enhancing both decoding accuracy and neuroscientific interpretability.

arXiv:2509.00057v1 Announce Type: new Abstract: Machine learning-based failure management in optical networks has gained significant attention in recent years. However, severe class imbalance, where normal instances vastly outnumber failure cases, remains a considerable challenge. While pre- and in-processing techniques have been widely studied, post-processing methods are largely unexplored. In this work, we present a direct comparison of pre-, in-, and post-processing approaches for class imbalance mitigation in failure detection and identification using an experimental dataset. For failure detection, post-processing methods-particularly Threshold Adjustment-achieve the highest F1 score improvement (up to 15.3%), while Random Under-Sampling provides the fastest inference. In failure identification, GenAI methods deliver the most substantial performance gains (up to 24.2%), whereas post-processing shows limited impact in multi-class settings. When class overlap is present and latency is critical, over-sampling methods such as the SMOTE are most effective; without latency constraints, Meta-Learning yields the best results. In low-overlap scenarios, Generative AI approaches provide the highest performance with minimal inference time.