February 2026

The railway sector plays a vital role in passenger transportation, economic growth, and large-scale urban development. Despite continuous improvements in signaling and control systems, railway safety remains a major concern due to frequent incidents caused by track obstructions such as unauthorized human intrusions, animals, vehicles, and miscellaneous foreign objects. Existing railway monitoring systems rely heavily on manual inspection, physical barriers, and rule-based alerts, which suffer from delayed response times, limited coverage, high maintenance costs, and reduced reliability under […]

Ver mais

Deep learning has driven remarkable progress in visual recognition, yet state-of-the-art models remain heavily reliant on large-scale labeled datasets and high-performance GPU infrastructure, assumptions that rarely hold in real-world industrial settings where data is scarce and deployment occurs on CPU-based systems. This working paper introduces the Ensemble Spatial-Agnostic Basis Adaptation Network (Ensemble SABA-Net), a lightweight classification framework explicitly designed for low-data and resource-constrained environments. The proposed architecture departs from conventional convolutional and attention-based designs by operating directly on […]

Ver mais

In this paper, we introduce and systematically investigate novel classes of vector-valued multiplier spaces associated with operator-valued series, utilizing the concepts of ( f )-statistical and weak ( f )-statistical convergence. We begin by studying the topological properties of these newly defined spaces, establishing that their completeness is completely characterized by the ( c_0(X)- ) multiplier convergence of the underlying series. Building upon this structural foundation, we then explore the precise relationships between these ( f )-statistical spaces […]

Ver mais

Hyperparameter optimization (HPO) is known to be costly in deep learning, especially when leveraging automated approaches. Most of the existing automated HPO methods are accuracy-based, i.e., accuracy metrics are used to guide the trials of different hyperparameter configurations amongst a specific search space. However, many trials may encounter severe training problems, such as vanishing gradients and insufficient convergence, which can hardly be reflected by accuracy metrics in the early stages of the training and often result in poor […]

Ver mais

Table of Links Abstract and 1. Introduction Related Work and Background Analysis 3.1 Limitations about Existing ReLUficatio 3.2 dReLU Are Neurons in Expert still Sparsely Activated? dReLU Sparsification Experiments Results 6.1 Downstream Tasks Performance 6.2 Sparsity of Sparsified Models Practical Inference Speedup Evaluation 7.1 Experiments Setting 7.2 Pure CPU Inference and 7.3 Hybrid GPU-CPU Inference 7.4 Deploy LLMs on mobile phones Conclusion and References A. Appendix / supplemental material B. Limitation C. Broader Impact 3.2 dReLU We introduce […]

Ver mais

Work on multi-scale organization and audit-based directionality lacks a minimal-substrate theorem: key primitives are often realized only by smuggling in external schedules, ad hoc audits, or declared quotients, making results hard to verify and compare across substrates. We introduce a no-smuggling minimal-substrate semantics for SPT, operationalize it via matched-control audit tests on finite stochastic machines, and demonstrate separations between protocol artifacts, intrinsic drive, and route-dependent packaging defects. Operationally, we define a canonical machine class ( mathcal S_{min} ) […]

Ver mais

Table of Links Abstract and 1. Introduction Related Work and Background Analysis 3.1 Limitations about Existing ReLUficatio 3.2 dReLU Are Neurons in Expert still Sparsely Activated? dReLU Sparsification Experiments Results 6.1 Downstream Tasks Performance 6.2 Sparsity of Sparsified Models Practical Inference Speedup Evaluation 7.1 Experiments Setting 7.2 Pure CPU Inference and 7.3 Hybrid GPU-CPU Inference 7.4 Deploy LLMs on mobile phones Conclusion and References A. Appendix / supplemental material B. Limitation C. Broader Impact 3 Analysis 3.1 Limitations […]

Ver mais

Table of Links Abstract and 1. Introduction Related Work and Background Analysis 3.1 Limitations about Existing ReLUficatio 3.2 dReLU Are Neurons in Expert still Sparsely Activated? dReLU Sparsification Experiments Results 6.1 Downstream Tasks Performance 6.2 Sparsity of Sparsified Models Practical Inference Speedup Evaluation 7.1 Experiments Setting 7.2 Pure CPU Inference and 7.3 Hybrid GPU-CPU Inference 7.4 Deploy LLMs on mobile phones Conclusion and References A. Appendix / supplemental material B. Limitation C. Broader Impact 2 Related Work and […]

Ver mais

This paper addresses the problem of enterprise risk identification in complex and dynamic business environments by proposing a risk prediction method based on lightweight neural networks. A unified data representation is first constructed to embed multi-source heterogeneous features of enterprises, allowing inputs to be effectively expressed in a low-dimensional space. The model structure combines grouped convolution and depthwise separable convolution to reduce parameter size and computational complexity while preserving the ability to capture key patterns. To further enhance […]

Ver mais

Table of Links Abstract and 1. Introduction Related Work and Background Analysis 3.1 Limitations about Existing ReLUficatio 3.2 dReLU Are Neurons in Expert still Sparsely Activated? dReLU Sparsification Experiments Results 6.1 Downstream Tasks Performance 6.2 Sparsity of Sparsified Models Practical Inference Speedup Evaluation 7.1 Experiments Setting 7.2 Pure CPU Inference and 7.3 Hybrid GPU-CPU Inference 7.4 Deploy LLMs on mobile phones Conclusion and References A. Appendix / supplemental material B. Limitation C. Broader Impact Abstract Exploiting activation sparsity […]

Ver mais