Neural and Evolutionary Computing Papers of the Week

We present SwarmEvolve, a framework in which hundreds of low-cost agents per round work in swarms, reason in latent space without decoding to text, and share information by passing KV caches.

This study presents a novel hybrid framework that integrates Physics-Informed Neural Networks (PINNs) with boosting methods to enhance the accuracy and robustness of solutions for Lane-Emden type differential equations.

We solve the equation by defining three synthetic cases - linear (\(\eta=0.001\), \(\gamma=10^{-6}\)), shock-dominated (\(\eta=0.02\), \(\gamma=10^{-6}\)), and dissipation-dominated (\(\eta=0.01\), \(\gamma=5\times10^{-4}\)) - and using Physics-Informed Neural Networks (PINNs) to showcase the solution.

ABSTRACT This study aimed to develop an interpretable machine learning framework using plantar‐pressure sensors to estimate knee moments during rugby‐specific movements.

In this paper, we introduce Agentic Soft-Token Compression (ASTC), a training-free compression method using soft tokens within LLM agent for long-horizon tasks.

This study benchmarks three distinct feature selection algorithms (Genetic Algorithm (GA), Differential Evolution (DE), Relief-F) to determine whether a universal feature set comprising common, shared features identified across subjects can be reliably established, thereby reducing or eliminating the need for subject-specific feature optimization.

This study proposes a multi-objective sizing and operation framework for an autonomous bifacial photovoltaic (bPV) water-supply pumping system, coupling dynamic borehole hydraulics, battery and water storage, and component degradation within a consistent evaluation chain from optimization through life-cycle post-verification.

A key challenge is identifying physically interpretable transport models from sparse observational data.

We propose a structured visual representations landscape and design an activation-based prior that allows us to effectively regularize the landscape with activations from brain regions or neural network units.

This study presents, to the best of our knowledge, two independent and complementary analytical strategies for the simultaneous quantification of tiotropium bromide (TBM) and olodaterol hydrochloride (OLH) in laboratory-prepared mixtures and the pharmaceutical formulation Stiolto ® Respimat.

Additionally, the fusion model exhibits a received signal strength index of -68 dBm, a coherent bandwidth of 25 MHz, a throughput of 320 Mbps, and a delay as low as 15ms, all of which are superior to those of comparative models. The proposed hybrid method effectively enhances the propagation performance of 5G signals in coal mine tunnels, reduces path loss, improves signal quality, and provides a valuable approach for studying electromagnetic wave propagation in such environments.

This paper proposes an optimal proportional-integral (PI) controller scheme to improve the dynamic performance of a grid-connected AquaBuOY wave energy conversion system (WECS).

Data from 19 adults walking at 1.2 m s−1 drove a reduced plantarflexor model with fixed unassisted kinematics; force, travel and moment limits were checked on every stride.

ABSTRACT In underground engineering construction, accurate prediction of surface settlement constitutes a critical challenge for ensuring the safety of urban infrastructure. Addressing the limitations of conventional prediction methods—such as their reliance on empirical parameters, low computational efficiency, and poor adaptability to complex geological conditions—this study proposes a Genetic Algorithm-Back Propagation (GA-BP) neural network-based predictive approach.